Newsgroups: comp.speech,comp.answers,news.answers Subject: comp.speech Frequently Asked Questions - part 3/3 From: andrew.hunt@east.sun.com (Andrew Hunt) Reply-To: andrew.hunt@east.sun.com (Andrew Hunt) Followup-To: comp.speech Organization: Speech Applications Group, Sun Microsystems Laboratories Summary: Information on Speech Technology Approved: news-answers-request@MIT.Edu Archive-name: comp-speech-faq/part3 Last-modified: 1997/09/06 URL: http://www.speech.su.oz.au/comp.speech/ COMP.SPEECH FAQ POSTING - PART 3/3 [Note: this document has been automatically extracted from a WWW site: http://www.speech.su.oz.au/comp.speech/ This may introduce some formatting errors.] Speech Synthesis comp.speech FAQ Section 5 * SpeechLinks: Speech Synthesis * Q5.1: What is speech synthesis? * Q5.2: How can speech synthesis be performed? * Q5.3: References/Books on Synthesis * Q5.4: Speech Synthesis on the WWW * Q5.5: Speech Synthesis Software/Hardware ___________________________________________________________________________ Q5.1: What is speech synthesis? Speech synthesis programs convert written input to spoken output by automatically generating synthetic speech. Speech synthesis is often referred to a "Text-to-Speech" conversion (TTS). ___________________________________________________________________________ Q5.2: Performing speech synthesis There are several algorithms. The choice depends on the task they're used for. The easiest way is to just record the voice of a person speaking the desired phrases. This is useful if only a restricted volume of phrases and sentences is used, e.g. messages in a train station, or schedule information via phone. The quality depends on the way recording is done. More sophisticated but worse in quality are algorithms which split the speech into smaller pieces. The smaller those units are, the less are they in number, but the quality also decreases. An often used unit is the phoneme, the smallest linguistic unit. Depending on the language used there are about 35-50 phonemes in western European languages, i.e. there are 35-50 single recordings. The problem is combining them as fluent speech requires fluent transitions between the elements. The intellegibility is therefore lower, but the memory required is small. A solution to this dilemma is using diphones. Instead of splitting at the transitions, the cut is done at the center of the phonemes, leaving the transitions themselves intact. This gives about 400 elements (20*20) and the quality increases. The longer the units become, the more elements are there, but the quality increases along with the memory required. Other units which are widely used are half-syllables, syllables, words, or combinations of them, e.g. word stems and inflectional endings. The Museum of Speech Analysis and Synthesis has pictures of artificial speech systems going back over 150 years: worth a visit. ( http://mambo.ucsc.edu/psl/smus/smus.html) ___________________________________________________________________________ Q5.3: References/Books on Synthesis Books and Papers * Thierry Dutoit, An Introduction to Text-to-Speech Synthesis, Kluwer Academic Publishers (Dordrecht), 1997, ISBN 0-7923-4498-7, 312 pages. Volume 3 in the series on Text, Speech and Language Technology. * Douglas O'Shaughnessy, Speech Communication: Human and Machine Addison Wesley series in Electrical Engineering: Digital Signal Processing, 1987. * T.V. Raman, Auditory User Interfaces --Toward The Speaking Computer Kluwer Academic Publishers, Boston, ISBN 0-7923-9984-6, August 1997, 168 pp. * D. H. Klatt, "Review of Text-To-Speech Conversion for English", Jnl. of the Acoustic Society of America (JASA), Vol 82, pp 737-793. * "Talking Machines, Theories, Models and Designs" Eds, G. Bailly & C. Benoit (Elsevier: North Holland) * I. H. Witten. Principles of Computer Speech, London: Academic Press, Inc., 1982. * W.B. Kleijn and K.K. Paliwal (Eds.), Speech Coding and Synthesis, Elsevier, Amsterdam, 1995. Contents, preface etc on the WWW: http://www.elsevier.nl/section/engtech/scs/menu.htm * John Allen, Sharon Hunnicut and Dennis H. Klatt, "From Text to Speech: The MITalk System", Cambridge University Press, 1987. * J.P.H. van Santen, R. W. Sproat, J. P. Olive, and J. Hirschberg, "Progress in Speech Synthesis", Springer, 1996. On the WWW * Survey of the State of the Art in Human Language Technology Report edited by Ronald A. Cole et. al. with a section on Text-to-Speech Technologies. http://www.cse.ogi.edu/CSLU/HLTsurvey/ch5node1.html Bibliographies and Reference Lists * WWW searchable online-bibiliography for Phonetics and Speech Technology with more than 8000 entries. Provided by Institut fur Phonetik at Johann Wolfgang Goethe-Universitat Frankfurt. http://www.uni-frankfurt.de/~ifb/bib_engl.html * Computational Speech Processing: Speech Analysis, Recognition, Understanding, Compression, Transmission, Coding, Synthesis ; Text to Speech Systems, Speech to Tactile Displays, Speaker Identification, Prosody Processing : BIBLIOGRAPHY, by Conrad F. Sabourin, 1994, 2 volumes, 1187p, ISBN 2-921173-21-2, INFOLINGUA inc., P.O. Box 187 Snowdon, Montreal, H3X 3T4, Canada. See also: http://gomer.mlink.net/infolingua.html ___________________________________________________________________________ Q5.4: Speech Synthesis on the WWW Most of the following are links to WWW pages with demonstrations of speech synthesis. Plenty more links are included in the detailed list of speech synthesis software/hardware in Q5.5. Speech Synthesis "Museum" URL: http://www.cs.bham.ac.uk/~jpi/synth/museum.html Maintained by Jon Iles (j.p.iles@cs.bham.ac.uk) at the University of Birmingham. Information and speech samples for + YorkTalk + Loughborough Sound Images + University of Birmingham - FDFS + Eurovocs + DECtalk + AT&T Bell Labs Synthesiser + S.W.A.Ll.C. - Welsh Synthesis from CSTR + All-Prosodic Speech Synthesis - IPOX + Orator from Bellcore The Festival Speech Synthesis System http://www.cstr.ed.ac.uk/projects/festival.html Pre-synthesized examples in English, Welsh and Spanish, and online demo of English. Pavarobotti http://www.shc.uiowa.edu/fun/pavarobotti/pavarobotti.html WWW demo of the Pavarobotti synthesis technology developed at the National Center for Voice and Speech (http://www.shc.uiowa.edu/ncvs_home.html). Say... http://wwwtios.cs.utwente.nl/say WWW demo of the rsynth speech synthesis software. The WWW capability was implemented by Axel Belinfante. Musee sonore de la synthese de la Parole en francais http://www.icp.grenet.fr/exemples_synthese/ex.html Speech synthesis examples from a series of French language speech synthesisers plus links to other speech synthesis demo pages. + ICP-Grenoble + CNET-Lannion (with TD-PSOLA) + KTH-Stockholm + Universite-Mons - several versions Lucent Technologies Bell Labs Text-to-Speech http://www.bell-labs.com/project/tts/ Demos and samples of the latest Lucent Technologies Bell Labs Text-to-Speech system. WATSON FlexTalk from AT&T Advanced Speech Products Group http://www.att.com/aspg/demo.html WWW interface to the WATSON FlexTalk speech synthesis demonstration. AT&T Bell Laboratories Voices http://www.research.att.com/cgi-bin/cgiwrap/mjm/voices.cgi WWW interface to the AT&T Bell Laboratories text to speech (TTS) synthesizer Laureate from British Telecom http://www.labs.bt.com/innovate/speech/laureate/ Demo of the Laureate speech synthesis system - not yet commercially available. ORATOR from Bellcore Online demo of the ORATOR system developed at Bellcore. http://www.bellcore.com/ORATOR/ SVOX from TIK, ETH in Zurich http://www.tik.ee.ethz.ch/cgi-bin/w3svox Demo of German speech synthesis from Institut fur Technische Informatik und Kommunikationsnetze. Speech Synthesis Research at OGI http://www.cse.ogi.edu/CSLU/research/TTS Examples of diphone speech corpora and algorithms developed at OGI for synthesis of American English and Mexican Spanish using the Festival framework. Lyricos http://www.cse.ogi.edu/CSLU/research/TTS/research/sing.html Demos of the Lyricos singing voice synthesis system. Concatenation-based synthesis of singing voice from MIDI input. Multi-Lingual TTS from Gerhard-Mercator University, Duisburg http://www.fb9-ti.uni-duisburg.de/demos/speech.html Synthesis in German, English or Japanese. TMH: Institutionen for Taloverforing och Musikakustik, Kungliga Tekniska Hogskolan http://www.speech.kth.se/info/software.html Synthesis in Swedish, Finish, Norwegian, Icelandic, Danish, British and American English, French, German, Italian, Spanish, LA Spanish and Greek. Haskins Laboratory WWW Site http://www.haskins.yale.edu/Haskins/MISC/special.html Examples of several types of speech synthesis. Articulatory Synthesis by HyperASY. SineWave Synthesis. Gestural Computational Model. Pattern Playback system of the 1940's! BeSTspeech from Berkeley Speech Technologies, Inc., (BST) http://www.bestspeech.com/weblang.html Eurovocs Multilingual Speech Synthesis http://www.elis.rug.ac.be/ELISgroups/speech/research/eurovocs.h tml Based on Lernout and Hauspie technology. HADIFIX German Speech Synthesis http://asl1.ikp.uni-bonn.de/~tpo/Hadiq.en.html Provided by the Instituts fur Kommunikationsforschung und Phonetik, Universitat Bonn. Centigram's TruVoice Demo http://www.centigram.com/centigram/TruVoice/index.html Allows control of speech rate, pitch and other prosodic charateristics. MBROLA: Free Speech Synthesis Project http://tcts.fpms.ac.be/synthesis/modelcmp.html WWW demo of MBROLA which compares the quality of PSOLA, MBR-PSOLA, LPC, and Hybrid Harmonic/Stochastic concatenative synthesizers. Provided by the TCTS Lab, Faculti Polytechnique de Mons, Belgium Institute of Phonetic Sciences http://fonsg3.let.uva.nl/IFA-Features.html Links to lots of on-line speech synthesis demonstrations provided by the Institute of Phonetic Sciences of the Faculty of Arts of the University of Amsterdam. Yahoo page on speech generation http://www.yahoo.com/Science/Computer_Science/Artificial_Intell igence/Natural_Language_Processing/Speech_Generation/ ___________________________________________________________________________ Q5.5: Speech Synthesis Software/Hardware Please email any updates, corrections or additions to the following list. The range of commercially available synthesis software is growing rapidly so any help in keeping up to date will be appreciated. Other lists of speech synthesis software on the WWW include: Kevin Lenzo's list of Macintosh Speech Resources and Apps http://www.cs.cmu.edu/~lenzo/mac_speech_apps.html Speech Toys Speech Synthesis Information http://www.speechtoys.com/spchtoys/spsyn.html In the FAQ... The following speech recognition software/hardware is described in the comp.speech FAQ. _Apple Macintosh_ * BeSTspeech from Berkeley Speech Technologies, Inc., (BST) * Infovox Product Range * Macintosh Speech Output Applications * Macintosh Speech Synthesis Manager * MacYack Pro * MBROLA: Free Speech Synthesis Project * ProVoice Developer's Speech Toolkit from First Byte * SENSYN speech synthesizer * Sound Bytes DeveloperUs Kit * Macintosh Speech Synthesis Manager _Windows (including 95, NT, 3.1)_ * AcuVoice * AT&T Watson Speech Synthesis * BeSTspeech from Berkeley Speech Technologies, Inc., (BST) * Creative TextAssist and TextAssist API * DECtalk: Text-to-Speech from Digital * ETI-Eloquence * HADIFIX * Infovox Product Range * IPOX: All Prosodic Speech Synthesis Architecture * Lernout and Hauspie Text-To-Speech Windows SDK * Listen2 Text Reader * MBROLA: Free Speech Synthesis Project * Monologue for Windows from First Byte * PAM - A Text-To-Speech Application * ProVerbe Speech Engine from ELAN Informatique * ProVoice Developer's Speech Toolkit from First Byte * SENSYN speech synthesizer * Sound Bytes DeveloperUs Kit * Tinytalk * TruVoice from Centigram * WinSpeech * ZMD Speech Synthesis _DOS_ * CSRE: Computerized Speech Research Environment * Infovox Product Range * MBROLA: Free Speech Synthesis Project * ProVoice Developer's Speech Toolkit from First Byte * SENSYN speech synthesizer * spchsyn.exe * Tinytalk * ZMD Speech Synthesis _OS/2_ * ProVerbe Speech Engine from ELAN Informatique * ProVoice Developer's Speech Toolkit from First Byte * Sound Bytes DeveloperUs Kit _Unix_ * AcuVoice * AsTeR * BeSTspeech from Berkeley Speech Technologies, Inc., (BST) * DECtalk: Text-to-Speech from Digital * ETI-Eloquence * Emacspeak - A Speech Output Subsystem For Emacs * Festival Speech Synthesis System * JSRU * Klatt-style synthesiser * KPE80 - A Klatt Synthesiser and Parameter Editor * "learph": Trainable text-to-phoneme software by Antonio Lucca * MBROLA: Free Speech Synthesis Project * Orator from Bellcore * ProVerbe Speech Engine from ELAN Informatique * rsynth * SENSYN speech synthesizer * SGI Developers Toolbox Synthesiser * Speak * TrueTalk * TruVoice from Centigram _Integrated Circuits and Dedicated Hardware_ * Eurovocs * Infovox Product Range * ProVerbe Speech Engine from ELAN Informatique * RC Systems V8600/V8601 Text to Speech synthesizers _Other Platforms_ * BeSTspeech from Berkeley Speech Technologies, Inc., (BST) * TheBigMouth (NeXT) * MBROLA: Free Speech Synthesis Project * Narrator Translator Library (Amiga) * Narrator (Amiga) * TextToSpeech Kit (NeXT) * Orator from Bellcore * SENSYN speech synthesizer * WreadFiles: File reader for Commodore Amiga _Unknown_ * Lernout and Hauspie Text-To-Speech (3 products) * Lucent Technologies Bell Labs Text-to-Speech system * SIMTEL * Text to Phoneme Program 1 * Text to phoneme program 2 * Text to phoneme program 3 AcuVoice * Platform: Windows, Solaris * Description: AcuVoice is a natural sounding text-to-speech system built using a concatenative approach. Currently it is available for an American English Male Voice. Software Developer Kits are available for the Windows Platform (32-Bit) and also for the Solaris Platform. More information and samples are available on the Acuvoice web site. * Contact: AcuVoice, Inc. 84 W. Santa Clara Street, Suite 720, San Jose, CA 95113-1810 Ph: 1(408)289-1661, Fax: 1(408)289-1201 Demo: 1(408)289-1177 Email: AcuVoice1@AOL.COM WWW: http://www.acuvoice.com/ AsTeR * Platform: UNIX * Description: TTS front-end program which encodes structural information about documents in speech synthesis. For more information check out: http://www.research.digital.com/CRL/personal/raman/aster/ aster-toplevel.html * Operation requirements: Lisp: Lucid, clisp * Contact: T. V. Raman WWW: http://www.research.digital.com/CRL/personal/raman/raman.html Email: raman@adobe.com AT&T Watson Speech Synthesis * Platform: Windows 95/NT on a Pentium 75 Mhz or higher * Description: Watson is a software implementation of AT&T Bell Laboratories voice processing technology. Watson includes BLASR Speech Recognition (see Q6.6) and FlexTalk speech synthesis. It requires no special hardware to run other than a standard sound card and/or phone card. Technical details for the FlexTalk speech synthesis include: + Compliant with MS Speech API. + Male and Female Voices available + 8 KHz and 11 KHz output + SoundBlaster compatible sound card and drivers required + Context sensitive abbreviation expansion + Accurate pronunciation of most proper names + Adjustable vocal tract size, speed, volume, pitch, etc. + American English only - other languages in development The AT&T Advanced Speech Products Group home page provides more detailed information including a Frequently Asked Questions list, information for application developers on the Independent Software Vendor (ISV) Program (including info on the SDK, licensing, and the training program). * Requirements: Uses 2 MB RAM, 10 MB Disk. Requires a Pentium 75 MHz or higher (uses * Cost and Availability: WATSON is a software-based speech platform with a Software Developers Kit (SDK) that allows application developers to use voice processing in their applications. It is not available as a stand-alone product. Licensing information (inc. price) is provided in the AT&T Advanced Speech Products Group home page * See also: Watson BLASR speech recognition in Q6.5, Microsoft Speech API, and Advanced Speech API. * Contact: AT&T Advanced Speech Products Group Suite 700, 44 East Mifflin Street, Madison, WI 53703, USA Ph: 1-800-5-WATSON, Fax: 1-608-259-2269 Email: aspg@attmail.com WWW: http://www.att.com/aspg/ BeSTspeech from Berkeley Speech Technologies, Inc., (BST) * Platform: available for Macintosh, Sun, Silicon Graphics, Windows PC and IBM RS/6000 platforms, and can be ported to others. * Description: BeSTspeech reads ASCII text no vocabulary limits. Available for Dutch, English (male and female), French, German, Italian, Portuguese, Spanish, Arabic, Cantonese, Japanese, Korean, Malay, Mandarin and Russian. * Availability: Berkeley Speech Technologies, Inc does not sell end user toolkits or products. * Contact: Berkeley Speech Technologies, Inc. 2246 Sixth Street, Berkeley, California 94710, USA Ph: (510) 841-5083, Fax: (510) 841-5093 Email: webmaster@bst.com WWW: http://www.bestspeech.com/index.html TheBigMouth - a Text to Speech Program * Platform: NeXT * Description: Text to speech program based on concatenation of pre-recorded speech segments. * Availability: ftp://ftp.cs.keio.ac.jp/pub/NeXT/source/TheBigMouth1.0.tar.Z Creative TextAssist * Platform: Windows * Description: Based on DECtalk speech synthesis. A detailed description of TextAssist is provided on the Creative WWW pages. TextAssist TextReader provides a convenient Windows user interface for text reading. * Availability: Creative TextAssist is bundled with most (all?) Creative Sound Blaster audio cards. TextAssist preview software is available from the Creative Labs TextAssist home page. * Contact: Creative Labs, Inc. Address, phone, email etc unknown WWW: http://www.creaf.com/ : http://www.creaf.com/wwwnew/tech/devcnr/tassist.html Creative TextAssist API * Platform: Windows * Description: The TextAssist API (TAAPI) is created for Microsoft Windows 3.1x and Windows 95 developers who intend to develop 16-bit Text-to-Speech software applications using Creative's TextAssist speech engine. It supports direct control of speech output characteristics, concurrent playback of text-to-speech and wave files, foreign language support, speech synchronization, exception dictionaries. It also includes a voice editing tool for creating new custom voices, a Visual Basic Custom Control for high-level support in Visual Basic and other languages * Availability: The TextAssist API is released to registered developers at no cost. * Contact: WWW: http://www.creaf.com/ FAQ: http://www.creaf.com/wwwnew/tech/devcnr/tassfaq.html CSRE: Computerized Speech Research Environment * Platform: DOS * Description: CSRE is a software system which includes in an implementation of the Klatt speech synthesizer. See the CSRE entry in Q1.9 and the AVAAZ WWW pages for more detail. * Contact: AVAAZ Innovations Inc. P.O.Box 8040, 1225 Wonderland Rd. N, London, Ontario, CANADA, N6G 2B0 Ph: +1-519-472-7944 , Fax: +1-519-472-7814 Email: info@avaaz.com WWW: http://www.icis.on.ca/homepages/avaaz/ DECtalk Speech Synthesis * Platform: Windows NT, Alpha with Digital UNIX and RS232 ports * Description: Converts ordinary text into natural-sounding, intelligible speech. Provides personalized voices, and extensive user controls. DECtalk technology is available for the following packaging options. + DECtalk PC card option: An industry-standard ISA/EISA bus card implementation that can be integrated with any Intel 486 processor-based system running DOS or Windows. Applications can be interfaced to the bus via a DOS Terminate and Stay Resident (TSR) driver or a Windows Dynamic Link Library (DLL). This option is available with an external speaker with volume control and headphone jack. + DECtalk Express external package: An external, portable package that you can plug in to any PC or serial port. The external package includes a built-in speaker and headphone jack, plus combined on/off and volume controls and a rechargeable battery pack. + DECtalk Software solution: Software-only text to speech for Alpha or Intel systems running Windows NT or Alpha systems running Digital UNIX. Provides complete speech synthesis capabilities so developers can enhance applications with DECtalk technology. DECtalk Software output can be directed to audio devices, into WAVE files, or into memory buffers. * Pricing: ://www.systems.digital.com/DIcatalog/html/DECtalk-Speech-Synthesis -oi.html * More Information: Digital Equipment Corporation WWW pages: http://www.digital.com/ DECtalk page: http://www.systems.digital.com/DIcatalog/html/DECtalk-Software.htm l Ph: 1-800-DIGITAL DECtalk Software * Platform: Digital UNIX and Windows NT * Description: DECtalk converts standard ASCII text into natural, intelligible speech. Speech output through any audio device is supported by Microsoft Video for Windows or Multimedia Services for Digital UNIX. An API gives developers direct access to text-to-speech functions. Provides nine voice personalities (4 female, 4 male, 1 child). Provides punctuation and tonal control, supports customized pronunciation of trade jargon and acronyms. Common programming interface works with both Alpha and Intel platforms. * More Information: Digital Equipment Corporation WWW pages: http://www.digital.com/ DECtalk Software page: http://www.systems.digital.com/DIcatalog/html/DECtalk-Software.htm l WWW: http://www.systems.digital.com/DIcatalog/html/DECtalk-Speech-Synth esis.html Ph: 1-800-DIGITAL ETI-Eloquence * Platform: MS Windows (Win95,NT,3.1), Solaris, SunOS, SGI, RS/6000 * Description: ETI-Eloquence is a software based text-to-speech system. It generates waveforms completely algorithmically instead of by concatenating waveforms, for maximum flexibility and naturalism. For instance, when the user requests a deeper voice, the software simulates a larger vocal tract, instead of simply pitch-shifting samples. It uses high-level linguistic parsing, which obviates the need for a huge dictionary. It handles numbers, acronyms, currency, etc. It includes a set of annotation symbols, for placing stress on particular words, expressing excitement/boredom, etc. Also allows