Paul Taylor

I have just completed a two year sabbatical at the Machine Intelligence lab, Engineering Dept, University of Cambridge.

Please take a look at a draft of my new book Text-to-Speech Synthesis

Examples of various speech synthesis systems

Research Areas

My primary area of research is speech synthesis. I have worked in most aspects of this, but now focus on unit selection.
I have been involved in the development of four Text-to-speech systems:

rVoice 2001 -2004, high quality commercial TTS system.
Festival, 1996- Open source synthesis system and toolkit (co-written with Alan Black and Richard Caley)
Chatr , 1993- System developed at ATR (I co-wrote the initial version with Alan Black)
Osprey , 1989-1991 Original diphone TTS system developed at CSTR.

Intonation Modelling for synthesis and recognition. Key work includes the "tilt" model of intonation
Diaglogue language modelling - using n-grams as a high level model of dialogue flow
Articulatory and Phonetic features for ASR front end

Brief CV:

2004- Visitor, University of Cambridge, sponsored by the Royal Society Industral Fellow programme.
2000-2004 Chief Technical Officer, Rhetorical systems. I was a co-founder and head of engineering for Rhetorical. Rhetorical specialised in high quality text-to-speech systems, and was acquired by Scansoft in Novemember 2004.
1999-2001 Director, Centre for Speech Technology Research, University of Edinburgh
1998-2001 Lecturer, University of Edinburgh
1989-1998 Research associate/fellow, University of Edinburgh
In addition, I also have extended periods at ATR, Japan (1993), Johns Hopkins (1997) and KTH, Sweden (1998)

Publications

This is a reasonably complete list. (Please note that due to working in the commercial realm, I was inactive in publications in the perdiod 2000-2004.)

Journal Publications

P. Taylor. Analysis and synthesis of intonation using the tilt model. Journal of the Acoustical Society of America, 107(3):1697-1714, 2000. .pdf

P. Taylor, A W Black, R Caley. "Hetrogeneous Relation Graphs as a mechanism for representing linguistic information", Speech Communication 33 pp 153-174, 2001

K. Richmond, S. King, and P. Taylor. Modelling the uncertainty in recovering articulation from acoustics. Computer Speech and Language, 17:153-172, 2003.
[ bib | Abstract ]

P A Taylor. Concept-to-speech by phonological structure matching. Philosophical Transactions of the Royal Society, Series A , 2000.
[ bib | .ps | .pdf ]

Simon King and Paul Taylor. Detection of phonological features in continuous speech using neural networks. Computer Speech and Language , 14(4):333-353, 2000.
[ bib | .ps | .pdf | Abstract ]

Paul A. Taylor, S. King, S. D. Isard, and H. Wright. Intonation and dialogue context as constraints for speech recognition. Language and Speech, 41(3):493-512, 1998.
[ bib | .ps | .pdf ]

Andreas Stolcke, N. Coccaro, R. Bates, P. Taylor, C. Van Ess-Dykema, K. Ries, Elizabeth Shriberg, D. Jurafsky, R.Martin, and M. Meteer. Dialog act modeling for automatic tagging and recognition of conversational speech. Computational Linguistics , 26(3), 2000.
[ bib | .ps | .pdf ]

Paul Taylor and Alan Black. Assigning phrase breaks from part of speech sequences. Computer Speech and Language, 12:99-117, 1998.
[ bib | .ps | .pdf ]

Elizabeth Shriberg, R. Bates, P. Taylor, A. Stolcke, K. Ries, D. Jurafsky, N. Coccaro, R. Martin, M. Meteer, and C. Van Ess-Dykema. Can prosody aid the automatic classification of dialog acts in conversational speech? Language and Speech, 41(3-4), 1998.
[ bib | .ps | .pdf ]

Paul A. Taylor and Amy Isard. SSML: A speech synthesis markup language. Speech Communication, (21):123-133, 1997.
[ bib | .ps | .pdf ]

Paul A. Taylor. The rise/fall/connection model of intonation. Speech Communication, 15:169-186, 1995.
[ bib | .ps | .pdf ]

Conference Publications

P. Taylor. Grapheme-to-Phoneme conversion using Hidden Markov models In Proc. Interspeech 2005
pdf

J. Vepa, S. King, and P. Taylor. New objective distance measures for spectral discontinuities in concatenative speech synthesis. In Proc. IEEE 2002 workshop on speech synthesis, Santa Monica, USA, September 2002.
[ bib | .pdf | ]

J. Vepa, S. King, and P. Taylor. Objective distance measures for spectral discontinuities in concatenative speech synthesis. In Proc. ICSLP, Denver, USA, September 2002.
[ bib | .pdf | ]