phonetic input. Supports MS SAPI. Produces male and female voices for General American English. Dialects under development include Alabama and Brooklyn. * Price: Flexible license agreements on application. * Availability:Eloquent Technology, Inc. 2389 North Triphammer Road, Ithaca, NY 14850 , USA Ph: (607) 266-7025, Fax: (607) 266-7030 Email: info@eloq.com WWW: http://www.eloq.com/ Emacspeak - A Speech Output Subsystem For Emacs * Platform: UNIX, Emacs * Description: Emacspeak is a speech output system that will allow someone who cannot see to work directly on a UNIX system. Emacspeak is built on top of Emacs. With emacspeak loaded, Emacs provides spoken feedback for everything you do. Emacspeak currently supports the new Dectalk Express speech synthesizer, as well as older versions of the Dectalk e.g. the MultiVoice. See the Emacspeak WWW page, the Emacspeak FAQ or the Emacspeak distribution for additional details. * Requirements: Requires GNU FSF Emacs 19 (version 19.23 or later) and TCLX 7.3B (Extended TCL) to run Emacspeak. * Availability: Emacspeak WWW page http://www.research.digital.com/CRL/personal/raman/emacsp eak/emacspeak.html Emacspeak source http://www.research.digital.com/CRL/personal/raman/emacsp eak/emacspeak.tar.gz * Contact: T. V. Raman, raman@adobe.com Eurovocs * Platform: Various - RS232 hardware connection * Description: Eurovocs is a stand-alone text-to-speech synthesizer which uses the text-to-speech technology of Lernout and Hauspie Speech Products. Available for Dutch, French, German and American English with other languages planned for release soon. One Eurovocs device can support two different languages. Eurovocs can be connected to any computer via a standard serial interface (RS232). It supports personal dictionaries, generation of DTMF tones, and pronunciation of special character sequences such as digit strings, telephone-numbers, date and time indications, abbreviations, alphanumeric strings etc. * Contact: Technologie & Revalidatie Postbus 128, B-9000 Gent, Belgium Ph: +32-9-264 33 97, Fax: +32-9-264 35 94 E-mail: noe@elis.rug.ac.be WWW: http://www.elis.rug.ac.be/ELISgroups/speech/research/eurovocs.html Festival Speech Synthesis System * Platform: General Unix (including Solaris (2.4,2.5), SunOS, HPUX, SGIs, Linux, Dec Alpha, FreeBSD) * Description: Festival is a general multi-lingual speech synthesis system developed at CSTR, University of Edinburgh. It offers a full text to speech system with various APIs, as well an environment for development and research of speech synthesis techniques. It is written in C++ with a Scheme-based command interpreter for general control. Festival's home page offers demos, the full manual and access to the download page. The distribution includes full source and documentation, and lexicons and speech databases for British English text to speech. * Price: Free for non-commercial use * Availability: by anonymous ftp: WWW: http://www.cstr.ed.ac.uk/projects/festival/download.html ftp: ftp://ftp.cstr.ed.ac.uk/pub/festival/1.1.1/ HADIFIX * Platform: Windows * Description: German speech synthesis system developed at the Institute for Communications Research and Phonetics , University of Bonn. Provides conversion of input text to phonemes, automatic prediction of stress, phrasing and pitch, and speech generation by concatenation of small units of natural speech. Demisyllables and similar units are used; they comprise all consonants before the vowel and the beginning of the vowel (initial demisyllable) or the end of the vowel and the following consonants (final demisyllable). For example, the word 'Strolch' is formed by concatenating 'Stro' and 'olch'. * Demo: Windows demo software available. Limited to synthesis of one short text (text.txt) at a time. Speech format limitations too. 1.3MB file. ftp://asl1.ikp.uni-bonn.de/pub/hadifix/hadidemo.zip A 1993 version is available with unlimited synthesis from a string of phonemic symbols and accent markers. 6MB file. ftp://asl1.ikp.uni-bonn.de/pub/hadifix/hadi25.lzh * WWW: http://asl1.ikp.uni-bonn.de/~tpo/Hadifix.en.html * On-line demo: http://asl1.ikp.uni-bonn.de/~tpo/Hadiq.en.html Infovox Product Range * Description: Multilingual Text-to-speech systems, languages available: American English, British English, German, French, Spanish, Italian, Swedish, Norwegian, Icelandic, Danish and Finnish. * Product name:INFOVOX 500, PC BOARD + Product description: Half length expansion board for IBM PC, XT, AT, PS/2 model 30 or compatible personal computers. The board can also be connected via the serial port. Language and control program for downloading into RAM or mounted on EPROMs + Platform: DOS/Windows with IBM PC, XT, AT, PS/2 model 30 or compatible + Delivered standard interface: MS DOS I/O driver * Product name: INFOVOX 600, OEM BOARD + Product description: OEM board built with CMOS IC's. Language and control program are stored in on-board fixed memory. + Platform: any, hardware interface: 9-pole D-SUB (RS 232-C) 300-9600 Baud. + Delivered standard interfaces: MS DOS I/O driver and interface to Apple Speech manager. * Product name: INFOVOX 700, DESKTOP UNIT + Product description: Desktop unit with built in Infovox 600 to be connected to any computer or terminal via an RS 232-C serial interface. Built in loudspeaker and rechargable battery for 4 hours use, and control knobs for continuous control of speech volume and speed. + Platform: various through hardware interface + Delivered standard interfaces: MS DOS I/O driver and interface to Apple Speech manager * Product name: INFOVOX 650, OEM BOARD + Product description: OEM-board built with CMOS IC's. Language and control program are stored in on-board memory. + Platform: any, hardware interface: 9 pole D-SUB (RS 232-C) 300-9600 Baud + Delivered standard interfaces: MS DOS I/O driver and interface to Apple Speech manager * Product name: INFOVOX 750, DESKTOP UNIT + Product description: Desktop unit with built in Infovox 650 to be connected to any computer or terminal via an RS 232-C serial interface. Built in loudspeaker and rechargable battery for 5 hours use, and a control knob for continuous control of speech volume. + Platform: various through hardware interface. Delivered standard interfaces include MS DOS I/O driver and interface to Apple Speech manager * Product name: Infovox 210, software for Apple Macintosh + Product description: Software based text-to-speech conversion. Produces 16 bit and 8 bit sound. Delivered on 3.5" diskettes with user lexicon and a complete documentation. + Platform: Apple Macintosh with minimum 68030, 33 MHz microprocessor. + Delivered standard interfaces: Standard interface to Apple Speech manager * Product name: Infovox 220, software for Microsoft Windows. + Product description: Software based text-to-speech conversion. Produces 16 bit sound and conforms to Microsoft Windows multimedia standard MCI. Delivered on 3.5" diskettes with user lexicon and a complete documentation. + Platform: Windows on IBM compatible PC with minimum 486/25MHz microprocessor. + Delivered standard interfaces: Standard interface to Microsoft Windows 3.1 and sound boards supporting Microsoft Windows multimedia driver for audio. * Contact: Telia Promotor Infovox AB TTS Sales Division P.O. Box 2069, S-171 02 Solna, Sweden Ph: +46 8 764 35 00, Fax: +46 8 735 78 76 Email: tts-sales@infovox.se WWW: http://www.promotor.telia.se/NYA/cc/t-s/index.html IPOX: All Prosodic Speech Synthesis Architecture * Platform: Windows * Description: IPOX is an experimental, all-prosodic speech synthesizer, developed by Arthur Dirksen and John Coleman. IPOX is freely available (after registration) for evaluation and non-profit research purposes. * Requirements: PC (preferably a fast 486) running Windows 3.1 or higher. Sound output requires a 16-bit Windows-compatible sound card * Availability: By WWW from http://www.tue.nl/ipo/people/adirksen/ipox/ipox.htm JSRU * Platform: UNIX and PC * Cost: 100 pounds sterling (from academic institutions and industry) * Description: A C version of the JSRU system, Version 2.3 is available. It's written in Turbo C but runs on most Unix systems with very little modification. A Form of Agreement must be signed to say that the software is required for research and development only. * Contact: Dr. E.Lewis _eric.lewis@bristol.ac.uk)_ Klatt-style synthesiser * Platform: Unix * Cost: Free * Description: Software posted to comp.speech in late 1992. * Availability: By ftp from the comp.speech ftp site + ftp://svr-ftp.eng.cam.ac.uk/pub/comp.speech/synthesis/klatt.3. 04.tar.gz + ftp://svr-ftp.eng.cam.ac.uk/pub/comp.speech/synthesis/klatt.3. 04.tar.Z * See also: KPE80 - A Klatt Synthesiser and Parameter Editor. KPE80 - A Klatt Synthesiser and Parameter Editor * Platform: Unix * Description: The KPE80 program provides a graphical interface for the implementation of the Klatt 1980 formant synthesiser written by Jon Iles and Nick Ing-Simmons. It was inspired by IGE, a piece of code written by Rob Fletcher ( http://www.york.ac.uk/~rpf1/IGE.html). * Technical Desc.: It is comprised of an X-Window interface and version 3.03 of the synthesiser code. The interface allows users to display and edit Klatt parameters using a graphical display which includes the time-amplitude waveform of both the original speech and its synthetic copy, and some signal analysis facilities. Most of the work in choosing the parameter values to produce the synthetic copy has to be done by the user. KPE will estimate the fundamental frequency contour from an original token; this estimate will need to be amended where errors occur. It is possible to specify the formant trajectories with some precision by overlaying the appropriate formant frequency parameter tracks on the spectrogram of the target waveform. A number of facilities exist to help in the refinement of parameter values: original and synthetic waveforms can be compared aurally, spectrally, and spectrographically using built-in speech analysis facilities. * File formats: KPE will read RIFF (.wav) files and SFS files. (SFS is a suite of speech-signal processing programs available free from Phonetics and Linguistics, UCL.) * Availability: KPE for SunOs 4.1.3 (statically compiled libraries) ftp://ftp.phon.ucl.ac.uk/pub/kpe/kpe80.sun413.tar.Z KPE for Linux (statically compiled libraries) ftp://ftp.phon.ucl.ac.uk/pub/kpe/kpe80.linux.tar.Z The source code (needs gcc and SUIT to compile) ftp://ftp.phon.ucl.ac.uk/pub/kpe/kpe80.src.tar.Z A postscript overview of KPE ftp://ftp.phon.ucl.ac.uk/pub/kpe/OVERVIEW.ps The SFS distribution ftp://ftp.phon.ucl.ac.uk/pub/sfs/ * See also: Public domain Klatt-style speech synthesis code. * Contact: Andrew Simpson Department of Phonetics and Linguistics, University College London Wolfson House, 4 Stephenson Way, London NW1 2HE Email: a.simpson@ucl.ac.uk WWW: http://www.phon.ucl.ac.uk/home/andrew/home.html "learph": Trainable text-to-phoneme software by Antonio Lucca * Platform: UNIX * Description: Experimental software which learns text to phoneme translation from examples using decision-tree-like data structures. It is based on the assumption that each letter can correspond to different phoneme strings depending on the context. * Availability: Examples and source are available on the WWW: http://www.silab.dsi.unimi.it/~al367212/ttsdoc.html * Contact: Antonio Lucca: toninlcc@tesi.dsi.unimi.it Lernout & Hauspie Text-to-Speech (3 products) Lernout & Hauspie have three TTS products. The functionality of the products is similar, however, they differ in hardware implementation and other details where described below. * L&H tts2000/T: TTS for the Telephony and Telecommunications Market * L&H tts2000/M: TTS for the Computer and Multimedia Market * L&H tts3000/C: TTS for the Buisness and Consumer Electronics Market * Description: Text to Speech (TTS) software based on parameterized segment concatenation (diphones, triphones and tetraphones) algorithms. Available for US English, German, Dutch, French, Spanish (Castilian), Italian and Korean. General features include: + The control of volume, speech rate and speech pitch. + The use of control sequences to customize TTS output (adding pauses, using phonetic input, etc.). + Switching between languages at run time. + A personal vocabulary editor is available for building exception dictionaries. + Readout modes: letter by letter, word by word or sentence by sentence. + Input formats: orthographic input, phonetic input, phonetic input with prosodic information. * tts2000/T + Output formats: 8 bit mu-law PCM, 8 bit A-law PCM, 16 bit linear PCM. + Sampling Frequency: 8kHz + Single channel platform examples: SHARP SH7000, ARM6/ARM7, Intel i960, TI TMS320C31, AT&T DSP3210 + Multi-channel platform examples: TI TMS320C31, AT&T DSP3210 * tts2000/M + Output formats: 8/16 bit wave format, 8 bit mu-law PCM, 8 bit A-law PCM, 16 bit linear PC. + Sampling Frequency: 8/10/11.025 kHz + Single processor platform examples: ARM6/ARM7, Intel 386/486/Pentium, Motorola 68040 + Two processor platform examples: {Intel 386/486/Pentium or Motorola 68030} and {ADI ADSP21XX or Motorola 5600X or TI TMS320C25/20C5X} * tts3000/C + Output formats: 8 bit mu-law PCM, 8 bit A-law PCM, 16 bit linear PCM. + Sampling Frequency: 10kHz + Single processor platform examples: SHARP SH7000, ARM6/ARM7, Intel i960, TI TMS320C31, AT&T DSP3210 + Two processors platform examples: { SHARP SH7000 or ARM6/ARM7 or Intel 386EX or Motorola 683XX} and {ADI ADSP21XX or Motorola 5600X or TI TMS320C25/C5X or TI TSP50C10} * See also: L&H Windows TTS SDK * More Information: on the Lernout & Hauspie WWW pages: http://www.lhs.com/tts.html * Price: Unknown * Contact: Lernout and Hauspie Speech Products 20 Mall Road, 4th Floor Burlington, MA 01803, USA Ph: +1-617-238-0960, Fax: +1-617-238-0986 Email: sales@lhs.com WWW: http://www.lhs.com/ Lernout & Hauspie Text-to-Speech Windows SDK * Platform: Windows * Description: The L&H Text-to-Speech software developers kit is able to integrate text-to-speech technology with your own or existing PC applications under Microsoft Windows 3.1. This software will allow conversion of written text into clear human sounding synthetic speech. * Requirements: IBM-compatible PC 386 DX/33 + 8Mb RAM + MS DOS 5.0 + MS Windows 3.1 (or higher) + SoundBlaster compatible sound board. * See also: L&H TTS Products * More Information: on the Lernout & Hauspie WWW pages: http://www.lhs.com/tts.html * Price: Unknown * Contact: Lernout and Hauspie Speech Products 20 Mall Road, 4th Floor Burlington, MA 01803, USA Ph: +1-617-238-0960, Fax: +1-617-238-0986 Email: sales@lhs.com WWW: http://www.lhs.com/ Listen2 Text Reader * Platform: Windows * Description: Listen2 is a multi-voice, multi-language text reader. Listen2 comes in two versions, English only that uses high quality male and female voices, and the International version that can speak up to 5 different languages: English, German, French, Spanish or Italian, all in male voices. The basic International program comes with built-in English and additional language fonts can be purchased separately. The English version comes complete. Both programs are dynamically switchable and configurable. This means that you can press a hot key to speed up the speech, make it louder or quieter, etc., as it is reading a file. You can also insert flags in text files to make it switch voices or switch languages, depending on what version you have. Listen2 has all the features of the JTS Reader shareware program plus a few more. It will voice your reminder messages or appointment list on start-up. It will also speak a reminder message on shutting down. * WWW: A more complete description is available on the Listen2 web page * Contact: Tom Slemko: e-mail: tslemko@islandnet.com, or, JTS Micro Consulting Ltd 10931 Lytton Road, RR#4, Ladysmith, B.C., Canada, V0R 2E0 WWW: http://www.islandnet.com/jts/ Lucent Technologies Bell Labs Text-to-Speech system * Platform: Unknown * Description:Lucent Technologies provides a web site with demos and samples of their latest speech synthesis technology. The site has interactive demos in American English, German, and Mandarin Chinese, and the capability to adjust voice parameters on the fly. Pre-synthesized demos for French, Italian, Russian, and Romanian are also provided. The site includes downloadable papers with detailed system descriptions. * WWW: http://www.bell-labs.com/project/tts/ Macintosh Speech Output Applications * Platform: Macintosh * Description: A comprehensive list of Macintosh Speech Applications is provided by Kevin Lenzo at CMU: http://www.cs.cmu.edu/~lenzo/mac_speech_apps.html The Apple Speech WWW Site also has some useful information: http://www.speech.apple.com/ Speech Manager and PlainTalk * Platform: Macintosh * Description: Apple's text-to-speech system extensions that enable applications to perform text-to-speech conversion. The Speech Manager runs on most Macs, but PlainTalk (and the high quality voices) requires a 68020 Mac or better. * Availability: By anonymous ftp from: ftp://ftp.support.apple.com/pub/apple_sw_updates/US/Macintosh/Syst em/PlainTalk 1.4.1/ This directory contains subdirectories for recent versions of PlainTalk. The current release (PlainTalk 1.4.1) contains the English Text-To-Speech with about a dozen voices (English_Text-to-Speech.hqx: 5.3 MByte), Mexican Spanish (Mexican_Spanish_TTS.hqx: 2.8 MByte), and the English Speech Recognition software (English_Speech_Recognition.hqx: 2.3MByte). * Cost: Free * WWW: The latest information is available from Apple's WWW page for speech recognition and synthesis: http://www.speech.apple.com/ * Note 1: Check out Kevin Lenzo's list of Macintosh Speech Applications. * Note 2: Joshua Baer (josh@skyweyr.com) runs a mailing list for Plaintalk. For subscription and other information visit the Plaintalk Discussion List Home page * Contact: Apple Computer, Inc. 1 Infinite Loop, Cupertino, CA 95014, USA WWW: http://www.speech.apple.com/ Email: PlainTalk@atg.apple.com MacYack Pro * Platform: Macintosh * Description: MacYack Pro is a commercial speech package for Macintosh that uses the PlainTalk Text-to-Speech synthesis software. Features include: + Add speech to any word processor. + Hear notification dialogs and other dialog boxes. + See and hear a customized message at startup or shutdown. + Hear calculations instantly. + Correct pronounciation errors. + Create custom double-clickable "speech files." + Have speaking alert sounds. + Add speech to HyperCard stacks. + Use AppleScript to add speech to other programs. * Price: $29.95 for a limited time, reduced from $49.95 regular price. 30 days money back guarantee. * Contact: Scantron Quality Computers 20200 Nine Mile Rd. St. Clair Shores, MI 48080 Ph: 1-800-777-3642, Fax: 810-774-2698 E-mail: sales@sqc.com WWW: http://www.sqc.com/ Product Info: http://www.lowtek.com/macyack/ MBROLA: Free Speech Synthesis Project * Platform: Sun4, Sun/SunOS5.4, HP, VAX/VMS, DEC Alpha/VMS, PS/DOS, PS/Windows 3.1, PS/Windows 95, PC/Solaris2.4, PC/Linux, SGI INDY/IRIX, NeXT, and soon for Macintosh. * Description: MBROLA is a high-quality, diphone-based speech synthesizer which is available for free. It is provided by the TCTS Lab of the Faculte Polytechnique de Mons (Belgium) which aims to obtain a set a speech synthesizers for as many languages as possible which will be free of use for non-commercial, non-military applications. MBROLA 2.00 takes a list of phonemes as input, together with prosodic information (duration of phonemes and a piecewise linear description of pitch), and produces 16bit speech samples at the sampling frequency of the diphone database (typically 16kHz). (It is therefore NOT a Text-To-Speech (TTS) synthesizer, since it does not accept raw text as input.) Databases are now being prepared for English, Spanish, Italian, Dutch, and Romanian. Collaborations are welcome. More information can be found at the MBROLA project homepage. * Demonstration: WWW demo of MBROLA which compares the quality of PSOLA, MBR-PSOLA, LPC, and Hybrid Harmonic/Stochastic concatenative synthesizers is available at http://tcts.fpms.ac.be/synthesis/modelcmp.html. * Contact: Dr Thierry Dutoit Faculte Polytechnique de Mons, TCTS Lab, 31, bvd Dolez, B-7000 Mons, Belgium. Ph: +32-65-374133, Fax: +32-65-374129 e-mail: mbrola@tcts.fpms.ac.be WWW: http://tcts.fpms.ac.be/synthesis/mbrola.html Monologue for Windows from First Byte * Platform: Windows * Description: Monologue is a software program that reads text from the clipboard in Windows 16 or 32 bit applications. It can be found as a bundled product with many sound cards and multimedia general purpose computer systems. Monologue can add the element of speech to virtually any text oriented application. Any pronounceable combination of letters and numbers will be spoken clearly. It can be applied to tasks such as eyes-free proofreading, data verification (e.g. spreadsheets), reading E-mail and more. User-changeable parameters provide control over the sound quality by allowing for changes in pitch, and the speed of speech. An exception dictionary saves preferred pronunciation of words and abbreviations. Monologue Win32 now includes support for the Microsoft SAPI. Monologue male "SpeechFonts" are available for US English, British English, German, French, Latin American Spanish, Italian. A US English Female SpeechFont is also available. For more detailed information and examples go to the First Byte WWW pages. * Availability: Currently bundled with many sound cards and multimedia general purpose computer systems. For pricing, licensing details, and release information see the First Byte WWW pages or email info@firstbyte.davd.com. * See also: ProVoice Developer's Speech Toolkit from First Byte * Contact: First Byte 19840 Pioneer Ave., Torrance, CA 90503 Ph: 310-793-0610 Fax: 310-793-0611 Email: info@firstbyte.davd.com WWW: http://www.firstbyte.davd.com/ Narrator Translator Library * Platform: Amiga * Description: A US English text to phoneme translator, implemented as a resident software library, for use with the Amiga Narrator Device. This software was supplied as a standard part of the Amiga operating system software up to O.S version 2.04. (Translator version 37.1, 1991) Approximately 700 translation rules are used to create the 'ARPAbet' phonemes. This software is functional on all current Amiga systems (O.S. 3.1). * Availability: limited to pre-owned system software disks and unsold O.S upgrade kits (Pre-O.S. 2.1). Replacement Library: Translator42 * Platform: Amiga * Description: an independent replacement for the Commodore-supplied "translator.library" which is a part of the Narrator speech synthesis package. It implements multi-lingual text-to-speech for an Amiga. The translation rules for each language are defined in a plain text 'Accent' file. There is a provision for the selection of unique languages for text segments by inserting in-line markup codes in the text: e.g. "Hello there! \french{Bonjour} \deutsch{gute morgen}". 'Accent' files for American English, British English, Swedish, Maori, Finnish, German, Icelandic, Klingon, Polish, Italian, and Welsh languages included in the archive. * Availability: Amiga The most current version, 42.4, of the library and source are available by anonymous ftp from Aminet: ftp://ftp.doc.ic.ac.uk/pub/aminet/util/libs/translator42.lha ftp://ftp.doc.ic.ac.uk/pub/aminet/dev/src/tran42src.lha Narrator * Platform: Amiga * Description: Formant based speech synthesis. Includes a Engish-to-phoneme translation library, and a SPEAK: pseudo-device for speech output. * Hardware: Standard Amiga hardware * Availability: Part of AmigaOS * See Also: The Narrator Translation library TextToSpeech Kit * Platform: NeXT Computers * Description: The TextToSpeech Kit does unrestricted conversion of English text to synthesized speech in real-time. The user has control over speaking rate, median pitch, stereo balance, volume, and intonation type. Text of any length can be spoken, and messages can be queued up, from multiple applications if desired. Real-time controls such as pause, continue, and erase are included. Pronunciations are derived primarily by dictionary look-up. The Main Dictionary has nearly 100,000 hand-edited pronunciations which can be supplemented or overridden with the User and Application dictionaries. A number parser handles numbers in any form. A letter-to-sound knowledge base provides pronunciations for words not in the Main or customized dictionaries. Dictionary search order is under user control. Special modes of text input are available for spelling and emphasis of words or phrases. The actual conversion of text to speech is done by the TextToSpeech Server. The Server runs as an independent task in the background, and can handle up to 50 client connections. * Misc: The TextToSpeech Kit comes in two packages: the Developer Kit and the User Kit. The Developer Kit enables developers to build and test applications which incorporate text-to-speech. It includes the TextToSpeech Server, the TextToSpeech Object, the pronunciation editor PrEditor, several example applications, phonetic fonts, example source code, and developer documentation. The User Kit provides support for applications which incorporate text-to-speech. It is a subset of the Developer Kit. * Hardware: Uses standard NeXT Computer hardware. * Cost: + TextToSpeech User Kit: $175 CDN ($145 US) + TextToSpeech Developer Kit: $350 CDN ($290 US) + Upgrade from User to Developer Kit: $175 CDN ($145 US) * Availability: Trillium Sound Research 1500, 112 - 4th Ave. S.W., Calgary, Alberta, Canada, T2P 0H3 Tel: (403) 284-9278 Fax: (403) 282-6778 Order Desk: 1-800-L-ORATOR (US and Canada only) Email: TTSInfo@trillium.ab.ca Orator Text-to-Speech Synthesizer * Platform: SUN SPARC, Decstation 5000. Written in C, and therefore portable to other UNIX platforms. Some successful ports: HP, RS-6000, PC-Unix [Linux]. * Description: Sophisticated speech synthesis package. Has text preprocessing (for abbreviations, numbers), acronym rules, and human-like spelling routines. Natural-sounding synthesis based on demisyllable concatenation. Has high accuracy for pronunciation of names of people, places and businesses in America; good accuracy for English text; rules for stress and intonation marking; various methods of user control and customization at most stages of processing. A new version of the ORATOR system is under development. Both ORATOR and this new "ORATOR II" system are capable of general text synthesis. The ORATOR II system has a more natural-sounding voice. * Hardware: Runs on common SPARC or Decstation workstations, using their internal audio output capability. Recommend at least 16M of memory. * WWW: More detailed information plus examples of ORATOR synthesis are available on the ORATOR WWW pages: http://www.bellcore.com/ORATOR/ * Misc 1: A free demo cassette is available. * Misc 2: Examples of Orator are also available on the University of Birmingham Speech Synthesis "Museum" WWW site (see Q5.4). * Availability and Pricing: Contact Bellcore's Licensing Office Tel: 1-800-521-CORE (521-2673) Fax: 1-908-336-2559 Email: Anthony Lindsey: alin1@panix.com WWW: http://www.bellcore.com/ORATOR/ PAM - A Text-To-Speech Application * Platform: Windows * Description: PAM is a talking personal assistant and text reader application. It uses the ProVoice TTS package. PAM will verbally advise about appointments and reminder messages at specified times during the day. It can read text files, clipboard text, and text sent in DDE messages. Using the full verbal interface, PAM can be used by visually challenged individuals. Shareware - thirty day free trial. * Requirements: Any Windows sound card, speakers or headphones. Min. memory - 4 megs, 8 megs recommended. * WWW: A more complete description is available on the JTS homepage: http://www.islandnet.com/~tslemko/ * Availability: The shareware can be downloaded by ftp from ftp://ftp.islandnet.com/jts/pam_en3c.zip. The file size is approx. 1 MByte. * Price: $US40 for the registered version. * Contact: Tom Slemko: e-mail: tslemko@islandnet.com, or, JTS Micro Consulting Ltd 10931 Lytton Road, RR#4, Ladysmith, B.C., Canada, V0R 2E0 ProVerbe Speech Engine from ELAN Informatique * Platform: Windows 3.x, NT, 95, OS/2, Unix Solaris, Unix SCO and hardware * Description: The ProVerbe Speech Engine from ELAN Informatique produces natural sounding speech from written text. Naturalness is achieved by using the TD-PSOLA process from the CNET (France telecom's research lab.) which is based on the concatenation of elementary speech units (including diphones). Supported languages are British English, American English, Russian, German, French and Spanish. For multi-channel applications Elan Informatique also provides hardware platforms. Elan Informatique provides a SDK reference document (sdken.doc: WinWord6 format). * Demo versions: Telephone demonstration: +33-561 17 67 01 Sample sound files and demonstration software available. A CD-ROM with all these demonstrations is available by registration. * Contact: Elan Informatique 4 rue Jean Rodier, 31400 TOULOUSE FRANCE Contact person: Pierre Delrat Phone: +33-561-36-0777 Fax: +33-61-36-0770 BBS: +33-561-36-0788 E-mail: sales@elan.fr ftp: ftp://ftp.elan.fr WWW: http://www.elan.fr/ ProVoice Developer's Speech Toolkit from First Byte * Platform: ProVoice Developer's Toolkits are available for DOS, Windows 3.1, Windows 95, Windows NT, OS/2, and Macintosh. * Description: ProVoice allows programmers to add synthesized speech to their applications. Your program passes text strings to the ProVoice speech engine that translates text into audible speech. Male and/or female "SpeechFonts" are available for many languages; English, French, German, UK British English, Italian, and Spanish. ProVoice converts text to speech in two phases using a set of phonetic translation and pronunciation rules. First, the software analyzes and translates text into "sound descriptors", a phonetic language with pitch, duration, and amplitude codes which are needed to produce stress patterns in phrases and sentences. Rules are used to analyze words, numbers, and punctuation. The second phase converts the intermediate phonetic language in speech signals; algorithms drive distinct speech signals into smooth flowing, continuous, clear speech. Real time synchronization of mouth movement and word boundaries allows animation of a graphical talking character, or highlighting of displayed text as it is spoken. Necessary tools and examples are provided for programmers to manipulate the ProVoice speech technology; including installation instructions, extensive samples programs, and complete documentation. In addition, sample code is provided on disk to illustrate speech programming techniques. * Note 1: First Byte will perform custom work for embedded systems. * Note 2: ProVoice Windows includes support for the Microsoft SAPI. It will speak through any Windows-supported wave audio device. * Note 3: Distribution of ProVoice for commercial use is subject to execution of a Commercial Product Distribution License Agreement. * WWW: For more detailed information and examples go to the First Byte WWW page: http://www.firstbyte.davd.com/ * See also: Monologue for Windows from First Byte * Price and Availability: Contact First Byte * Contact: First Byte 19840 Pioneer Ave., Torrance, CA 90503 Ph: 310-793-0610, Fax: 310-793-0611 Email: info@firstbyte.davd.com WWW: http://www.firstbyte.davd.com/ RC Systems V8600/V8601 Text to Speech synthesizers * Platform 1: IBM PC: ISA card. * Platform 2: Interface to PC/104 standard microcontrollers. * Platform 3: Standalone (or embedded) hardware thru RS232 or parallel printer port or processor bus. * Description: Converts plain ASCII text to speech. Programmable voices, pitch rate, volume, etc. Built-in DTMF and tone generators. * Price: $151-$299 US (qty 1) * Contact: RC Systems 1609 England Avenue, Everett, WA 98203, USA Ph: (206) 355-3800 Fax: (206) 355-1098 Europe: +44181 539-0285 rsynth * Platform: Various (including Solaris2.3, SunOS4.1.3, HPUX, SGI Irix4.x, Linux) * Description: Public domain text-to-speech systm assembled from a variety of sources. It supports CMU and BEEP format dictionaries (as described in Q1.10) and now utilises stress marks in the dictionary in synthesising intonation. * Price: Free * Misc: Axel Belinfante has implemented a WWW rsynth demo: http://wwwtios.cs.utwente.nl/say. * Availability: by anonymous ftp from ftp://svr-ftp.eng.cam.ac.uk/pub/comp.speech/synthesis/rsy nth-2.0.tar.Z ftp://svr-ftp.eng.cam.ac.uk/pub/comp.speech/synthesis/rsy nth-2.0.tar.gz SENSYN speech synthesizer * Platform: PC/DOS/Windows, Macintosh, Sun, and NeXT * Rough Cost: $300 * Description: This formant synthesizer produces speech waveform files based on the (Klatt) KLSYN88 synthesizer. It is intended for laboratory and research use. Note that this is NOT a text-to-speech synthesizer, but creates speech sounds based upon a large number of input variables (formant frequencies, bandwidths, glottal pulse characteristics, etc.) and would be used as part of a TTS system. Includes full source code. * Availability: Sensimetrics Corporation Sidney Street, Cambridge MA 02139. Fax: (617) 225-0470; Tel: (617) 225-2442. Email: sensimetrics@sens.com WWW: http://www.sens.com/ SGI Developers Toolbox Synthesiser * Platform: SGI * Description: The SGI Developer Toolbox 4.0 CDROM contains a basicpublic domain text-to-speech program in the publics/speak directory. The directory includes man pages and source. * Availability: on the SGI Developer Toolbox 4.0 CDROM SIMTEL A wide range of speech related software, sound-blaster software and signal processing software for PCs is available on SimTel and its mirror sites. It can be obtained by ftp from: ftp://ftp.coast.net/SimTel/msdos/voice/ and is now on the WWW: http://www.acs.oakland.edu/oak/SimTel/win3/sound.html Voicemaker The archives include the program Voicemaker which synthesises speech from phonemes using "concatenation" of phonemes recorded by the user. Voicemaker is a freeware program. It requires an IBM or compatible, 512KB RAM, sound blaster compatible sound card. ftp://ftp.coast.net/SimTel/msdos/voice/vm110.zip Sound Bytes DeveloperUs Kit * Platform: Subroutine library for Windows, OS/2 and Macintosh * Hardware: Windows - 16 MHz 80386 (minimum) running Windows 3.1; 4 Mb RAM with at least 1.4 Mb RAM free. Disk space 1.4 Mb. OS/2 - 16 MHz 80386 (minimum) running OS/2 2.0 or above; 8 Mb RAM with at least 1.4 Mb RAM free. Mac - Any Mac with at least 2.5 Mb of RAM running 6.0.4 or higher. Telephone compatible. Compatible with commonly used sound cards. * Description: SBDK is a software-only sentence-level synthesizer that converts unrestricted English text (ASCII) into synthesized voice through diphone concatenation. SBDK utlizes parsing to incorporate the intonational and rhythmic patterns of normal speech. The developerUs kit includes two voices, one female and one male. The product has a 55,000-word built-in dictionary and a tool for creating customized user dictionaries. It converts numbers, dates, dollars, phone numbers and times to words, and has a SoundOut facility that provides a choice of pronouncing unknown words phonetically or spelling them out. Developers can vary voice pitch (130-220 Hz) and rate (65-200 wpm), synchronize speech to other events, have multiple channels of speech to the same or different boards, etc. Speech sampling options: 8-bit linear; 8-bit companded at 11 kHz (Windows); 8-bit mu-law PCM at 8 or 11 kHz; 16-bit linear at 11 kHz. * Cost: Sound Bytes may be licensed for internal use or resale. Site license fee= $3750. Resale or Internal runtime fees= 2% of net sales price per runtime sold, OR $150 per telephone port, OR per unit pricing for internal use determined case-by-case. * Misc: Demo disks are available for Windows and the Mac. * Availability: Natural Speech Technologies, Inc. Ph: (619) 457-2526. spchsyn.exe * Platform: DOS * Availability: By anonymous ftp as a self extracting DOS archive. ftp://evans.ee.adfa.oz.au/mirrors/tibbs/applications/spchsyn.exe * Requirements: May require special TI product(s), but all source is there. "Speak" - a Text to Speech Program * Platform: Sun SPARC * Description: Text to speech program based on concatenation of pre-recorded speech segments. A function library can be used to integrate speech output into other code. * Hardware: SPARC audio I/O * Availability: by anonymous ftp ftp://wilma.cs.brown.edu/pub/speak.tar.Z Speech Manager and PlainTalk * Platform: Macintosh * Description: Apple's text-to-speech system extensions that enable applications to perform text-to-speech conversion. The Speech Manager runs on most Macs, but PlainTalk (and the high quality voices) requires a 68020 Mac or better. * Availability: By anonymous ftp from: ftp://ftp.support.apple.com/pub/apple_sw_updates/US/Macintosh/Syst em/PlainTalk 1.4.1/ This directory contains subdirectories for recent versions of PlainTalk. The current release (PlainTalk 1.4.1) contains the English Text-To-Speech with about a dozen voices (English_Text-to-Speech.hqx: 5.3 MByte), Mexican Spanish (Mexican_Spanish_TTS.hqx: 2.8 MByte), and the English Speech Recognition software (English_Speech_Recognition.hqx: 2.3MByte). * Cost: Free * WWW: The latest information is available from Apple's WWW page for speech recognition and synthesis: http://www.speech.apple.com/ * Note 1: Check out Kevin Lenzo's list of Macintosh Speech Applications. * Note 2: Joshua Baer (josh@skyweyr.com) runs a mailing list for Plaintalk. For subscription and other information visit the Plaintalk Discussion List Home page * Contact: Apple Computer, Inc. 1 Infinite Loop, Cupertino, CA 95014, USA WWW: http://www.speech.apple.com/ Email: PlainTalk@atg.apple.com Text to phoneme program (1) * Platform: unknown * Description: Text to phoneme program. Based on Naval Research Lab's set of text to phoneme rules. * Availability: by anonymous ftp ftp://shark.cse.fau.edu/pub/src/phon.tar.Z Text to phoneme program (2) * Platform: unknown * Description: Text to phoneme program. * Availability: by anonymous ftp ftp://ftp.doc.ic.ac.uk/packages/unix-c/utils/phoneme.c.gz Text to phoneme program (3) * Description: A public domain version of the same Naval Research Lab text to phoneme rules. * Availability: By anonymous ftp ftp://svr-ftp.eng.cam.ac.uk/pub/comp.speech/synthesis/english2phon eme.tar.gz Tinytalk * Platform: DOS / Windows??? * Description: Shareware package is a speech 'screen reader' which is used by many blind users. * Price: Tinytalk is now $150. There are package deals on Tinytalk with various speech synthesizers. * Availability: Tinytalk is available by anonymous ftp from the following site Files: ttexe167.zip and ttdoc167.zip (executable and documenation) ftp://ftp.netcom.com/pub/eb/ebohlman/ (Note: it is a busy ftp server.) * Contact: Eric Bohlman OMS Development 610-B Forest Ave., Wilmette, IL 60091 Ph: (800)831-0272 Fax: 708-251-5793 Outside North America: (708)-251-5787 Email: ebohlman@netcom.com TrueTalk * Platform: Sun Sparcstation 1+/2/LX/5/10/20 with SunOS 4.1.3, or SGI Indy/Indigo/Indigo2 with IRIX 5.2. More platforms in development. * Description: Personal TrueTalk, by Entropic Research Laboratory, Inc., is an all-software Text-to-Speech (TTS) system designed to voice-enable UNIX X-Windows workstations. It combines a graphical interface with a powerful TTS engine based on technology developed by AT&T Bell Laboratories. Features include: + Intelligible, prosodically natural speech. + Text taken from file input, highlighted X selections, the interface scratch pad, other programs connected through a TCP/IP socket, or Tcl/Tk applications via the Tk "send" mechanism. + Stop, pause and resume while speech is in progress. + Visual indication of corresponding text position when paused. + Nine speaking voices, with Male and Female versions of each voice. + Adjustable speaking rate and volume. + Supports drop-in text filters; "email" and "lively" examples included. + Audio output through workstation headphones or speaker. + Complete on-line documentation, including mouse-activated help windows. * Misc: A more detailed description of TrueTalk is available on the Entropic WWW server: http://www.entropic.com/truetalk.com * Availability: You can obtain Personal TrueTalk through the Internet. For details, see ftp://ftp.entropic.com/pub/truetalk/README.ptt Personal TrueTalk is available free of charge for evaluation purposes. You can fully-enable your evaluation copy at any time by purchasing a license key from Entropic. * Requirements: 12MB disk space, 8MB process size (24MB system RAM recommended). * Cost: US$495; US$395 academic * Contact: Entropic Research Laboratory, Inc., Washington, D.C. Voice: 1-800-ENTROPIC (North America), (202) 547 1420 Fax: (202) 547-6648 Email: truetalk@entropic.com WWW: http://www.entropic.com/ TruVoice from Centigram * Platform: Windows-NT, Windows 95, Windows 3.1 (limited release), Sun Solaris 2.x * Description: TruVoice., an advanced text-to-speech converter, is available for multiple environments. TruVoice converts text into spoken language. TruVoice adds intelligible, natural-sounding speech to sound enabled platforms. + Small, 1.5MB, memory footprint + Advanced text pre-processing + No vocabulary restrictions + User-definable pronunciation dictionary + Accurately pronounces surnames and place names + Preprocessor provides e-mail and spreadsheet reading capabilities and expands abbreviations. + Multiple languages available: American English, Latin American Spanish, German, French, Italian + Flexible pitch, volume and speech rate + Intonation support for punctuation + Supports navigational capabilities such as, pause, resume and jump forward / jump back with sentence or word boundaries More detailed information is provided in the brochure page on the Centigram WWW site. A demonstration of TruVoice is available on the Centigram WWW pages. * Cost: + Windows versions are $495 for the SDK + Solaris versions are $995 + Contact Centigram for other pricing. * Contact: TruVoice Sales Centigram Communications Corporation 91 East Tasman Drive, San Jose, CA 95134 Ph: (408) 944-0250 Fax: (408) 428-3732 Demo: 800-746 1632 Email: webmaster@centigram.com WWW: http://www.centigram.com/ WinSpeech * Platform: Windows * Description: WinSpeech is a text-to-speech application that reads text and produces speech to the audio output. Features basic text editing tools, talk from editing window, DDE server allows other Windows applications to send text for talking, coach mode for providing audio instructions throughout the program, dictionary editing tools for customizing pronunciation. WSPLIB text-to-speech DLL is a speech functions library for developers. More information available by email. * Requirements: System requirements: IBM PC or compatible computer with Windows 3.1 or higher. Sound card is recommended but not required. * Availability: Freeware available through the PC WholeWare WWW page. * Contact: PC WholeWare 33 Justin Street, Lexington, MA 02173, U.S.A. Email: info@pcww.com WWW: http://www.pcww.com/index.html WreadFiles: File reader for Commodore Amiga * Platform: Commodore Amiga * Description: WreadFiles is a vocal text file reader program for use on the Commodore Amiga. The text is printed to the screen and spoken. Features include: + Text is read in sentences rather than lines. + Dynamic Speech Correction on over 4000 word or word fragments. + Pronunciations for many place names, personal names, foreign names, foreign expressions and abbreviations. + Run from Workbench or CLI. + Used with A1000 (OS 1.3), A3000 (OS 2.04-2.1), and A4000 (OS 3.0) * Requirements: Standard Amiga Translator.library and Narrator.device required. 2.04 versions recommended. 