J. Frankel, K. Richmond, S. King, and P. Taylor. An automatic speech recognition system using neural networks and linear dynamic models to recover and model articulatory traces. In Proc. ICSLP , 2000.
[ .pdf ]

Edmilson Morais, Paul Taylor, and Fabio Violaro. Concatenative text-to-speech synthesis based on prototype waveform interpolation (a time frequency approach). In Proc. ICSLP 2000, Beijing, China, 2000.
[ bib | .ps | .pdf ]

S. King, P. Taylor, J. Frankel, and K. Richmond. Speech recognition via phonetically-featured syllables. In PHONUS , volume 5, pages 15-34, Institute of Phonetics, University of the Saarland, 2000.
[ bib | .ps | .pdf | Abstract ]

Janet Hitzeman, Alan W. Black, Paul Taylor, Chris Mellish, and Jon Oberlander. An annotation scheme for concept-to-speech synthesis. In Proceedings of the European Workshop on Natural Language Generation , pages 59-66, Toulouse, France, 1999.
[ bib | .ps | .pdf ]

Paul Taylor and Alan W Black. Speech synthesis by phonological structure matching. In Eurospeech99, Budapest, Hungary, 1999.
[ bib | .ps | .pdf ]

Kurt E. Dusterhoff, Alan W. Black, and Paul A. Taylor. Using decision trees within the tilt intonation model to predict f0 contours. In Eurospeech 99, Budapest, 1999.
[ bib | .ps | .pdf ]

Simon King, Todd Stephenson, Stephen Isard, Paul Taylor, and Alex Strachan. Speech recognition via phonetically featured syllables. In Proc. ICSLP `98, pages 1031-1034, Sydney, Australia, December 1998.
[ bib | .ps | .pdf | Abstract ]

Andreas Stolcke, E. Shriberg, R. Bates, P. Taylor, K. Ries, D. Jurafsky, N. Coccaro, R. Martin, M. Meteer, and C. Van Ess-Dykema. Dialog act modelling for conversational speech. In AAAI Spring Symposium on Applying Machine Learning to Discourse Processing, 1998.
[ bib | .ps | .pdf ]

Paul A. Taylor, S. King, S. D. Isard, and H. Wright. Intonation and dialogue context as constraints for speech recognition. Language and Speech, 41(3):493-512, 1998.
[ bib | .ps | .pdf ]

Janet Hitzeman, Alan W. Black, Paul Taylor, Chris Mellish, and Jon Oberlander. On the use of automatically generated discourse-level information in a concept-to-speech synthesis system. In ICSLP98 , volume 6, pages 2763-2768, Sydney, Australia, 1998.
[ bib | .ps | .pdf ]

Richard Sproat, Andrew Hunt, Mari Ostendorf, Paul Taylor, Alan Black, and Kevin Lenzo. Sable: a standard for TTS markup. In ICSLP98 , volume 5, pages 1719-1724, Sydney, Australia, 1998.
[ bib | .ps | .pdf ]

Richard Sproat, Andrew Hunt, Mari Ostendorf, Paul Taylor, Alan Black, and Kevin Lenzo. Sable: a standard for TTS markup. In Third ESCA workshop on speech synthesis, pages 27-30, Jenolan Caves, Blue Mountains, Australia, 1998.
[ bib | .ps | .pdf ]

Paul A Taylor. The Tilt intonation model. In ICSLP98 , Sydney, 1998.
[ bib | .ps | .pdf ]

Paul A Taylor, Alan Black, and Richard Caley. The architecture of the festival speech synthesis system. In The Third ESCA Workshop in Speech Synthesis, pages 147-151, Jenolan Caves, Australia, 1998.
[ bib | .ps | .pdf ]

R. Sproat, Paul A. Taylor, M. Tanenblatt, and Amy Isard. A markup language for text-to-speech synthesis. In Eurospeech 97, 1997.
[ bib | .ps | .pdf ]

Alan W. Black and Paul A. Taylor. Assigning phrase breaks from part-of-speech sequences. In Eurospeech97, volume 2, pages 995-998, Rhodes, Greece, 1997.
[ bib | .ps | .pdf ]

Dan Jurafsky, A. Stolcke, E. Shriberg, R. Bates, P. Taylor, K. Ries, N. Coccaro, R. Martin, M. Meteer, and C. Van Ess-Dykema. Automatic detection of discourse structure for speech recognition and understanding. In 1997 IEEEWorkshop on Speech Recognition and Understanding,, Santa Barbara, 1997.
[ bib | .ps | .pdf ]

Alan W. Black and Paul A. Taylor. Automatically clustering similar units for unit selection in speech synthesis. In Eurospeech97, volume 2, pages 601-604, Rhodes, Greece, 1997.
[ bib | .ps | .pdf ]