1 Meg or more ram recommended. External speakers required. * Availability: No fee requested for non-commercial use. From: + GEnie: Page 555,3 File Number 24627 + Aminet ftp://ftp.wustl.edu/pub/aminet/util/misc/WreadFiles47.lha * Contact: Written by Michael L. Barlow Email: M.Barlow1@GEnie.geis.com or mbarlow@pacific.telebyte.com or MikeB@cuix.pscu.com ZMD Speech Synthesis "Speaky" Speech Synthesis from ZMD * Platform: DSP solution for platform independent speech synthesis implementation * Description: "Speaky" provides German speech synthesis system in a DSP solution. It includes pre-processing of input ASCII text with unlimited vocabulary, both parametric and non-parametric speech synthesis algorithms, and prosody modelling. More detailed information and audio samples can be found at the ZMD WWW Site. * Contact: Zentrum Mikroelektronik Dresden GmbH Grenzstrasse 28, D-01109 Dresden, Germany Ph: +49-351-8822-306, Fax: +49-351-8822-337 Email: assp@zmd-gmbh.de WWW: http://www.zmd-gmbh.de/ ZMD PCMCIA Speech Synthesis Card * Platform: MS-DOS, Windows * Description: Complete text-to-speech synthesis system for the German language with unlimited vocabulary using VOICE Processor "Speaky". The required pre-processing of the input ASCII text is performed by a software programm that is downloaded automatically from the PCMCIA Speech Synthesis Card during the card's initialising routine. Headphone or active loudspeaker can be connected directly for signal output. More detailed information and audio samples can be found at the ZMD WWW Site. * Requirements: PC Card slot, Card & Socket Services Software * Contact: Zentrum Mikroelektronik Dresden GmbH Grenzstrasse 28, D-01109 Dresden, Germany Ph: +49-351-8822-306, Fax: +49-351-8822-337 Email: assp@zmd-gmbh.de WWW: http://www.zmd-gmbh.de/ ___________________________________________________________________________ Speech Recognition comp.speech FAQ Section 6 * SpeechLinks: Speech Recognition * Q6.1: What is speech recognition? * Q6.2: How is speech recognition performed? * Q6.3: How can I build a simple speech recogniser? * Q6.4: References & books on speech recognition * Q6.5: Speech Recognition Hardware/Software * Q6.6: Speaker Recognition (Verification and Identification) * Q6.7: Integrated Speech Products ___________________________________________________________________________ Q6.1: What is speech recognition? Automatic Speech Recognition Automatic speech recognition is the process by which a computer maps an acoustic speech signal to text. Automatic speech understanding is the process by which a computer maps an acoustic speech signal to some form of abstract meaning of the speech. What does speaker dependent / adaptive / independent mean? A speaker dependent system is developed to operate for a single speaker. These systems are usually easier to develop, cheaper to buy and more accurate, but not as flexible as speaker adaptive or speaker independent systems. A speaker independent system is developed to operate for any speaker of a particular type (e.g. American English). These systems are the most difficult to develop, most expensive and accuracy is lower than speaker dependent systems. However, they are more flexible. A speaker adaptive system is developed to adapt its operation to the characteristics of new speakers. It's difficulty lies somewhere between speaker independent and speaker dependent systems. What does small/medium/large/very-large vocabulary mean? The size of vocabulary of a speech recognition system affects the complexity, processing requirements and the accuracy of the system. Some applications only require a few words (e.g. numbers only), others require very large dictionaries (e.g. dictation machines). There are no established definitions, however, try * small vocabulary - tens of words * medium vocabulary - hundreds of words * large vocabulary - thousands of words * very-large vocabulary - tens of thousands of words. What does continuous speech or isolated-word mean? An isolated-word system operates on single words at a time - requiring a pause between saying each word. This is the simplest form of recognition to perform because the end points are easier to find and the pronunciation of a word tends not affect others. Thus, because the occurrences of words are more consistent they are easier to recognise. A continuous speech system operates on speech in which words are connected together, i.e. not separated by pauses. Continuous speech is more difficult to handle because of a variety of effects. First, it is difficult to find the start and end points of words. Another problem is "coarticulation". The production of each phoneme is affected by the production of surrounding phonemes, and similarly the the start and end of words are affected by the preceding and following words. The recognition of continuous speech is also affected by the rate of speech (fast speech tends to be harder). ___________________________________________________________________________ Q6.2: How is speech recognition performed? A wide variety of techniques are used to perform speech recognition. There are many types of speech recognition. There are many levels of speech recognition / analysis / understanding. Typically speech recognition starts with the digital sampling of speech. The next stage is acoustic signal processing. Most techniques include spectral analysis; e.g. LPC analysis (Linear Predictive Coding), MFCC (Mel Frequency Cepstral Coefficients), cochlea modelling and many more. The next stage is recognition of phonemes, groups of phonemes and words. This stage can be achieved by many processes such as DTW (Dynamic Time Warping), HMM (hidden Markov modelling), NNs (Neural Networks), expert systems and combinations of techniques. HMM-based systems are currently the most commonly used and most successful approach. Most systems utilise some knowledge of the language to aid the recognition process. Some systems try to "understand" speech. That is, they try to convert the words into a representation of what the speaker intended to mean or achieve by what they said. ___________________________________________________________________________ Q6.3: How can I build a simple speech recogniser? QUICKY RECOGNIZER sketch: Doug Danforth provides a detailed account in article 253 in the comp.speech archives. A summary is provided below. It is also available by anonymous ftp ftp://svr-ftp.eng.cam.ac.uk/pub/comp.speech/info/DIY_SpeechReco gnition This is a simple recognizer that should give you 85%+ recognition accuracy. The accuracy is a function of the words you have in your vocabulary. Long distinct words are easy. Short similar words are hard. You can get 98+% on the digits with this recognizer. Overview: * Find the begining and end of the utterance. * Filter the raw signal into frequency bands. * Cut the utterance into a fixed number of segments. * Average data for each band in each segment. * Store this pattern with its name. * Collect training set of about 3 repetitions of each pattern (word). * Recognize unknown by comparing its pattern against all patterns in the training set and returning the name of the pattern closest to the unknown. Many variations upon the theme can be made to improve the performance. Try different filtering of the raw signal and different processing methods. Public Domain Recognition Software Q6.5 contains information on public domain speech recognition software including: Lotec and Myers' Hidden Markov Model software. Discrete Hidden Markov Model Demonstration Software Hidden Markov Models (HMMs) are widely used in speech recognition systems. Joe Picone has put together some demonstration software for basic discrete HMMs including Viterbi and Baum-Welch training and evaluation, random sequence generation (generating data from a model), and model updating (useful for incremental training). There is a simple demo program that supports all of these modes from command line arguments. This allows experiments to test the classic coin-toss examples commonly described in textbooks. The code closely parallels the following textbook: * J.R. Deller, Jr., J.G. Proakis, and J.H.L. Hansen, Discrete-Time Processing of Speech Signals, MacMillan, 1993, ISBN: 0-02-328301-7. The code is written in C++ and is intended to facilitate learning and understanding of the algorithms. The code is available on the ISIP web site: http://www.isip.msstate.edu/software/ Lecture notes corresponding to the examples are also available: http://www.isip.msstate.edu/publications/1996/speech_recognition_short _course ___________________________________________________________________________ Q6.4: References & books on speech recognition * Product Reviews and Comparisons * Using Speech Recognition: Health Issues * On the WWW * Technology: General and Introductory * Technical * Course Notes * Bibliographies and Reference Lists Product Reviews and Comparisons * "Talk Show", Wayne Rash Jr., PC Magazine (USA), Dec 20, 1994. * "Seybold Report on Desktop Publishing" published a nine-page, head-to-head comparison of Dragon's DOS software with IBM's OS/2 software. March 7, 1994; Volume 8, Number 7; Pages 3-11; ISSN:0889-9762; Seybold Publications, P.O. Box 644, Media, PA 19063 USA, phone (610) 565-2480. * McGraw-Hill Inc.'s "BYTE, the Magazine of Technology Integration," published a two-page review of IBM's Personal Dictation System software. May 1994; Volume ?, Number ?; Pages 145-146; ISSN:0360-5280; Editorial, Executive, and Circulation address: One Phoenix Mill Lane, Peterborough, NH 03458 USA, phone ? Using Speech Recognition: Health Issues * The National Center for Voice and Speech provides some basic information on preserving "Vocal Health" on their WWW site: http://www.shc.uiowa.edu/hygiene/home.html * Voice Users Mailing List: detail in Q1.4.html of the FAQ. * Typing Injury FAQ: http://www.cs.princeton.edu:80/~dwallach/tifaq/ has a range of information on Typing Injuries, avoiding them, alternatives and more. * Typing Injuries Page: http://alumni.caltech.edu/~dank/typing-archive.html has links to dozens of useful resources. * Voice Problems -- Prevention and Correction: advice on preserving your voice with specific hints for using speech recognition. ftp://ftp.csua.berkeley.edu/pub/typing-injury/voice-problems * " Talking to a PC May Be Hazard To Your Throat", by Julie Chao in the Wall Street Journal. * " Talking to Computers Has its Hazards", by Gordon Arnaut in The Globe and Mail On the WWW * Survey of the State of the Art in Human Language Technology: Report edited by Ronald A. Cole et. al. with a section on Spoken Input Technologies. http://www.cse.ogi.edu/CSLU/HLTsurvey/ch1node2.html Technology: General and Introductory Some general introduction books on speech recognition technology: * Fundamentals of Speech Recognition; Lawrence Rabiner & Biing-Hwang Juang Englewood Cliffs NJ: PTR Prentice Hall (Signal Processing Series), c1993, ISBN 0-13-015157-2 * Speech recognition by machine; W.A. Ainsworth London: Peregrinus for the Institution of Electrical Engineers, c1988 * Speech synthesis and recognition; J.N. Holmes Wokingham: Van Nostrand Reinhold, c1988 * Speech Communication: Human and Machine, Douglas O'Shaughnessy; Addison Wesley series in Electrical Engineering: Digital Signal Processing, 1987. * Electronic speech recognition: techniques, technology and applications, edited by Geoff Bristow, London: Collins, 1986 * Readings in Speech Recognition; edited by Alex Waibel & Kai-Fu Lee. San Mateo: Morgan Kaufmann, c1990 Technical * Hidden Markov models for speech recognition; X.D. Huang, Y. Ariki, M.A. Jack. Edinburgh: Edinburgh University Press, c1990 * Speech Recognition: The Complete Practical Reference Guide; T. Schalk, P. J. Foster: Telecom Library Inc, New York; ISBN O-9366648-39-2; 377 pages; paperback only. Covers speech recognition in a telephony environment and wish to use call processing hardware based in PCs. It is written using Dialogic hardware as the example for the hardware. * Automatic speech recognition: the development of the SPHINX system; by Kai-Fu Lee; Boston; London: Kluwer Academic, c1989 * An Introduction to the Application of the Theory of Probabilistic Functions of a Markov Process to Automatic Speech Recognition, S. E. Levinson, L. R. Rabiner and M. M. Sondhi; in Bell Syst. Tech. Jnl. v62(4), pp1035--1074, April 1983 * Review of Neural Networks for Speech Recognition, R. P. Lippmann; in Neural Computation, v1(1), pp 1-38, 1989. * Automatic Speech and Speaker Recognition: Advanced Topics, C.H. Lee, F.K. Soong and K.K. Paliwal (Eds.), Kluwer, Boston, 1996. Course Notes * Joseph Picone of the Institute for Signal and Information Processing (ISIP) at Mississippi State University has put the course notes for "Fundamentals of Speech Recognition" on the WWW. The course covers background probability and phonetics/acoustics, speech signal analysis, dynamic programming, dynamic time warping, hidden Markov modelling, language modelling, neural networks, etc. The WWW sites provides the syllabus and lecture notes. WWW: http://www.isip.msstate.edu/publications/1996/ee_8993/ Bibliographies and Reference Lists * WWW searchable online-bibiliography for Phonetics and Speech Technology with more than 8000 entries. Provided by Institut fur Phonetik at Johann Wolfgang Goethe-Universitat Frankfurt. http://www.uni-frankfurt.de/~ifb/bib_engl.html * Computational Speech Processing: Speech Analysis, Recognition, Understanding, Compression, Transmission, Coding, Synthesis ; Text to Speech Systems, Speech to Tactile Displays, Speaker Identification, Prosody Processing : BIBLIOGRAPHY, by Conrad F. Sabourin, 1994, 2 volumes, 1187p, ISBN 2-921173-21-2, INFOLINGUA inc., P.O. Box 187 Snowdon, Montreal, H3X 3T4, Canada. See also: http://gomer.mlink.net/infolingua.html ___________________________________________________________________________ Q6.5: Speech Recognition Hardware and Software The number of speech recognition packages, and the information about the software is changing rapidly. Any help with keeping this information up to date will be appreciated. * Products in the FAQ * Speech Recognition Processors (ICs) * Recognition Information on the WWW * Speech Recognition Resellers and Value-Add In the FAQ: The following speech recognition software/hardware is described in the comp.speech FAQ. _Apple Macintosh_ * Digital Dreams Speech Recognition Plug-Ins * Dragon Dictation Products * Macintosh Speech Recognition Manager * PowerSecretary _Windows (including 95, NT, 3.1)_ * AT&T Watson Speech Recognition * Cambridge Voice for Windows * CustomVoice and CustomTelephone: A&G Graphics Interface Inc. * DragonDictate for Windows * Dragon Dictation Products * Dragon Developer Tools * Ficomp Interpreter 6000 * IBM VoiceType Dictation and Control * IN CUBE * Kurzweil Speech Recognition (2 products) * Lernout & Hauspie ASR SDK * Listen for Windows 2.0 from Verbex Voice Systems * Microsoft Speech Recognition * NCC Dictate * Phonetic Engine 500 (PE500) from Speech Systems, Inc. * Philips Speech Recognition (2 products) * ProNotes Voice Tools * PureSpeech * smARTspeak from Advanced Recognition Technologies, Inc. * Visual Voice from Stylus Innovation * VoiceAssist for Windows from Creative Labs, Inc. * VoiceServer for Windows * Whisper * WildCard Speech Products _DOS_ * DATAVOX - French * Dragon Developer Tools * Ficomp Interpreter 6000 * Jialong He's Speech Recognition Research Tool * smARTspeak from Advanced Recognition Technologies, Inc. * Votan VPC2100 Voice Card and VSP 1010 Speech Processor _OS/2_ * IBM VoiceType Dictation and Control _Unix_ * AbbotDemo * BBN Hark Telephony Recognizer * EARS: Single Word Recognition Package * Ficomp Interpreter 6000 * Hidden Markov Model Toolkit (HTK) from Entropic * IN CUBE * Jialong He's Speech Recognition Research Tool * Lotec Speech Recognition Package * Myers' Hidden Markov Model software * NICO Artificial Neural Network Toolkit * Nuance Speech Recognition System * PureSpeech * recnet _Integrated Circuits and Dedicated Hardware_ * HM2007 - Speech Recognition Chip * OKI VRP6679 - Speech Recognition Chip * Sensory Inc. Integrated Circuits * Speech Commander - Verbex Voice Systems * Voice Control Systems Recognition * VCS 2030 & 2060 Voice Dialer _Other Platforms_ * Simon Says (NeXT) * Voice Command Line Interface (Amiga) * Visus SpeechKit _Unknown_ * Berkeley Restaurant Project (BeRP) * Lernout & Hauspie ASR (3 products) * Voice-Trek 2.0 * Voicetek Corp. * Voice Processing Corporation Speech Recognition Product Line Speech Recognition Processors (ICs) Jean-Pierre Lereboullet has put together a detailed list of Voice Recognition Processors which covers about 15 ICs and pieces of related hardware (including D6106, HM2007, MSM6679, RSC-164, TC8860F/64F/65F, 5A128). The document is available on the comp.speech ftp server: ftp://svr-ftp.eng.cam.ac.uk/pub/comp.speech/info/VoiceRecognitionProce ssors Recognition Information on the WWW In addition to the entries on speech recognition in this FAQ, the following WWW sites provide information on speech recognition: Commercial Speech Recognition: Russ Wilcox of PureSpeech Inc. http://www.tiac.net/users/rwilcox/speech.html Macintosh Speech Resources and Apps http://www.cs.cmu.edu/~lenzo/mac_speech_apps.html Speech Recognition Information: 21st Century Eloquence http://www.voicerecognition.com/ Applied Speech Technology Laboratory of CLSI at Stanford http://csli-www.stanford.edu/users/bscott/SRTech.html Speech Toys Speech Recognition Page http://www.speechtoys.com/spchtoys/sprec.html Speech recognition product lists: postings to comp.speech ftp://svr-ftp.eng.cam.ac.uk/pub/comp.speech/info/SpeechRecognit ionProducts Search Alta Vista for Speech Recognition Search Lycos for Speech Recognition Yahoo pages on Speech Recognition http://www.yahoo.com/business/corporations/computers/software/v oice_recognition/ http://www.yahoo.com/Science/Computer_Science/Artificial_Intell igence/Natural_Language_Processing/Speech_Recognition/ Speech Recognition Resellers and Value-Added Services 1stVoice 2470 El Camino Real, Suite 110, Palo Alto CA 94306-1701 Ph: 415-857-1320, Fax: 415-856-6996 WWW: http://www.1stvoice.com/ Email: mail@1stvoice.com Dragon Dictation Products 21st Century Eloquence 325-A Royal Poinciana Plaza, Palm Beach, Florida 33480, USA Ph: 800-245-2133, Fax: 407-835-4901 WWW: http://www.voicerecognition.com/ Kurzweil, IBM VoiceType, Dragon, Kolvox Auscript (Australia) Suite 2, Level 3, 60-70 Elizabeth St, Sydney, NSW 2000, Australia Ph: +61-2-238 6565, Fax: +61-2-238 6566 WWW: http://www.auscript.com.au/ Dragon Systems BRITE WWW: http://www.brite.com/ Computer Telephony Integration & Interactive Voice Response DAX Systems, Inc. 30 Chapin Road, Unit 1201, P.O. Box 778, Pine Brook, NJ/USA 07058 Ph: +1-201-227-8111, Fax: +1-201-227-8197 Email: info@daxsystems.com WWW: http://www.daxsystems.com/ Computer Telephony and Integrated Voice Response HealthCare Resources 1444 Aviation Blvd, #103, Redondo Beach, CA 90278, USA Ph: +1-310-937-5156, Fax: +1-310-937-5159 EMail: Scalif@AOL.COM Power Secretary & Dragon Dictate. Specializing in: Medical/Dental, Motion Picture Industry, Carpal Tunnel related and Disabled Persons. O'Brien Resources Ph: (540) 347-4988 (Address unknown) Email: obrien@crosslink.net WWW: http://www.crosslink.net/~obrien/ Kurzweil Voice Recognition Products SCI VoiceAutomated 215 1/2 Main Street, Huntington Beach, CA 92648, USA Ph: 800-597-6600, Ph: +1-714-969-7632, Fax: +1-714-969-0122 http://www.voiceautomated.com/ IBM VoiceType, Kurzweil Voice, DragonDictate and Philips speech. Synapse 3095 Kerner Blvd., Suite S, San Rafael, CA 94901, USA Ph: (415) 455-9700, Fax: (415) 455-9801 Email: SYNAPSE_ADAPTIVE@msn.com WWW: http://www.synapseadaptive.com/ Dragon Systems, Kurzweil and IBM products. Talk Technology Ph: 1-800-270-1672, Fax: 1-516-360-1213 Email: info@talktechnology.com http://www.talktechnology.com/ Talk Technology, Inc. Tel: +1-718-745-9199, Fax: +1-718-499-6480 Email: mnm@pipeline.com WWW: http://www.usbusiness.com/talk/ Dragon Dictate and portable (notebook) solutions ToppCopy Telecom Email: ffalzett@toppcopy.com WWW: http://www.toppcopy.com/ Philips Digital Dictation VoiceWare Systems 230 California Street, Suite 410, San Francisco, CA 94111 Ph: (415) 433-2001, Fax: (415) 433-6909 Email: info@talk2type.com WWW: http://www.talk2type.com/home.htm IBM, Dragon Systems, Kurzweil Applied Intelligence, WildCard Technologies WorkLink A.D.A. Solutions by WorkLink 2566-A Telegraph Avenue, Berkeley, California 94704 USA Ph: 510-848-8363, Fax:510-848-7322 WWW: http://www.worklink.net/ Email: wayne@worklink.net Dragon Dictation Products AbbotDemo * Platform: SunOS4, IRIX, Linux, HU-UX * Description: Large vocabulary, speaker independent, continuous automatic speech recognition system. Uses recurrent neural networks and hidden Markov models with a 5,000 word vocabulary upgradable) and a trigram word grammar. Includes a front end for waveform capture and display (including spectrogram) and a graphical display of the phoneme representation as well as a rewriting display of the best guess word sequence. * Requirements: UN*X, X, 8 Mbyte free RAM, 486DX or faster processor, 16 bit soundcard, reasonable quality microphone and a copy of the Wall Street Journal newspaper. * Price: Free for non-commercial use * Availability: By anonymous ftp from ftp://svr-ftp.eng.cam.ac.uk/pub/comp.speech/recognition/AbbotDemo * Note 1: This is not a complete system for dictation. * Note 2: At present there are no sources with this distribution. For sources for an earlier version see the recnet entry. * Note 3: Not supported. * Contact: AbbotDemo@compute.demon.co.uk Tony Robinson Cambridge University Engineering Department Trumpington Street, Cambridge, CB2 1PZ, UK Tel: +44-1223-332815 Fax: +44-1223-332662 AT&T Watson Speech Recognition * Platform: Windows 95/NT on a Pentium 75 Mhz or higher * Description: Watson is a software implementation of AT&T Bell Laboratories voice processing technology. Watson includes BLASR Speech Recognition and FlexTalk speech synthesis (see Q5.5). It requires no special hardware to run other than a standard sound card and/or phone card. Technical details for BLASR Speech Recognition include: + Compliant with Microsoft Speech API and Telephone API + Speaker independent, continuous speech recognition + Fast, run-time vocabulary change + Open mic and telephone line environments + SoundBlaster compatible sound card and drivers required + Subword models and whole-word digit models + Background, silence, and filler/garbage models + 50 word name vocabulary or 100 word phrase real-time recognition with 95% accuracy + Rejection of out-of-vocabulary words + American English only - other languages in development + Barge-in speech begin/end notification - requires hardware echo cancellation The AT&T Advanced Speech Products Group home page provides more detailed information including a Frequently Asked Questions list, information for application developers on the Independent Software Vendor (ISV) Program (including info on the SDK, licensing, and the training program). * Requirements: Uses 2 MB RAM, 10 MB Disk. Requires a Pentium 75 MHz or higher CPU (uses * Cost and Availability: WATSON is a software-based speech platform with a Software Developers Kit (SDK) that allows application developers to use voice processing in their applications. It is not available as a stand-alone product. Licensing information (inc. price) is provided in the AT&T Advanced Speech Products Group home page * See also: Watson FlexTalk speech synthesis in Q5.5, Microsoft Speech API, and Advanced Speech API. * Contact: AT&T Advanced Speech Products Group Suite 700, 44 East Mifflin Street, Madison, WI 53703, USA Ph: 1-800-5-WATSON, Fax: 1-608-259-2269 Email: aspg@attmail.com WWW: http://www.att.com/aspg/ BBN Hark Telephony Recognizer * Platform: Available for Unix-based workstation and PC platforms including IBM RS6000/AIX and Pentium/SCO Unix. * Description: Large vocabulary (2,000+ words), speaker independent, continuous ASR software. Specifically designed for large scale telephony applications. Using a client/server architecture, all features and capabilities are integrated in one software product instead of on separate boards. Very memory efficient, the Hark Telephony Recognizer runs in as little as 2MB of physical memory. Multiple recognizers can be run on a single platform. Uses Hidden Markov Model and phoneme-based BBN recognition algorithms. An API is provided for integration with existing applications. A developer's toolkit is available. * Price and availability: Price varies depending on vocabulary size. Version 3.0 available immediately. * Misc: BBN Hark provides application design and human factors consulting services. Regular monthly training classes on developing speech-enabled applications are held at BBN Hark's Cambridge (Mass) headquarters. * WWW: For additional information see BBN Hark's home page. * Contact: BBN Hark Systems 70 Fawcett Street, Cambridge, MA 02138, USA Tel: 617-873-4636 Fax: 617-873-2473 WWW: http://www.bbn.com/bbn_hark/HarkHome.html Berkeley Restaurant Project (BeRP) * Description: BeRP is a test bed for a speech recognition system being developed by the International Computer Science Institute in Berkeley, CA. BeRP is a medium-vocabulary, speaker-independent spontaneous continuous speech understanding system. BeRP functions as a knowledge consultant whose domain is the restaurants in the city of Berkeley. The system serves as a testbed for several research projects, including robust feature extraction, connectionist phonetic likelihood estimation, automatic induction of multiple pronunciation lexicons, foreign accent detection and modeling, advanced language models, and lip-reading. * Note: As far as I know the BeRP software is in-house software - that is, it is not made available for distribution. * More information: http://www.icsi.berkeley.edu/real/berp.html Cambridge Voice for Windows * Platform: Windows * Description: Speaker-independent recognition of continuous speech in real time. Vocabularies can range from small to very large (more than 60,000 word forms). Support is planned for languages including English, Danish, Dutch, French, German, Italian, Norwegian, Spanish, Swedish, and Japanese. The engine complies with the Microsoft Speech API. * Contact: Cambridge Group Research, Ltd. Box 7290, Buffalo Grove, IL 60089 Ph: (708) 821-1040, Fax: (708) 821-1041 E-mail: 76061.3350@compuserve.com CustomVoice and CustomTelephone: A&G Graphics Interface Inc. * Platform: Windows * CustomVoice: Speech recognition custom control for Visual Basic, Visual C++, Borland C++, and other development platforms that support *.VBX. Provides an engine/proprietary independent development platform for speech recognition. Currently supports ICSS, but should soon support other platforms. Includes a grammar debugger and parser APIs to parse spoken speech into useful data types. Requirements: 486/DX or better PC, Windows 3.1 or Windows for Workgroups, 8Mb RAM (minimum), SoundBlaster 16, microphone, and mouse. Supports Visual Basic, Visual C++, Borland C++, and Delphi. * CustomTelephone: Windows-based developers tool that allows programmers to build speech enabled "telephony" applications via standard custom control properties (VBX). It supports IBM VoiceType Application Factory (VTAF), a continuous speech, speaker independent speech recognizer, and supports voice response boards such as Dialogic. Comes with a VB custom control, pre-built grammar sets for common data types, an interactive grammar debugger to identify valid speech patterns, and parser API functions that convert recognized speech into data types supported by VB, C++ and Delphi. Includes sample applications with source code, and VBX, VCL and DLLs. Bundled with speech recognition engines. Requirements: 486/DX or better, Windows 3.1 or Windows for Workgroups, 8Mb RAM (minimum), SoundBlaster or compatible sound card, Dialogic D2X or D4X board, and mouse. Microphone and speaker optional. Supports Visual Basic, Visual C++, Borland C++, and Delphi. * Contact: A&G Graphics Interface 51 Gore Street, Cambridge, MA 02141-1213 , USA Ph: +1-617-492-0120, Fax: +1-617-427-2133 Email: customvc@world.std.com CompuServe: 74774,273 CompuServe ( GO SPEECH ) WWW: http://www.customvoice.com/ DATAVOX - French * Platform: PC / DOS * Description: Continuous speech - speaker independent or dependent. * Requirements: 2 PC format boards (RdF1000 and TdS 96/25) and an A/D - D/A module (ASA116) * Misc: Application software may dialog with DATAVOX through 2 types of interfaces : + Keyboard overlay: The application software may be used with any PC compatible package. No specific adaptation is necessary, you only need to define your configuration with the application software. + C library: Allows a user-written program to drive the recognition system. DATAVOX is based on the AMADEUS speech recognition software developed at LIMSI. It provides + Continuous speech recognition with 500 words speaker dependent, 50 words speaker independent (custom-made vocabulary). + Grammar of the application language (syntax acquisition, verification and simplification software). + Large vocabulary : DATAVOX can recognize vocabularies of several thousand words as long as there are no more than 500 words in the active vocabulary at any given node. It takes less than 1 second to change syntax and vocabulary. + Training controlled by the system (use of co-articulation models). + Response time less than 500 ms for any phrase length. + Synthetis (ADPCM) can be heard simultaneously while recognition is being carried out. * Contact: VECSYS Le Chene rond, 91570 Bievres, France Voice: 33 1 69 41 15 04, Fax: 33 1 69 41 24 30 Digital Dreams Speech Recognition Plug-Ins * Platform: Apple Macintosh * Description (General): A suite of speech plug-ins for the interactive multimedia market which enable developers to quickly incorporate speech recognition into their titles without having to resort to a low-level programming language, such as C. Speech plug-ins bridge the gap between a speech recognition API, such as Apple's PlainTalk Speech Recognition technology, and authoring/development environments, such as Macromedia Director or HyperCard. Digital Dreams currently offers Macintosh speech plug-ins for Macromedia Director and HyperCard. Support for other environments, including AppleScript, Apple Media Tool, Authorware, and Windows is being developed. Currently available for North American Adult English. More information is available on the Digital Dreams WWW site. * ShockTalk: is a combination of Netscape, ShockWave and Speech Recognition technologies for the Power Macintosh and Quadra AVs that enables you to navigate web sites and hyperlinks using spoken commands as well as create shockwave movies that respond to spoken user interactions. * Requirements: Power Macintosh (PowerPC w/ MacOS) Microphone (PlainTalk compatible) PlainTalk Speech Synthesis and PlainTalk Speech Recognition Netscape Navigator * Contact: Digital Dreams 4308 Harbord Drive, Oakland, CA, 94618, USA Tel: (510) 547-6929 Fax: (510) 547-6799 email: dreams@surftalk.com WWW: http://www.surftalk.com/ FTP: ftp://ftp.surftalk.com/ DragonDictate for Windows * Platform: Windows * Description: Information moved to the page on Dragon Dictation products including DragonDictate for Windows Dragon Dictation Products * Dragon NaturallySpeaking * DragonDictate for Windows * Dragon PowerSecretary * General Information Dragon NaturallySpeaking * Platform: Windows * Description: General purpose, continuous speech dictation system. Personal Edition has a 30,000 word active vocabulary and comes with a 200,000+ word pronunciation dictionary; users can also add their own words or phrases. More information on Dragon's NaturallySpeaking web site. * Requirements: 133Mhz Pentium, 32 MB RAM (Windows 95) or 48 MB RAM (Windows NT 4.0), supported sound card. * Price: see Dragon's NaturallySpeaking web site. * Related products: see general information below * Contact: see general information below DragonDictate for Windows * Platform: Windows * Description: Speech-to-text dictation system. Discrete dictation; continuous command/control; speaker-adaptive. Also provides mouse movement for hands-free operation of Windows. Comes with a 120,000 word pronunciation dictionary; users can also add their own words or phrases. Dictate directly into any application. Available in US and UK English, French, Italian, German, Spanish, and Swedish. Add-on vocabularies for medicine, law, business and finance, computers and technology, journalism. Available as DragonDictate Singles Editions (10,000 words active), DragonDictate Personal Edition (10,000 words active), DragonDictate Classic Edition (30,000 words active), DragonDictate Power Edition (60,000 words active). Includes Office97 support. More information on the Dragon Systems web site. * Requirements: 486/66, 7-10 MB dedicated RAM (depending on edition), Windows 3.1x, NT 3.51, or 95. Supported sound boards: Creative Labs Sound Blaster 16, Microsoft Windows Sound System, IBM M-Audio Capture/Playback Adapter, many notebooks with built-in audio. See Dragon Systems Compatibility list for details. * Price: Check at the Dragon Systems web site. * Related products: see general information below * Contact: see general information below Dragon PowerSecretary * Platform: Apple Macintosh * Description: Speaker dependent/adaptive system requiring words to be separated by short pauses. Available as PowerSecretary Power Edition, Personal Edition, PowerSecretary MED for Healthcare Professionals. Vocabulary: 30,000 - 60,000 at any one time, automatically selected from 120,000-word dictionary. * Requirements: Power Macintosh 6100, 7100, 8100, Performa 6100 series, Powerbook 540, 68040 class Macintosh such as Quadra 660AV, 700, 800, 840AV, 900, 950, Centris 650 and 660AV. Hard Disk with at least 25Mb free. System 7.5 or greater (Some systems require add-on hardware) * More information: PowerSecretary home page * Related products: see general information below * Contact: see general information below General Information Dragon Dictation Products * Dragon NaturallySpeaking * DragonDictate for Windows * Dragon PowerSecretary * General Information Dragon Developer Products * Dragon PhoneQuery * DragonXTools * Dragon SpeechTool * Dragon VoiceTools Related Web Sites * Simon Crosby's FAQ for DragonDictate Contact: * Dragon Systems, Inc. 320 Nevada Street, Newton, MA 02160, USA Tel: 1-617-965-5200 or 1-800-TALK-TYP Fax: 1-617-527-0372 Email: info@dragonsys.com WWW: http://www.dragonsys.com/ CompuServe: GO DRAGON Dragon Developer Tools * Dragon PhoneQuery * DragonXTools * Dragon SpeechTool * Dragon VoiceTools Dragon PhoneQuery * Platform: Windows NT * Description: Software for building voice response systems. Callers are able to do the following: Ask for information using completely natural and continuous language. Have a spoken dialog to fine tune a request. Request information to be faxed, sent by electronic mail, or read over the phone, using text-to-speech. More information on the Dragon Systems telephony pages. * Requirements: Pentium or Pentium Pro PC running Windows NT 4.0. Telephone interconnect requirements vary by application. * Related products: see general information below * Contact: see general information below DragonXTools * Platform: Windows * Description: VBX and OCX controls that allow an application to control DragonDictate's capabilities, ranging from small vocabulary command and control to customized large vocabulary dictation. More information is available on the Dragon Developer pages * Related products: see general information below * Contact: see general information below Dragon SpeechTool * Platform: Windows * Description: Create small, optimized vocabularies for your speech-enabled applications, or supplement DragonDictate's extensive built-in vocabularies with specialized terms and names. More information is available on the Dragon Developer pages * Related products: see general information below * Contact: see general information below Dragon VoiceTools * Platform: Windows, DOS * Description: integrate small-vocabulary speech recognition directly into your DOS and Windows 3.1x applications. More information is available on the Dragon Developer pages * Related products: see general information below * Contact: see general information below General Information Dragon Dictation Products * Dragon NaturallySpeaking * DragonDictate for Windows * Dragon PowerSecretary * General Information Dragon Developer Products * Dragon PhoneQuery * DragonXTools * Dragon SpeechTool * Dragon VoiceTools Related Web Sites * Simon Crosby's FAQ for DragonDictate Contact: * Dragon Systems, Inc. 320 Nevada Street, Newton, MA 02160, USA Tel: 1-617-965-5200 or 1-800-TALK-TYP Fax: 1-617-527-0372 Email: info@dragonsys.com WWW: http://www.dragonsys.com/ CompuServe: GO DRAGON EARS: Single Word Recognition Package * Platform: Linux and Unixs with the Voxware sound driver * Description: Intended as a limited ready-to-use single word recognizer. However, its design aims at being a platform for various kinds of methods used in speech recognition (SR). EARS is designed to be a flexible environment for recognition system components; for example, take this feature extractor and that recognizing method, and this list of words. New methods for single word recognition can be integrated easily, as EARS uses C++ abstract base classes. You speak the words you want to be recognized later. Your utterances can be saved to RIFF WAV files for inspection, change or delete them before they are further processed to the pattern files on which the recognizer is finally trained. As of version 0.20, the feature extractors are: Rasta-PLP, PLP, LPC, Mel-Cepstrum. The implemented recognizers are: DTW and non-recurrent neural nets on fixed-size sound patterns. * Requirements: Soundcard with mic * Misc 1: The current version is an Alpha release. * Misc 2: For more information subscribe to the EARS mailing list. Send email to majordomo@phil.uni-sb.de with "subscribe ears-list" in the body. * Misc 3: Niels Thorwirth (thorwir@pi4.informatik.uni-mannheim.de) has made changes to Version 0.14 which support the AF audio server software (see Q1.11) and the OGI Speech Tools (see Q1.9) so that EARS is more portable to other UNIX platforms. Available by email to Niels. * Requirements: Soundcard with mic * Availability: Source and Linux binaries are available by anonymous ftp ftp://svr-ftp.eng.cam.ac.uk/pub/comp.speech/recognition/ears-0.26. tar.gz ftp://sunsite.unc.edu/pub/Linux/apps/sound/speech/ears-0.26.tar.gz * Contact: Ralf W. Stephan: ralf@ark.franken.de Ficomp Interpreter 6000 * Platform: DOS, Windows 3.1, Win95, Win NT, UNIX * Description: Ficomp Systems, inc., is a systems integrator that has developed commercial speaker-dependent, continuous-speech recognition applications for use in high noise environments on several platforms. Applications are specialized in the finance industry for exchange floors, banks and brokerage firms. * Contact: Ficomp Systems, Inc. Ph: (732) 274-2600, Fax: (732) 274-2601 117 Docks Corner Road, Dayton, NJ 08810 E-Mail: fsisales1@aol.com WWW: http://www.ficompsystems.com/ HM2007 - Speech Recognition Chip * Platform: Intergrated circuit. * Description: HM2007 is a 48-pin single chip CMOS voice recognition LSI circuit with on-chip analog front end, voice analysis, recognition process and system control functions. A 40 word isolated-word voice recognition system can be composed of an external microphone, keyboard, SRAM and a few other components. When combined with a microprocessor, an intelligent recognition system can be built. A demo board for this chip is being distributed by The Summa Group. * Cost: Approx US$16 for the HM2007 and US$160 for the demo board. * Misc: Jean-Pierre Lereboullet's document on Voice Recognition Processors provides additional information on the HM2007. * Producer: HUALON Microelectronic Corp. USA Tel: (415) 288 0390 Fax: (415) 288-0399 * Distributor 1: Marywale Engineering Company Tel: (602) 247 4451 Fax: (602) 247 6167 Email: meco@indirect.com * Distributor 2: The Summa Group Limited One California Street, Suite #1940, San Francisco, CA 94111 Ph: (415) 288-0390 * Distributor 3: Images Company 39 Seneca Loop, Staten Island, NY 10314, USA Ph: +1-718-698-8305, Fax: +1-718-982-6145 Sells single piece quanities of HM2007 48Pin Dip Chip and HM2007 52 Pin PLCC style chip. Sells HM2007 Demo Kits unassembled $100.00 and assembled $135.00 (using 48 Pin dip chip) Entropic's HTK (HMM Toolkit) * Platform: Range of Unix platforms. * Description: HTK is a software toolkit for building continuous density HMM based speech recognisers. It consists of a number of library modules and a number of tools. Functions include speech analysis, training tools, recognition tools, results analysis, and an interactive tool for speech labelling. Many standard forms of continuous density HMM are possible. Can perform isolated word or connected word speech recognition. It van model whole words, sub- word units. Can perform speaker verification and other pattern recognition work using HMMs. HTK is now integerated with the ESPS/Waves speech research environment which is described in Section 1.9. * Misc 1: The availability of HTK changed in early 1993 when Entropic obtained exclusive marketing rights to HTK from the developers at Cambridge. * Misc 2: More detailed information on HTK is available from the Entropic WW server: http://www.entropic.com/htk.html * Cost: On request. * Contact: Entropic Research Laboratory, 600 Pennsylvania Ave, S.E. Suite 202, Washington, D.C. 20003, USA Phone: (202) 547-1420. email - info@entropic.com WWW: http://www.entropic.com/ IBM VoiceType Dictation * Platform: OS/2 and Windows * Description: IBM VoiceType Dictation supports speech input at 70-100 words a minute and can be used to control your desktop and applications. Isolated-word, speaker-dependent system using a speech adapter card. Available for U.S. English, U.K. English, French, German, Italian, Spanish and Arabic. Provided with a general office vocabulary and support for major OS/2 and Windows applications. Additional specialised vocabularies are available: + US: Legal, Emergency Medicine, Radiology and Journalism + UK: Legal + IT: Radiology * Requirements: See http://www.software.ibm.com/workgroup/voicetyp/vtprod13.html * Cost: See http://www.software.ibm.com/workgroup/voicetyp/vtordna.html * Misc: An IBM VoiceType Dictation FAQ is supported by UltraMedia Systems International (a distributor of IBM VoiceType): http://www.infi.net/~ums/ibmfaq.htm * Demo software: Available on the IBM WWW site: http://www.software.ibm.com/workgroup/voicetyp/vtcust1.html * Contact: US Ph: 1-800-TALK-2-ME or 1-914-766-1900. Email: talk2me@vnet.ibm.com WWW: http://www.software.ibm.com/workgroup/voicetyp/vtcust1.html IBM VoiceType Control (US Only) * Platform: OS/2 and Windows * Description: VoiceType Control is a speech recognition navigator that lets you control programs by speaking. VoiceType Control converts voice commands to keystroke macros. The program provides speaker independent, continuous speech recognition, so you do not have to train the program for your specific speech patterns. * Requirements: ? * Cost: ? * Demo software: http://www.software.ibm.com/workgroup/voicetyp/vtcust2.html * Contact: US Ph: 1-800-TALK-2-ME or 1-914-766-1900. Email: talk2me@vnet.ibm.com WWW: http://www.software.ibm.com/workgroup/voicetyp/vtcust2.html IN CUBE * Platform: Three versions for Windows 95, Windows NT and Sun SPARCstations * IN CUBE for Windows 95: Developed for general purpose Windows 95 users. It is packaged for online distribution with a full working demo and an option to register and unlock the full product. The system uses Command Corp's Mark II continuous speech recognition engine and handles changable lexicons of up to 75 commands. + Price: $49.95 US + Requirements: 386/25MHz processor or better, Microsoft Windows 3.1 or later, Windows compatible sound card or built-in audio, and microphone. + Availability: http://www.commandcorp.com/cci/win95.html Demo mode available. * IN CUBE Mark II Pro for Windows NT: IN CUBE is a continuous realtime speech recognition system developed to provide a fast and convenient means of window navigation and voice macro command input for command intensive applications like CAD and publishing. Speaker-dependent training and ability to add new