Helen Wright and Paul A. Taylor. Modelling intonational structure using hidden markov models. In ESCA workshop on Intonation: Theory Models and Applications, Athens, Greece, 1997.
[ bib | .ps | .pdf ]

Alan W. Black and Paul A. Taylor. The Festival Speech Synthesis System: System documentation. Technical Report HCRC/TR-83, Human Communciation Research Centre, University of Edinburgh, Scotland, UK, 1997. Avaliable at http://www.cstr.ed.ac.uk/projects/festival.html.
[ bib ]

Paul A. Taylor, Simon King, Stephen Isard, Helen Wright, and Jacqueline Kowtko. Using intonation to constrain language models in speech recognition. In Proc. Eurospeech'97, Rhodes, 1997.
[ bib | .pdf | Abstract ]

Paul A. Taylor, Hiroshi Shimodaira, Stephen Isard, Simon King, and Jacqueline Kowtko. Using prosodic information to constrain language models for spoken dialogue. In Proc. ICSLP `96, Philadelphia, 1996.
[ bib | .ps | .pdf ]

Stephen D. Isard, S. King, P. A. Taylor, and J. Kowtko. Prosodic information in a speech recognition system. In IEEE workshop on speech recognition, Snowbird, Utah, 1995.
[ bib ]

Stephen Isard, Simon King, Paul A. Taylor, and Jacqueline Kowtko. Prosodic information in a speech recognition system intended for dialogue. In IEEE Workshop in speech recognition, Snowbird, Utah, 1995.
[ bib | Abstract ]

Paul A. Taylor and Amy Isard. SSML: A speech synthesis markup language. In 2nd Speak! Workshop: Speech Generation in Multimodal Information Systems and Practical Applications, Darmstadt, 1995.
[ bib ]

Paul A. Taylor. Using neural networks to locate pitch accents. In Proc. Eurospeech '95, Madrid, 1995.
[ bib | .ps | .pdf ]

Eric Sanders and Paul A. Taylor. Using statistical models to predict phrase boundaries for speech synthesis. In Proc. Eurospeech '95, Madrid, 1995.
[ bib | .ps | .pdf ]

Alan W. Black and Paul A. Taylor. A framework for generating prosody from high level linguistics descriptions. In Spring meeting, Acoustical society of Japan, 1994.
[ bib ]

Alan W. Black and Paul A. Taylor. Assigning intonation elements and prosodic phrasing for English speech synthesis from high level linguistic input. In ICSLP94, volume 2, pages 715-718, Yokohama, Japan, 1994.
[ bib | .ps | .pdf ]

Alan W. Black and Paul A. Taylor. CHATR: A generic speech synthesis system. In COLING '94, volume 2, pages 983-986, Kyoto, Japan, 1994.
[ bib | .ps | .pdf ]

Paul A. Taylor and Alan W. Black. Synthesizing conversational intonation from a linguistically rich input. In Second ESCA/IEEE Workshop on Speech Synthesis, New York, 1994.
[ bib | .ps | .pdf ]

Paul A. Taylor. Automatic recognition of intonation from F0 contours using the rise/fall/connection model. In Proc. Eurospeech '93, Berlin, 1993.
[ bib | .ps | .pdf ]

Paul A. Taylor. Synthesizing intonation using the RFC model. In Proc. ESCA workshop on prosody, lund, sweden, 1993.
[ bib | .ps | .pdf ]

Paul A. Taylor and S. D. Isard. A new model of intonation for use with speech recognition and synthesis. In International Conference on Spoken Language Processing, Banff, Canada, 1992.
[ bib | .ps | .pdf ]

Paul A. Taylor. A phonetic model of English intonation . PhD thesis, University of Edinburgh, 1992.
[ bib | .ps | .pdf ]

Paul A. Taylor, I. A. Nairn, A. M. Sutherland, and M. A. Jack. A real time speech synthesis system. In Proc. Eurospeech '91, Genova Italy, 1991.
[ bib ]

Paul A. Taylor, I. A. Nairn, A. M. Sutherland, and M. A. Jack. A real time speech synthesis system. In IEEE symposium, 1991.
[ bib ]

Paul A. Taylor, I. A. Nairn, A. M. Sutherland, and M. A. Jack. An interactive synthetic speech generation system. In IEEE Colloquium on Systems and Applications of Man-Machine Interaction Using Speech I/O, London, 1991.
[ bib ]

Paul A. Taylor and Stephen D. Isard. Automatic diphone segmentation. In Proc. Eurospeech '91, Genova, Italy, 1991.
[ bib ]

Paul A. Taylor and Stephen D. Isard. Automatic diphone segmentation using hidden markov models. In SST-90, Third International Australian Conference in Speech Science and Technology, Melbourne, Australia, 1990.
[ bib ]