commands and macros. + Price: $495 including the PRO 8 microphone. $540 including the MT 858 desk microphone. + Requirements: Windows NT, Windows NT-compatible audio board (16-bit audio recommended). + Availability: http://www.commandcorp.com/cci/pront.html Demo available. * IN CUBE Voice Command for Sun SPARCstations: Provides continuous realtime speech recognition system for window navigation and voice macro command input to the workstation. Speaker-dependent training and ability to add new commands and macros. An IN CUBE Application Programming Interface is available with a library of linkable object modules is available for developers. + Price: $495 per seat. The developer's API sells for $695. + Requirements: SUN OS 4.1.x or Solaris 2.x with OpenWindows and Motif. Works with all audio-equipped SPARCs and clones. Models range from SPARCStation 1s to SPARCStation 20s. + Availability: http://www.commandcorp.com/cci/in3sparc.html A free 5 day evaluation license is available. * Contact: Command Corp. Inc., 3761 Venture Drive, PO Box 956099, Duluth, Georgia, 30136, USA Ph: +1-770-813-8030 Email: in3@commandcorp.com WWW: http://www.commandcorp.com/incube_welcome.html Jialong He's Speech Recognition Research Tool * Platform: SUN SPARC (SunOS), PC (MSDOS) * Description: This is a speech recognition research tool. it contains a feature extraction program and three speech recognizers: a DTW recognizer, discrete didden Markov model (DHMM) based recognizer and Continuous density hidden Markov mode (CHMM) with Gaussian mixture functions based recognizer. The utilities are grouped as: + feature -- extract featue vectors from a speech signal (MFCC etc.) + dtwcmp -- dynamic time-wapping (DTW) comparision. + gensym -- turn vector sequences to discrete observation symbols. dhmm -- discrete HMM training program. dtest -- DHMM companion test program. + chmm -- continuous density HMM training program. viterbi -- CHMM companion test program. Note, this is a research tool not a complete speech recognition system. * Availability: By anonymous ftp: MSDOS Version UK: ftp://svr-ftp.eng.cam.ac.uk/pub/comp.speech/recognition/s pchtool.zip Germany: ftp://ftp.informatik.uni-ulm.de/pub/NI/jialong/spchtool.z ip Sun SPARC version, compiled with GNU C UK: ftp://svr-ftp.eng.cam.ac.uk/pub/comp.speech/recognition/s pch_sun_v1.tar.gz Germany: ftp://ftp.informatik.uni-ulm.de/pub/NI/jialong/speech_sun _v1.tar.gz * See also: Jialong He's Speaker Recognition (Identification) Tool * Contact: Jialong He email: jialong@neuro.informatik.uni-ulm.de Kurzweil Voice for Windows * Platform: Windows 3.1 or later * Description: Kurzweil Voice for Windows is a dictation product enabling the user to create text and enter data by speaking to Windows-based applications. System is adaptive but requires no initial training. Users can choose either 30,000 or 60,000 word active vocabulary. Application command translation templates for popular Windows application such as WordPerfect, 1-2-3, Organizer, Word (30+ applications are listed on the Kuzweil WWW pages). More detailed information is available on the Kurzweil WWW pages. * Requirements: 486DX/33 or higher, 8 or 16 MB dedicated memory (depends on vocabulary, 30 MBs dedicated disk space, VGA or higher, Kurzweil-supplied microphone and DSP board. * Contact: Kurzweil Applied Intelligence, Inc. 411 Waverley Oaks Road, Waltham, MA 02154 USA Phone: 1-800-380-1234 Email: info@kurzweil.com WWW: http://www.kurzweil.com/ Kurzweil Clinical Reporter * Platform: Windows 3.1 or later * Description: Kurzweil Clinical Reporter is a voice-activated clinical reporting system for computer-based patient records. The family of products includes: + VoiceEM for emergency medicine + VoiceEM/TR for triage reporting + VoiceRAD for diagnostic imaging and radiology + VoicePATH for surgical and anatomical pathology + VoiceMED for Primary Care for family medicine, internal medicine and pediatrics + VoiceORTHO for office-based orthopaedic surgery + VoiceCATH for invasive cardiology + VoiceReport for general reporting * More information: from the Kurzweil WWW pages: http://www.kurzweil.com/medical/ * Contact: Kurzweil Applied Intelligence, Inc. 411 Waverley Oaks Road, Waltham, MA 02154 USA Phone: 1-800-380-1234 Email: info@kurzweil.com WWW: http://www.kurzweil.com/ Lernout & Hauspie ASR 1000/T and 1000/M [Note: L&H asr200/A is described below.] * L&H asr1000/T: ASR for the Telephony and Telecommunications Market * L&H asr1000/M: TTS for the Computer and Multimedia Market * Description: Automatic speech recognition software providing continuous speech recognition, isolated word recognition, keyword spotting or continuous digits recognition. The engine is speaker independent, and phoneme-based with optimization for commonly used words. General features include: + Languages available: US English, German, French, Spanish (Castilian), Dutch. + Available vocabulary: >100,000 words. + Line adaptation. + Rejection of out of vocabulary/grammar words. + N-best alternatives for isolated word recognition and keyword spotting. + Push to talk. * asr1000/T + Single channel platform examples: Motorola 56156, TI TMS320C2X/C3X/C5X + Multi-channel platform examples: TI TMS320C3X/C5X, AT&T DSP32C/3210, Motorola 96000 + Input: 8 kHz telephone sampling * asr1000/M + Single processor platform examples: Intel 486/Pentium + Input: 8 kHz telephone or 11 kHz microphone sampling * See also: L&H ASR SDK for Windows * More Information: on the Lernout & Hauspie WWW pages: http://www.lhs.com/asr.html * Cost: Unknown * Contact: Lernout & Hauspie Speech Products 800 West Cummings Park, Suite 3100 Woburn, MA 01801, USA Tel: (617) 238 0960 Fax: (617) 238 0986 Email: sales@lhs.com WWW: http://www.lhs.com/ Lernout & Hauspie ASR 200/A for the Automotive and Industrial Market * Description: Automatic speech recognition software providing isolated word recognition, keyword spotting and alphabet recognition (optional). This engine is robust, speaker independent and word based. Other features: + Vocabulary: 100 words US English + Voice activation detection + Response time + Platform examples: Analog Devices ADSP2101/5 + Input: 8 kHz telephone or microphone sampling * See also: L&H ASR SDK for Windows * More Information: on the Lernout & Hauspie WWW pages: http://www.lhs.com/asr.html * Cost: Unknown * Contact: Lernout and Hauspie Speech Products 20 Mall Road, 4th Floor Burlington, MA 01803, USA Ph: +1-617-238-0960, Fax: +1-617-238-0986 Email: sales@lhs.com WWW: http://www.lhs.com/ Lernout & Hauspie ASR SDK * Platform: Windows * Description: Windows based Software Development Kits are available for integrating automatic speech recognition technology with Windows based PC applications. * Requirements: IBM-compatible 486 DX/33 MHz + 8 MB RAM + MS DOS 5.0 + MS Windows 3.1 (or higher) + Sound Blaster compatible sound board. * See also: L&H ASR Products * More Information: on the Lernout & Hauspie WWW pages: http://www.lhs.com/asr.html * Contact: Lernout and Hauspie Speech Products 20 Mall Road, 4th Floor Burlington, MA 01803, USA Ph: +1-617-238-0960, Fax: +1-617-238-0986 Email: sales@lhs.com WWW: http://www.lhs.com/ Listen for Windows 2.0 from Verbex Voice Systems * Platform: Windows * Description: Listen for Windows Version 2.0 is a Speaker Independent software product that provides continuous speech recognition for Windows applications. The product works with most industry standard sound cards and PCs with inbedded audio chips. Listen for Windows comes with over 16,000 commands in speech interfaces for over 40 software applications, such as MS Office, Lotus SmartSuite,Quicken, etc. The Listen Command Editor allows a user to change or add commands to existing speech interfaces or create new speech interfaces for most Windows applications. More detailed information is available on the Verbex Listen for Windows page. Verbex also sells Verbal Advantage Voice Browser for controlling a web browser, Verbal Advantage DeskTop for controlling desktop applications. * Requirements: 486/25SX PC or higher * Pricing and Availbility: See the Verbex ordering page for pricing. Verbex products are available over the web or can be shipped. Microphones available from Verbex. * Demo: A "Freeware" demo is available from the Verbex WWW site demo page. * Contact: Verbex Voice Systems 1090 King Georges Post Rd., Bldg 107, Edison NJ 08837, USA Ph: 1-800-ASK-VRBX, (908) 225-5225, Fax:(908) 225-7764 WWW: http://www.verbex.com/ Lotec Speech Recognition Package * Platform: Sun * Description: Public domain speech recognition software. Operates from input in Sun audio format (.au files) and outputs word hypotheses and time labelling data. The software includes programs to collect speech samples, a labeller, a "featurizer" which parameterises speech files, a word spotter and the recogniser. The software can real time recognition on a Sparc 10 for small vocabularies. * Requirements: Sun SPARC audio input and a "decent" microphone Sun multimedia demo software (in /usr/demo/SOUND) and X. * Availability: By anonymous ftp ftp://ftp.sanpo.t.u-tokyo.ac.jp/pub/nigel/lotec/lotec.tar.Z * Contact: Nigel Ward: _nigel@sanpo.t.u-tokyo.ac.jp _ Macintosh Speech Recognition Manager * Platform: Macintosh * Description: supports developers who wish to add speech recognition to existing Macintosh applications. Provides speaker independent recognition and robustness to noise. Apple's Speech home page provides developer information and the complete speech recognition and synthesis synthesis SDKs. The recognition SDK includes samples code, control panels, interfaces, documentation and the recognizer. * Availability: under licensing conditions from the Macintosh Speech Developer's page http://www.speech.apple.com/speech/dev/dev.html. * Requirements: Power Macintosh with 16-bit sound, System 7.5, and a PlainTalk Microphone or equivalent * Cost: Free * See also: Macintosh Plaintalk and Speech Manager (Q5.5). * Note: Check out Kevin Lenzo's list of Macintosh Speech Applications. * Contact: Apple Computer, Inc. 1 Infinite Loop, Cupertino, CA 95014, USA WWW: http://www.speech.apple.com/ Email: PlainTalk@atg.apple.com Microsoft Speech Recognition Microsoft Dictation Research Demonstration * Platform: Windows 95 or Windows NT 4.0 * Description: A free demonstration of research technology that enables a computer to transcribe what you speak into Windows applications such as email and word-processors. Features of the demo software include: + 60,000 word vocabulary with the ability to add new words + High recognition accuracy + Works with any Windows 5application + "Dictation Pad" provides enhanced dictation features + "IntelliSense" converts spoken numbers and times automatically + Compatible with the Microsoft Speech API * Requirements: Windows 95 or Windows NT 4.0, Pentium 90 or better (RISC builds are available), 16 megabytes of RAM on Windows 95, Sound card with 16 kHz 16 bit input signals, High quality close-talk microphone, Speakers. * Availability: Free demo software is available at: http://www.research.microsoft.com/research/srg/install.htm * More information: http://www.research.microsoft.com/research/srg/ Microsoft Command and Control Engine * Platform: Windows 95 * Description: Provides command and control speech recognition using SAPI (the Microsoft Speech API) and "Whisper", Microsoft's speech recognition technology. Features include: + Speaker independent, continuous, sub-word modeling, context free grammars + Has its own letter-to-sound rules means it can recognize any words in a grammar. + North American English + PC microphone and telephone speech recognition with high performance + Word spotting option + Results objects containing top-N choices, segmentation, and confidence + Written to SAPI, the Microsoft Speech API. * Requirements: Windows 95 or Windows NT 4.0, Pentium 60 or better. (RISC builds are available), 1.5 megabyte working set, 16 kHz or 8 kHz input signals, 6 megabytes on disk, Requires Microsoft Speech SDK to use. * Availability: Free demo software is available at: http://www.research.microsoft.com/research/srg/install.htm * More information: http://www.research.microsoft.com/research/srg/ Myers' Hidden Markov Model software * Platform: Unix * Description: Hidden Markov model software for automatic speech recognition. C++ code that implements a basic left-right hidden Markov model and corresponding Baum-Welch (ML) training algorithm. It is meant as an example of the HMM algorithms described by L.Rabiner and others. The code was built in order to learn how HMM systems work and we are now offering it to the net so that others can learn how to use HMMs for speech recognition. Keep in mind that ease of understanding was our primary concern, not efficiency. The code can be used to build an experimental speech recognition systems using "train_hmm" and "test_hmm", and can be used in conjunction with written tutorials on HMMs to understand how they work. * Availability: By anonymous ftp from the comp.speech archive site. There are two files in the directory + ftp://svr-ftp.eng.cam.ac.uk/pub/comp.speech/recognition/ The files are + hmm.README + hmm-1.03.tar.gz * Contact: Richard Myers: rmyers@isx.edu NCC Dictate * Platform: Windows * Description: NCC Digital DictateTM is an add-on, enhanced interface for use with IBM's VoiceType(TM) Dictation for Windows and various Windows 3.1 applications (e.g. MS Word, WordPerfect). Digital DictateTM provides faster corrections and dictation rates and various other features. This version is not a stand alone product; it requires VoiceTypeTM Dictation to provide the speech recognition engine and the Windows application. Features include: + Direct dictation into Windows applications with access to all functions while dictating. + Versions for MS Word, WordPerfect, Ami Pro, and other Windows applications. + Speech enabled editing. + Capability to save speaker models and defer corrections. + Microphone "pause and restore" functions controlled with speech commands. + Add-on vocabularies for legal, medical, science and business. + SWITCH-ITTM foot pedal control or CardSwitchTM infrared wireless control available which switch between dictation and proofing/correction modes. * Requirements: IBM's VoiceTypeTM Dictation for Windows; a computer system meeting VoiceTypeTM Dictation for Windows requirements; VoiceTypeTM Dictation Adapter. * Availability: Through computer dealerships. * Price: $US295 * Contact: NCC Incorporated 5808 E. Turquoise, Scottsdale, AZ 85253 Ph: (602) 922-6236 Fax: (602) 596-9050 NICO Artificial Neural Network Toolkit * Platform: UNIX (ANSI C source code) * Description: The NICO Toolkit is an artificial neural network toolkit specifically designed and optimized for automatic speech recognition applications. Networks with both recurrent connections and time-delay windows are easily constructed. The network topology is flexible -- any number of layers is allowed and layers can be arbitrarily connected. Tools for extracting input-features from the speech signal are included as well as tools for computing target values from standard phonetic label-files. * Availability: Through the NICO homepage (http://www.speech.kth.se/NICO/index.html) or the download page. * Contact: Nikko Strom, nikko@speech.kth.se Nuance Speech Recognition System * Platform: UNIX-based workstations including Sun and SGI. * Description: The Nuance Recognizer features client-server architecture with multiple recognizers available on a single processing platform. Primarily developed for telephony-based applications, the system accepts speaker-independent, continuous speech and supports very large vocabularies. Included is a "template matching" natural language capability for identifying the meaning of speech. A toolkit is available for use in developing a wide variety of speech recognition applications. * Price and availability: Contact Nuance * Contact: Nuance Communications 333 Ravenswood Ave., Building 110, Menlo Park, CA 94025, USA Ph: +1-415-462-8200, Fax: +1-415-462-8201 WWW: http://www.nuancecom.com/ OKI VRP6679 - Voice Recognition Processor * Platform: Intergrated circuit. * Description: Speech recognition IC. 25 words max. Speaker independent recognition capability. Recognition rate quoted as 97% in a noisy environment (e.g. a car). * Misc: Alias MSM6679 * Misc 2: More information is provided in Jean-Pierre Lereboullet's document on Voice Recognition Processors. * Cost: Approx US$20. Demo board $876 * Availability: OKI Semiconductor and OKI Distributors Corporate Headquarters 785 North Mary Avenue, Sunnyvale, CA, 94086 2909 Tel: (408) 720 1900, Fax: (408) 720 1918 Phonetic Engine 500 (PE500) from Speech Systems, Inc. * Platform: Windows * Description: Speaker independent, 40,000 word vocabulary, continuous speech recognition for MS Windows. Grammars with high perplexity possible. Includes noise rejection. Uses proprietary DSP board. * Cost: Prices in US$ - quantity one. The PE500 SDK is $995.00 including board, microphone, and runtime software. Runtime only is $595.00. SpeechWizard(r) adds speech input to existing Windows applications, $295.00. Two-day training: $295.00 with purchase, $595.00 without. * Misc: The user defines the grammar of allowed utterances and must write software to invoke the board driver functions that control recognition. The user must also write software to collect/parse/interpret the ASCII text strings returned when recognition succeeds. * Misc 2: SSI now offers speech application development services. * Contact: Speech Systems, Inc. 2945 Center Green Court South Boulder, CO 80301-2275, USA Tel: 303.938.1110 Fax: 303.938.1874 http://www.speechsys.com Philips Speech Recognition (2 products) SpeechMagic: Dictation * Platform: Windows 3.1 and higher * Description: A continuous speech recognizer providing a 64,000 word vocabulary, speaker adaptation and multiple languages. SpeechMagic is currently available for English and German. SpeechMagic acts as a server application, processing speech input and providing text output. Uses an add-on ISA compatible recognition accelerator board. SpeechMagic provided a correction editor, editing and playback of recordings, and a vocabulary manager for entering new words, abbreviations, macros and special transcriptions (e.g. for foreign words). Windows DDE support and a native API are provided for integration. * Hardware Requirements: IBM compatible personal computer (486DX/ 66 MHz or higher), minimum 16 MB of RAM, hard disk capacity > 500 MB, and a Philips LFH 6210 Accelerator Board. * More Information: For more information visit the SpeechMagic WWW page or the Philips Speech home page. Speech Processing System 6000s (Europe only) * Description: Dictation of medical findings using continuous speech recognition. Designed for German speaking radiologists and encompasses the complete radiology vocabulary. The authors use dictation stations (PCs) which are fitted with microphones. The transcriptionists use editing stations (also PCs) which are additionally fitted with headphones and footswitches. The SP6000s has a single speech recognition unit serving all users, and it offers automatic data transfer as well as the advantages of digital dictation functions. For more information visit the Philips SP6000s WWW page. * More Information: For more information visit the Philips SP6000s WWW page or the Philips Speech home page. Dragon PowerSecretary * Platform: Apple * Description: Information moved to the page on Dragon Dictation products including Dragon PowerSecretary (Previously Articulate PowerSecretary.) ProNotes Voice Tools * Platform: Windows * Description: ProNotes Voice Tools are designed to bring the speech recognition capabilities of the IBM VoiceTypeTM Dictation System for Windows into any program without the need for the programmer to directly interface with the speech engine at the API level. There are five tools, as described below, which are all available in three forms: Visual Basic(TM) Custom Controls (known as VBXs), 16-bit OLE Custom Controls, and 32-bit OLE Custom Controls. The tools are intended for use by Windows(TM) developers working with Windows 3.1(TM), Windows for Workgroups 3.11(TM), Windows NT 3.51 Workstation(TM), and Windows 95(TM). The custom controls can be utilized with any application development environment which supports the use of such controls (e.g. Visual Basic and Visual C++). Playback and Record An object which allows developers to use the IBM Speech Engine to record and play back sound files. Can be used to add voice prompts and to allow end users to record and playback sound files. Voice Button An object having standard button properties and behavior, which can additionally be controlled by voice. The button can also be used as a label or a 3D panel. Dictation Window A text box that allows free dictation, voice macro utilization, and correction by voice. Each Dictation Window has access to global and context sensitive vocabularies for both command and dictation. There are three correction modes. Voice List Box Has standard list box properties and behavior, but can additionally be controlled by voice. A user can select items by pronouncing the entry's text or the entries can be numbered and selected accordingly. Voice Navigator Provides navigation by voice within an application developed with the Voice Tools, between voice-enabled objects described above, as well as some standard objects found within the application. * Requirements: Hardware: 80486/33 DX or higher, 60MB hard disk space for IBM VoiceType Dictation software, 10MB hard disk space for ProNotes Voice Tools, 3.5" floppy, VGA (or compatible), 16MB RAM, IBM VoiceType Dictation adapter, microphone, and speakers. Software: DOS version 6.0 or later, with SHARE.EXE running, Windows 3.1 or later, IBM VoiceType Dictation software, any programming environment or system compatible with Visual Basic or OLE Custom Controls. * Price: Unknown * Contact: Pronotes, Inc. 1546 Magee Avenue, Philadelphia, PA 19149, USA Ph: 800-70-NOTES or +1-215-533-8569, Fax: +1-215-533-1276 Email: proinfo@pronotes.com WWW: http://www.pronotes.com/ PureSpeech 2.0 Recognition Engine * Platform: Windows 3.1, Windows 95, Unix, Dialogic Antares DSP * Description: Speaker-independent, continuous speech, large active vocabulary speech recognition engine for American English, UK English, French, German and Spanish. Permits on-the-fly additions to the vocabulary using phonetic models and telephone or wideband microphone input. Flexible grammar, natural language processing, discourse models. Software only with a small RAM/CPU footprint. Can be used as a voice user interfaces (VUI's) for PC software applications. Can also be used for high-volume call center telephony, especially in banks, finance and other specialized applications. A toolkit for the Dialogic Antares is available. * Availability: PureSpeech is not available as a stand-alone product. It is available embedded in Windows-based software or as a toolkit. * Contact: PureSpeech, Inc 100 Cambridge Park Drive, Cambridge, MA 02140, USA Ph: (617) 441-0000 Fax: (617) 441-0001 Email: amy@speech.com WWW: http://www.speech.com/ recnet * Platform: UNIX * Description: Speech recognition for the speaker independent TIMIT and Resource Management tasks. It uses recurrent networks to estimate phone probabilities and Markov models to find the most probable sequence of phones or words. The system is a snapshot of evolving research code. There is no documentation other than published research papers. The components are: + A preprocessor which implements many standard and many non- standard front end processing techniques. + A recurrent net recogniser and parameter files + Two Markov model based recognisers, one for phone recognition and one for word recognition + A dynamic programming scoring package. The complete system performs competatively. * Cost: Free * Requirements: TIMIT and Resource Management databases * Contact: Tony Robinson: _ajr@eng.cam.ac.uk_ * Availability: by anonymous ftp ftp://svr-ftp.eng.cam.ac.uk/pub/comp.speech/recognition/r ecnet-1.3.tar.Z Sensory Inc. Integrated Circuits * Platform: Integrated circuits * Description: Sensory's low cost high quality Interactive Speech line of speech recognition IC's are designed for consumer telephony products, portable consumer electronics, and other consumer applications. Technologies available include speech recognition (speaker-independent and speaker-dependent), speaker verification, speech/music synthesis, digital record/playback, and general product control on one chip. Development tools and demonstration units are available. Detailed product information on the Interactive Speech chips is available from the Sensory Circuits WWW site. * Contact: Sensory, Inc. 521 E. Weddell Drive, Sunnyvale, CA 94089 Ph: +1-408-744-9000, Fax: +1-408-744-1299 Email: Sales@SensoryInc.com WWW: http://www.sensoryinc.com/ Simon Says (NeXT) * Platform: NeXT * Description: Provides the ability to link commands to spoken phrases. * Availability:By anonymous ftp. Simon Says demo ftp://ftp.informatik.uni-muenchen.de/pub/comp/platforms/next/Audio /audio-apps/SimonSaysDemo.1.5.1.N.b.tar.gz Readme file ftp://ftp.informatik.uni-muenchen.de/pub/comp/platforms/next/Audio /audio-apps/SimonSaysDemo.1.5.1.README * Contact: Metrosoft 710 13th Street, Suite 310 X, San Diego, California 92101 Ph: 619.488.9411 Fax: 619.488.3045 Email: info@metrosoft.com [NeXTmail welcome] smARTspeak from Advanced Recognition Technologies, Inc. * Platform: Windows, Windows 95, DOS, and General Magic It also works on the following Processors/Microcontollers: Intel's 80 x 86, Intel's 8031, 8051, Motorola's 68000, and Hitachi's SH1, SH3, SH8. * Description: smARTspeak is suited to voice command and control applications, such as voice dialing in cellular and desktop telephones, or voice command operation in computers and multimedia products. It uses a compact (10KB size on 16 bit machines), fast, user dependent recognition engine. smARTspeak can recognize any language in any accent. ART recently completed a Software Developer Kit (SDK) for smARTspeak, running under Windows 3.1 or higher which allows the voice recognition engine to be used within Windows Applications. More detailed information on smARTspeak and the SDK is available on the ART WWW pages. * Availability: Currently liscensed to other equipment manufacturers (OEMs), system integraters, software, and application developers, and value added resellers (VARs) who port are technology into their product. * Contact: Advanced Recognition Technologies, Inc. International Office: 43 Brodezky Street, POB 39918, 61398 Tel Aviv, lsrael Ph: 972-3-642-7242, Fax: 972-3-642-5887 Email: 100274.3223@Compuserve.com WWW: http://www.artcomp.com/ US Office: 9574 Topanga Canyon Blvd. Chatsworth, CA 91311, USA Ph: 818-678-3999, Fax: 8181-678-3994 WWW: http://www.artcomp.com/ Speech Commander - Verbex Voice Systems * Platform: Various: external hardware with serial port connection * Description: A hand-held (portable) device about the size of a paperback book which provides speaker-dependent continuous speech recognition. The active vocabulary is dependent on the model chosen and can vary from 300 to 10,000 active words. The device connects through a serial port, so it can be connected to a wide range of computers. It comes with a battery pack. * Contact: Verbex Voice Systems 1090 King Georges Post Rd., Bldg 107, Edison NJ 08837, USA Ph: (908) 225-5225, Fax: (908) 225-7764 Email: sales@listen.verbex.com WWW: http://www.verbex.com/ 'Speech Recognition Expert' Toolkit for Windows * Description: Provides an object-oriented development tool designed to rapidly build speech enabled applications without writting source code. Currently supports IBM's VoiceType Application Factory. Future versions to support other platforms. Includes BlackBox library and Custom Grammar Tools. * Requirements: Layout for Windows from Objects, Inc. * Price: $US349 + Shipping/Handling * Contact: Speech Technologies, Inc. P.O. Box 3905 Naperville, IL 60567-3905 CompuServe @102147,3521 Ph: (708)983-7634 Visual Voice from Stylus Innovation * Platform: Microsoft Windows * Description: Visual Voice is a toolkit for building Windows-based voice processing and telephony applications including interactive voice response (e.g. touch-tone banking), fax-on-demand, and voice mail. Visual Voice can be used to add voice recognition to your telephony applications. Voice Recognition (VR) Support for Visual Voice is exposed as a standard VBX control and provides one or more voice recognition "resources" to your application. Applications can dynamically assign resources across several voice lines. Voice recognition is either "discrete" or "continuous". Discrete recognition is slightly more accurate and requires the speaker to pause briefly between words. Continuous recognition provides a natural way to enter information by speaking without pauses. Three configurations are supported: Software-Only Solution The software only solution uses Telaccount's SpeechEasy technology for discrete recognition using your PC's CPU. A vocabulary is included with digits, basic command words and more. Hardware-Assisted Solution with Dialogic AEB boards Discrete voice recognition in over 25 languages using Dialogic D/41D voice boards and the Dialogic VR/40 board. Vocabularies are included with digits, basic command words, voice mail vocabulary and more. Hardware-Assisted Solution with Dialogic PEB boards. Use the VR control with any Dialogic PEB-based voice board, such as the D/12x or D/24x, to access voice recognition resources from your phone lines. This requires a Dialogic VRP board with either 1 to 4 VRM/40 modules (4 channel discrete voice recognition modules) and/or 1 to 4 VRM/2C modules (2 channel continuous voice recognition modules). You can have up to 4 modules on each VRP: 4 VRM/40s for 16 channels of discrete voice recognition; 4 VRM/2Cs for 8 channels of continuous recognition; or a combination. Over 25 languages supported. Includes vocabularies as described above. * Pricing: Unknown * Availability: From Stylus Innovations Inc. or from the distributors listed on the Stylus WWW pages. * Misc: More detailed technical information, slide show demonstration software is available on the Stylus home page. * Contact: Stylus Innovation Inc. One Kendall Square, Building 300, Cambridge, MA 02139 Ph: (617) 621 9545, Fax: (617) 621 7862 WWW: http://www.stylus.com/ Compuserve forum: GO STYLUS Email: info@stylus.com Voice Command Line Interface * Platform: Amiga * Description: VCLI will execute CLI commands, ARexx commands, or ARexx scripts by voice command through your audio digitizer. VCLI allows you to launch multiple applications or control any program with an ARexx capability entirely by spoken voice command. VCLI is fully multitasking and will run in the background, continuously listening for your voice commands even while other programs are running. Documentation is provided in AmigaGuide format. VCLI 6.0 runs under either Amiga DOS 2.0 or 3.0. * Requirements: Supports the DSS8, PerfectSound 3, Sound Master, Sound Magic, and Generic audio digitizers. * Availability: by ftp from wuarchive.wustl.edu in the file systems/amiga/incoming/audio/VCLI60.lha and from amiga.physik.unizh.ch as the file pub/aminet/util/misc/VCLI60.lha * Contact: Author's email is RHorne@cup.portal.com Voice Control Systems Continuous Speech Recognition * Description: Voice Control Systems (VCS) continuous speech recognition is a proprietary phonetic recognizer based on technology developed at VCS over the last 17 years. It is robust for applications such as the "hands-free" automotive environment or telephone networks, both wireless and wireline. VCS speech recognition is used by many developers and manufacturers in telecommunications. VCS technology is a software-based capability which VCS has currently developed for a limited number of processing environments. VCS offers "off-the-shelf" capabilities for the TI-C3X and C4X DSPs with other hardware platform support planned for the future. As a benchmark, today's VCS continuous technology requires about 1/2 of a 33Mhz TMS320C31. VCS continuous technology is available in cellular and wireline based libraries for continuous digit input in approximately 15 languages. VCS continuous recognition is a modified HMM decision strategy built upon the foundation of VCS phonetic "front end". * Availability: VCS continuous technology is available today in software form from VCS or implemented in hardware or speech systems from VCS distributors including Dialogic Corporation, Brite Voice, Intervoice, Periphonics, and Syntellect. * Cost: Software royalties are volume based and range from per unit costs of $500 per recognizer to less than $5 in large quantities. * See also: the VCS Phonetic Dictionary Recognizer and VCS Isolated Word Speech Recognition below, and the VCS 2030 & 2060 Voice Dialers. * Contact: Voice Control Systems, Inc. 14140 Midway Rd., Dallas, Tx. 75244, USA Ph: +1-214-386-0300, Fax: +1-214-386-5555 Email: sales@vcsi.com WWW: http://www.voicecontrol.com/ Voice Control Systems Phonetic Dictionary Recognizer * Description: This recognizer is based upon a HMM type recognition strategy coupled with the VCS "front end" (feature extraction software). The HMM modeling is based upon the basic phonetic building blocks in each language. In American English this is approximately 43 units. The recognition vocabulary is built up by combining these units into word models. By building the words in this way new recognition vocabularies may be constructed. The phonetic assembly can also be used for "word spotting" recognition libraries. * Platform: This VCS recognition software runs on the TI TMS320C30 DSP. Two recognizers can operate on a single 55mhz C30. Currently the software may be purchased as an Enhanced Technology from VCS to run on the Dialogic VR/160p speech recognizer board. The hardware is purchased from Dialogic, with the "Enhanced" software purchased from VCS. Up to four phonetic recognizers can run on a single 160; one per VRM2C (C30-33mhz DSP) daughtercard. * Note: This recognizer is in its late "beta" stage of development and is available for U.S. English vocabularies. Other languages are presently under development. * Price: VCS software is priced at $350 per recognizer for unit quantities with volume discounts available. * See also: VCS Continuous Recognition above, VCS Isolated Word Speech Recognition below, and the VCS 2030 & 2060 Voice Dialers. * Contact: Voice Control Systems, Inc. 14140 Midway Rd., Dallas, Tx. 75244, USA Ph: +1-214-386-0300, Fax: +1-214-386-5555 Email: sales@vcsi.com WWW: http://www.voicecontrol.com/ Voice Control Systems Isolated Word Speech Recognition * Description: Voice Control Systems (VCS) isolated word recognition using VCS phonetic recognizer technology. It is robust in demanding environments such as the "hands-free" automotive environment, telephone networks, wireless or wireline. Capabilities include speaker-independent, speaker-dependent and speaker-adaptive recognition. Libraries are available for 45+ languages and custom vocabulary development services are available. The technology is suited for many applications including: + Desktop computing: such as keyboard accelerators orinteractive multimedia. + Network telephony: such as automating operator functions or voice dialing. + Computer telephony: such as remote access to a personal computers. + Automotive accessory control: such as voice activated cellular phones or other automotive accessories. + Consumer electronics: such as voice controllers for video games or VCRs and televisions. * Platform: Include Intel-X86, TI-C5X, C3X, C4X and C2X, OKI 6679, and NEC-V20 and V30, and can operate on 16 bit microcontrollers. As a benchmark, 8 recognizers can run on an Intel 486-33 DX. * Availability: The technology is available under software licenses direct from VCS or by purchasing hardware from an OEM. VCS OEMs include: Dialogic, Oki Semiconductor, Intervoice, Periphonics, etc. * Cost: VCS isolated word recognition software is available under a volume pricing license agreement. Small quantity royalties are in the $500.00 per recognizer range while large (millions) quantity royalties are less than $1.00 per recognizer. * See also: VCS Continuous Speech Recognition and VCS Phonetic Dictionary Recognizer above, and the VCS 2030 & 2060 Voice Dialers. * Contact: Voice Control Systems, Inc. 14140 Midway Rd., Dallas, Tx. 75244, USA Ph: +1-214-386-0300, Fax: +1-214-386-5555 Email: sales@vcsi.com WWW: http://www.voicecontrol.com/ Visus SpeechKit * Platform: NeXT * Description: SpeechKit is based on SPHINX, a speaker-independent, 1000 word or so, continuous speech recognition system which allows you to incorporate speech recognition into your applications. You can design your vocabulary and grammars. * Contact: Visus - no address or phone provided. A possible contact is Robert Brennan at Carnegie Mellon University. email: Robert_Brennan@cmu.edu VCS 2060 Voice Dialer VCS 2030 Voice Dialer * Platform: Stand-alone hardware, TMS320C5X based with VCS phonetic speech recognition and CELP speech compression. * Description: The VCS 2060 is a telephone dialing system which recognizes 50 names - and speed dials the associated telephone number. The VCS 2030 has 20 memories. Users use speaker-independent recognition to select the "call", "program", or "list" menu, then place a call, enroll a new memory, or listen to playback of entries in the phonebook. Enrollment is simple and includes a "name tag" enrollment pass so that when one selects an entry to call, the selection is confirmed by repeating the memory's associated name tag, e.g. "calling Pete". The system uses both speaker-independent and speaker-dependent technology from Voice Control Systems, Inc. * Installation: The VCS 2060 can be installed in series (RJ-11) with one phone for single phone operation or installed in parallel (RJ-31) to provide voice dialing from every phone in a house. * Cost: Standard retail prices: + VCS 2030 Voice Dialer - $269.00 + VCS 2060 Voice Dialer - $299.00 * Availability: From catalogs or direct from Voice Control Systems. Voice Control Systems 14140 Midway Rd., Dallas, Tx. 75225, USA Ph: 800-VCS-7525, Fax: +1-214-386-5555 Email: sales@vcsi.com WWW: http://www.voicecontrol.com/ Voice-Trek 2.0 * Platform: Unknown. * Description: VoiceTrek is primarily used by the United States Postal Service to sort mail. Tardis Technology Inc. was created to develop and market applications that utilize speech recognition. They do consulting work as well as turnkey systems. * Contact: Tardis Technology Inc., Voice Recognition Div. 6444 E. Spring St., #286, Long Beach, CA 90815-1500, USA Phone: +1-310-497-0077, Fax: +1-310-497-0080 VoiceAssist for Windows from Creative Labs, Inc. * Platform: Windows * Description: Seeking a description. * Availability: VoiceAssist preview software is available from the Creative Labs VoiceAssist home page. * Contact: Creative Labs, Inc. Ph: 1-800-998-1000 (Sales) Ph: 1-800-998-5227 (Product info and dealer referrals) CompuServe: support forum: GO BLASTER WWW: http://www.creaf.com/ VoiceServer for Windows * Platform: Windows * Description: Speaker dependent, each with an independent directory. Isolated words. Up to 1000 words/user, 300 words/window. 1 word occupies 2Kb on hard disk. Can be used to control Windows applications by issuing voice commands instead of menu selection. * Rough Cost: 292 Pounds(UK) * Requirements: None * Misc: Price includes a half-sized AT voice card (including a DSP), software, documentation & a microphone (attachable to keyboard or speaker). A light-weight high-spec headset is an optional extra. * Contact: Mark Redwood Applied Voice Technologies 26 Danbury Street, Islington, London, UK, N1 8JU Ph: + 44 71 454 1224 : Fax: + 44 71 454 1225 Voicetek Corp. * Platform: Unknown. * Description:Voicetek Corporation provides voice processing solutions, training and consulting services and an object-oriented, graphical Generations Platform for development of integrated computer telephony systems. * Contact: Voicetek Corporation 19 Alpha Road, Chelmsford, MA 01824, USA Ph: +1-508-250-9393, Fax: +1-508-250-9378 WWW: http://www.voicetek.com/ Votan VPC2100 Voice Card and VSP 1010 Speech Processor * Platform: DOS * VPC2100 Voice Card: a hardware and software system based on the TMS320C10. providing continuous speech recognition. The VPC2100 consists of a circuit board, microphone, speaker, software, and documentation. It is designed to add voice I/O and telephone management capabilities to the PC/AT and compatibles. Features: + Voice store-and-forward at 4- to 16.4-Kb/s speed + Speaker-independent speech recognition (0-9, YES, NO) + Continuous speaker-dependent speech recognition + Telephone interface, pulse or tone dialing, call progress, and DTMF + Software for development, voice mail, telephone management, and VoiceKey + High-level applications-generator software * Votan VSP 1010 speech-processor board: can service a single voice channel, providing recognition, voice output, and telephone interfacing. Digital signal processing is performed by a TMS320 integrated circuit. * Costs: Unknown * WWW: http://www.ti.com/sc/docs/dsps/develop/3rdparty/vot.htm * Contact: Votan Division, MOSCOM Corporation 6920 Koll Center Parkway, Suite 214, Pleasanton, CA 94566, USA Ph: +1-510-426-5600, Fax: +1-510-426-6767 Voice Processing Corporation Speech Recognition Product Line * Platform: Unknown. * Description: Voice Processing Corporation (VPC) supplies automated speech recognition systems. VPC's products are used in the telecommunications, cellular and personal computer markets to enable computers to understand human speech. The company's VPro product line is sold to original equipment manufacturers (OEMs), value added resellers (VARs), system integrators and application developers. VPC's speech recognition systems are currently used in applications such as voice mail, voice activated dialing, interactive voice response, and command and control of personal computers. The following are descriptions of the Voice Processing Corporation's VPro Product Line: VProContinuous, VPro/XD, VPro/RT, VProCel, VProSpeller, VProPRL, VPro hardware platforms, and the application Osprey. More information is available on these products at the VPC WWW site: http://www.vpro.com/ * VProContinuous(TM) is a speaker-independent, continuous digit recognizer. It recognizes digit strings spoken in a continuous manner, by any caller, without unnatural beeps or pauses. VProContinuous uses out-of-vocabulary rejection and word spotting technologies to reject extraneous words and phrases often spoken by callers. The VProContinuous vocabulary consists of the words "zero" through "nine," "yes," "no," and "oh." The product is language-independent. American English, Australian English, Brazilian Portuguese, Canadian French, Castilian Spanish, French, German, Italian, Mexican Spanish, Portuguese, Swiss German and U.K. English versions are available. * VPro/XD(TM) is a discrete or multiword speech recognizer for extra-demanding applications and/or vocabularies. This robust discrete product recognizes isolated discrete utterances (words or very short phrases). VPro/XD utilizes proprietary out-of-vocabulary rejection and word-spotting technologies. VPro/XD is speaker-independent and includes Talkover capability allowing speech-interrupt over prompts. Pre-trained vocabulary libraries are available in American English, Australian English, Brazilian Portuguese, Canadian French, Castilian Spanish, Central American Spanish, German, Italian, Mandarin Chinese, Mexican Spanish, Portuguese, Swiss German and UK English. Pre-trained vocabularies consisting of voice mail words, voice dialing words, call control words, banking, and emergency words are available in American English (both cellular and land-line). * VPro/RT(TM) is a discrete speech recognizer for rapid training of vocabularies in the field. This robust discrete product recognizes isolated discrete utterances. Application designers and end-users define the vocabulary of their choice and train the system in real-time either prior to system start-up, or adapting on-the-fly while the system is running live. Vocabularies can be subset, and applications involving thousands of words can be developed quickly. VPro/RT, which also supports Talkover, is suited to speaker-dependent recognition tasks, such as the personal directory of names in a voice-activated dailing application. VPro/RT is also good for applications that require speaker-independent vocabularies to be developed quickly in the field or those that require many vocabularies. VPro/RT can also be used as a tool for quick prototyping of applications. * VProCel consists of speaker-independent VProContinuous, VPro/XD and speaker-dependent VPro/RT specifically tuned for the cellular environment. The speaker-dependent discrete feature of VProCel allows for a user-defined 20-word personal directory, with a one-pass enrollment whereby users need only speak their chosen commands once. In addition, cellular-ready VPro/XD vocabularies consisting of voice-activated dialing command words are also available. VProCel is suited to voice-activated dialing applications using either digit strings or a listing of words in a personal directory. * VProSpeller is a recognizer that can determine which name or word is being spelled by a caller. Users may spell a string of letters (up to 32 letters) in an uninterrupted manner (without prompts or beeps between each letter). VProSpeller can recognize confusable letters by conducting an automated search of a database of words maintained by the application for the best candidates to match. * VProPRL Designed for customers who wish to enable VPC speech recognition technologies on platforms other than those supported by VPro hardware, the VProPRL is a portable recognizer library of VProContinuous, VPro/XD and VPro/RT, which can be embedded into a wide variety of hardware platforms. It consists of a library of object modules which can be linked with a user application or task. * VPro Hardware Platforms: VPro-42, VPro-84, VPro-88 : The VPro platforms are ISA compliant PC/AT boards. Each supports four to eight Virtual Speech Processors (VSPs). Each VSP, depending on load factors, can handle multiple telephone lines. Application and host computers communicate with each of the VSPs as separate autonomous units. VPro platforms use Texas Instruments TMS320C31 microprocessors which provide up to 133 MFLOPS of compute power. The platforms can have up to 8 megabytes of memory shared among all processors. In addition, each processor has 512K bytes of local memory. Both the PEB and MVIP PCM audio buses are supported by all VPro platforms. * Osprey is a call management software application that performs the kinds of telephone related activities typically done by a personal assistant, such as answering the phone, screening callers, routing calls, and taking and delivering messages. It is an automated phone attendant. * Price and availability: Contact Voice Processing Corporation * Contact: Kelli V. Smith Voice Processing Corporation 1 Main Street, Cambridge, MA, 02142 USA Ph: (617)494-0100 Fax: (617)494-4970 e-mail: KSmith@vpro.com WWW: http://www.vpro.com/ Whisper See the new page for Microsoft speech recognition software. * Platform: Windows 95 and Windows NT 4.0 * Description: Command and control recognition. WildCard Speech Products * Platform: Windows 3.1 and Windows 95 * OfficeTalk for Windows: provides voice commands for dictation, navigation, command and control, and formatting for business uses of computers. Provides user voice access to a wide variety of software applications in office suites from Microsoft, Novell/WordPerfect, and Lotus. More information on the WildCard OfficeTalk page. * LawTalk for Windows: adds features and interfaces that meet the specific needs of legal users. More information on the WildCard LawTalk page. * VoiceCompanion for the Internet: Surf the net using voice commands. Controls browsers like Netscape and Microsoft Explorer. More information on the VoiceCompanion web page. * VoiceCompanion - RemoteAccess: Over the telephone remote access to your desktop PC, for voicemail, FAX forwarding and address book information. More information on the VoiceCompanion web page. * Availability: WildCard Technologies Inc. 180 West Beaver Creek Road, Richmond Hill, Ontario, Canada L4B 1B4 Phone: (905) 731-6444, Fax: (905) 731-7017 Email: sales@wildcardtech.com WWW: http://www.wildcardtech.com/ ___________________________________________________________________________ Q6.6: Speaker Recognition (Verification and Identification) * Introduction * In the FAQ * On the WWW Introduction Speaker recognition is the process of automatically recognizing who is speaking on the basis of individual information included in speech signals. It can be divided into Speaker Identification and Speaker Verification. Speaker identification determines which registered speaker provides a given utterance from amongst a set of known speakers. Speaker verification accepts or rejects the identity claim of a speaker - is the speaker the person they say they are? Speaker recognition technology makes it possible to a the speaker's voice to control access to restricted services, for example, phone access to banking, database services, shopping or voice mail, and access to secure equipment. Both technologies require users to "enroll" in the system, that is, to give examples of their speech to a system so that it can characterise (or learn) their voice patterns. In the FAQ: * ImagineNation: Voice Activated UnLock Technology * Jialong He's Speaker Recognition (Identification) Tool * Keyware Biometric Security Products * SpeakerKey Voice Verifier from ITT * SpeakEZ Voice Print Speaker Verification * Voice Control Systems: Speaker Verification Technology On the WWW Survey of the State of the Art in Human Language Technology Report edited by Ronald A. Cole et. al. with a section on Speaker Recognition. http://www.cse.ogi.edu/CSLU/HLTsurvey/ch1node47.html Speaker Identification And Verification: LIMSI Report A technical description. http://www.limsi.fr/Recherche/TLP/reco/2pg95-sv/2pg95-sv.html Long Index of References on Automatic Speaker Verification A list of more than 350 papers on speaker verification in text or BibTeX format. Provided by G.Matas. http://sig.enst.fr/~chollet/ForMehdi/SpRecV1.l_ind.html CAVE: Caller Verification in Banking and Telecommunications European consortium developing speaker recognition technologies. http://www.ptt-telecom.nl/cave/ Hangai Lab demonstrations of speaker verification and speaker identification. Do it yourself demonstrations: http://miya8f05.ee.kagu.sut.ac.jp/study/speech/speech1.html http://miya8f05.ee.kagu.sut.ac.jp/study/speech/speech2.html Voice Activated UnLock Technology (VAULT): ImagineNation * Description: Password-based voice verification technology using a card to store voice-print data. Introductory information and the VAULT FAQ are provided on the ImagineNation WWW pages. * Contact: Imagine PO Box 212, Swansea, MA 02777, USA Ph: +1-508-678-9563 Fax: 508-678-1470 Email: feedback@ImagineNation.com WWW: http://www.ImagineNation.com/ Jialong He's Speaker Recognition (Identification) Tool * Platform: SUN SPARC (SunOS), PC (MSDOS) * Description: This package contains a set of speaker recognition research utilities, including Gaussian mixture models, VQ codebook designing program and MLP network. They can also be used as general classifiers. The utilities are divided into the following categories: + Feature extraction and dimensional reduction cepstrum -- extract features from speech sigals (LPCC, MFCC, etc.). search -- select effective features (SFS, SBS method). randline -- randomize the a sequence, auxiliary utility. bin2asc -- binary to ASCII, auxiliary utility. + MLP network mlptrain -- MLP network training program. mlptest -- MLP network test program. + VQ codebook training and test programs lbglvq -- VQ codebook training program. nearest -- VQ codebook test program. + Gaussian mixture model (GMM) gmmtrain -- GMM training program. gmmtest -- GMM test program. Note: this is a research tool not a true speaker recognition system. * Availability: By anonymous ftp: MSDOS Version UK: ftp://svr-ftp.eng.cam.ac.uk/pub/comp.speech/recognition/s pkrtool.zip Germany: ftp://ftp.informatik.uni-ulm.de/pub/NI/jialong/spkrtool.z ip Sun SPARC version, compiled with GNU C UK: ftp://svr-ftp.eng.cam.ac.uk/pub/comp.speech/recognition/s pkr_sun_v1.tar.gz Germany: ftp://ftp.informatik.uni-ulm.de/pub/NI/jialong/speaker_su n_v1.tar.gz * See also: Jialong He's Speech Recognition Research Tool * Contact: Jialong He email: jialong@neuro.informatik.uni-ulm.de Keyware Biometric Security Products * Description: VoiceGuardian and S2 Security Server provide authentication and access control technologies. An online demo of Voice Guardian is available. * Contact: Keyware Technologies _USA_ Keyware Technologies 500 West Cummings Park, Suite 3600, Woburn, MA 01801, USA Ph: (617) 933 1311, Fax: (617) 933 1554 _Belgium_ Keyware Technologies Excelsiorlaan 28-30, 1930 Zaventem, Belgium Ph: 32 2 721 4574, Fax: 32 2 721 5015 _Email:_ sales@keywareusa.com _WWW:_ http://www.keywareusa.com/ SpeakerKey Voice Verifier from ITT * Platform: Windows/Pentium and Solaris/SPARC * Description: SpeakerKey provides over-the-phone voice verification. It is configurable for use in a wide range of applications. SpeakerKey provides a Speaker Verification API (SVAPI). SpeakerKey uses two technologies: (1) speaker-independent digit recognition using hidden Markov models, (2) speaker verification using "Nearest Neighbour Matching with Likelihood Ratio Scoring and cohort speakers." Dr. Joe Campbell maintains a SpeakerKey FAQ on the WWW. It provides a more detailed description of SpeakerKey and discusses several speaker verification issues: http://www.vitro.bloomington.in.us:8080/~BC/REPORTS/SpeakerKeyFAQ. html * Requirements: Minimum 60 MHz Pentium (with sound card) or SPARCstation 5, plus phone line interface devices. * Price: Evaluation kits available from $75. Developer's kits are $1500. Run-time licenses are priced from $600 to $10,000 depending upon the number of user and/or verifications per hour. Application customization is available. * Contact: ITT Industries Fort Wayne, IN, USA Ph: +1-219-487-6321, Fax: +1-219-487-6126 Email: speakerkey@itt.com SpeakEZ Voice Print Speaker Verification * Description: Designed to prevent cell phone theft and cloning fraud by comparing the cellular caller's statement of a pass-phrase to a stored digital "voice print" of the authorized subscriber. If the caller's voice patterns do not match the stored voice print, service will be denied or the caller will be referred to operator assistance for further validation processing. Features include: + Customer selected password. + Vocabulary and language independent. + No special hardware required by customer. + Multiple delivery options. * Contact: T-NETIX, Inc. 6675 South Kenton Street Englewood, CO 80111 USA Phone: (800) 352-8628, (303) 790-9111, Fax: (303) 790-9540 WWW: http://www.t-netix.com/ Voice Control Systems: Speaker Verification Technology * Description: SpeechPrint ID technology provides language independent speaker verification. Features: + Multiple speech input formats + Operates over various microphones or the telephone network + Can can be used in conjunction with discrete and continuous recognition + Robust against background noise and spurious telephone channel noise For more information on features, hardware and software requirements, pricing and availability, contact Voice Control Systems, Inc. or visit their the VCS WWW site or the SpeechPrint ID WWW page. * See also: VCS speech recognition products in Q6.5. * Contact: Voice Control Systems, Inc. 14140 Midway Rd., Dallas, Tx. 75244, USA Ph: +1-214-386-0300, Fax: +1-214-386-5555 Email: sales@vcsi.com WWW: http://www.voicecontrol.com/ ___________________________________________________________________________ Q6.7: Integrated Speech Products This section lists those products which integrate different speech technologies into a single user package. For example, speech recognition and speech synthesis can be combined to provide a dialog management system. Strictly speaking, this doesn't really belong under in Section 6 (Speech Recognition) but since these products all include speech recognition, it seems a reasonable place to put it for now! In the FAQ... * SpeechWorksfrom Applied Language Technologies, Inc. * Nortel Speech Technology Products SpeechWorksfrom Applied Language Technologies, Inc. * Description: SpeechWorks and companion products provide advanced speech recognition technology for the telephony market. SpeechWorks can be used by developers to "speech-enable" call center, messaging, enhanced services, and other types of applications. The three major system modules - SpeechWorks, DialogModules and SpeechBuilder - are described below. More detailed information is available from the Applied Language Technologies home page. ALTech develops and markets speech understanding software which provides large vocabulary, speaker-independent, phonetic speech recognition. ALTech's software contains a comprehensive set of features for speech-enabling telephone-based transactions and services. SpeechWorks is based on technology licensed from the Spoken Language Systems Group at the Massachusetts Institute of Technology. * SpeechWorks: provides the core speech recognition capabilities. Features include: + Phonetic segment-based, speaker-independent, large vocabulary, continuous speech recognition + Real-time vocabulary generation directly from text + Database integration + "Barge-in" capability + Adaptive channel normalization + "n-best" output and associated confidence scores + Support for multiple languages + Software-only or DSP-based implementations + Support for multiple platforms and operating systems (e.g., SCO UNIX, WindowsNT, etc.) * DialogModules: manage the "conversation" between the system and the caller within an application. They provide high-level application building blocks which enable developers to quickly and easily add speech interfaces to computer telephony applications. Each DialogModule accomplishes a particular task within an application, ranging from "simple" tasks such as capturing a yes/no response or a phone number, to more complex tasks such as capturing credit card information or name and address information. DialogModules provide "out-of-the-box" functionality. They contain pre-built grammars, user-interface design, internal call flow and error recovery routines, parameters for customization and a set of C++ class libraries and C APIs. * SpeechBuilder: provides tools for customizing the DialogModules and for developing and maintaining applications. A GUI-based Vocabulary Editor provides the ability to generate and maintain vocabulary or word lists. Pronunciations can be generated automatically using the built-in dictionary or can be automatically generated using a set of text-to-phoneme rules. * Product Bundles: are available which combine SpeechWorks and multiple DialogModules into application templates for a set of generic application categories. + SpeechForms SpeechForms provides an interactive method for entering data over the phone, such as ordering products, filling out surveys and completing registration forms. Typical applications include: order entry, reservations, catalog and literature requests, catalog shopping, subscriptions, change of service, claims, credit card activation, home banking, stock transactions, and warranty reservations. + SpeechQuery SpeechQuery is used to deliver information in response to voice requests over the phone, such as airline information, product delivery status and retirement benefit information. Typical applications include: order status, product information, account balance, flight status, movie listings, job listings, stock quotes, guide services,classified ads, claims status, dealer locator services, and technical support. + SpeechAgent SpeechAgent provides a set of modules for automating telephone-based voice messaging applications, such as integrated messaging, single-number services and voice-dialing. Typical applications include: voice messaging, voice dialing, auto attendant, address book access, email access, and scheduling. * Platform: Platforms and Operating systems: ALTech's software can be deployed on industry-standard hardware platforms and operating systems including: Sun SPARC-based systems running SunOS or Solaris, IBM RS/6000s running AIX, HP systems running HP-UX, and 486/Pentium-based PCs and servers running Windows, WindowsNT, SCO UNIX, or Solaris. ALTech's systems are designed to run all or some of the software on a digital signal processor. * Availability: contact ALTech for licensing information. * Contact: Applied Language Technologies, Inc. 215 First Street, Cambridge, MA 02142 Ph: 617-225-0012, Fax: 617-225-0322 Email: to Alisa Moyer: moyer@altech.com WWW: http://www.altech.com/ Nortel Speech Technology Products * Nortel's AudioGram Delivery Service (ADS): When a busy or no answer condition is encountered, an intercept message offers ADS, which provides a service to the calling party by taking a message automatically. ADS records the caller's message and attempts delivery repeatedly if needed until the message is delivered. ADS is comprised of four independent services: 0+, 1+ and Local, Intentional, and Millenium AudioGram. ADS services utilize Nortel's Flexible Voice Recognition (FVR) voice-processing capabilities. ADS features include: + Cost-saving common service platform (NAV) + Builds upon existing network investment in toll infrastructure capabilities of AABS (Automated Alternate Billing Service) + Leverages the capabilities of existing TOPS (Traffic Operator Position System) attendants. More information: is available on the Nortel Multimedia Network Applications WWW page for AudioGram Delivery Service. * Nortel's Voice-Activated Auto Attendant (VAAA): Replaces touch tone menu with easy-to-use voice interface. Geared to businesses and corporations to provide more effective management of incoming customer calls. Residing on the Network Applications Vehicle (NAV) platform, VAAA uses Flexible Vocabulary Recognition (speaker-independent) technology to recognize spoken words, and directs calls accordingly. Other features include: + Cost-saving common service platform (NAV) + Serves DTMF and rotary dial callers. + Handles incoming calls for all corporate users (Centrex, PBX, or key systems) More information: is available on the Nortel Multimedia Network Applications WWW page for Voice-Activated Auto Attendant. * Nortel's Voice-Activated Dialing (VAD): Phoneme-based speech dialing capabilities provided through speaker-trained and speaker-independent technologies. Residing on the Network Applications Vehicle (NAV) platform, VAD enables subscribers to dial using speech, as well as to create and customize personal telephone directories. Other features include: + Cost-saving common service platform (NAV) + Speech playback and Text-to-speech synthesis + Dual Language capability (optional) + Speech Recording + Canadian French speechware (optional, prompts and FVR) + Spanish speechware (optional, prompts and FVR) + 75-name VAD directory size + Word-spotting + DTMF tone detection + Directory sharing + Scalable service deployment + Talk-through More information: is available on the Nortel Multimedia Network Applications WWW page for Voice-Activated Dialing. * Nortel's Voice-Activated Premier Dialing (VAPD): Enables businesses to take advantage of the public network directories to stimulate customer calls. Residing on the Network Applications Vehicle (NAV) platform, VAPD uses Flexible Vocabulary Recognition (speaker-independent) technology to recognize business names, and routes calls to the appropriate business entity. VAPD promotes cost savings by utilizing a common service platform, the Network Applications Vehicle (NAV). It services DTMF callers as well as rotary dialers, and handles incoming calls for all corporate users: Centrex, PBX, and key systems. More information: is available on the Nortel Multimedia Network Applications WWW page for Voice-Activated Premier Dialing. * Platform: This speech-based service operates on the Network Applications Vehicle (NAV) platform. NAV is a multi-application, digital signal processing platform supporting both speech- and display-based applications. The NAV platform provides the speech recognition capabilities and application logic used by NAV features an open, modular hardware architecture and flexible software design. Other features include: + Scalable hardware - from 24 to over 2000 ports per NAV node; 1 to 24 independent application shelves per node + Powerful speech processing - speaker-independent and speaker-trained speech processing support + Reliability - N+1, N+M, and 2N redundancy + Central Management - access via graphical user interface to remote connections * See Also: Nortel Feature Planning Guide, reference number 50004.11; NAV Applications and Planning Guide, reference number 50118.16. Nortel's Multimedia web pages: http://www.nortel.com/entprods/multimedia/ * Contact: NORTEL Multimedia Communications Systems Division Multimedia Network Applications 1000 Park Forty Plaza Durham, NC 27713 USA Ph: 1-800-4NORTEL WWW: http://www.nortel.com/entprods/multimedia/ ___________________________________________________________________________ Copyright (c) 1993-6 by Andrew Hunt, all rights reserved. This FAQ may be posted to any USENET newsgroup, on-line service, or BBS as long as it is posted in its entirety and includes this copyright statement. This FAQ may not be distributed for financial gain. This FAQ may not be included in any collections or compilations without express permission from the author. --- Andrew Hunt Speech Applications Group Sun Microsystems Laboratories Ph: (508) 442-2681 2 Elizabeth Drive, MS UCHL03-207 Fax: (508) 250-5067 Chelmsford, MA 01824, USA Email: andrew.hunt@east.sun.com