Gunnar's Homepage

I am working on my PhD in automatic speech recognition in the Speech, Vision and Robotics Group of the Cambridge University Engineering Department. My supervisor is Phil Woodland. Currently I spend most of my time writing a large vocabulary decoder and working on the HTK3 and the HTK Rich Audio Transcription projects. See my HTK homepage for details.

I will be joining VoiceSignal Technologies in Boston later this year to work on embedded speech recognition like voice dialing on mobile phones.

Curriculum Vitae

2002-now Research Associate in the HTK Rich Audio Transcription project (part of the DARPA EARS programme).

1999-now PhD student in the SVR group at CUED working on large vocabulary decoding

1998-1999 M.Phil. in 'Computer Speech and Language Processing' at Cambridge University

1993-1998 Baccalaureus Scientiae in Computer Science at University of Hamburg

1992-1993 service in the German Navy

Publications & Talks

G. Evermann, H.Y. Chan, M.J.F. Gales, T. Hain, X. Liu, D. Mrva, L. Wang, P.C. Woodland Development of the 2003 CU-HTK Conversational Telephone Speech Transcription System Proceedings ICASSP 2004, Montreal.

G. Evermann, P. C. Woodland Design of fast LVCSR Systems Proceedings IEEE ASRU, 2003, St. Thomas.

D.Y. Kim, G. Evermann, T. Hain, D. Mrva, S.E. Tranter, L. Wang, P.C. Woodland Recent Advances in Broadcast News Transcription Proceedings IEEE ASRU, 2003, St. Thomas.

G. Evermann, D. Y. Kim, L. Wang, P. C. Woodland 2003 CU-HTK Fast System Description Rich Transcription Workshop, May 2003, Boston, MA.

D. Y. Kim, G. Evermann, T. Hain, D. Mrva, S. E. Tranter, L. Wang and P. C. Woodland 2003 CU-HTK Broadcast News English System Development Rich Transcription Workshop, May 2003, Boston, MA.

P. C. Woodland, H. Y. Chan, G. Evermann, M. J. F. Gales, T. Hain, D. Y. Kim, X. Liu, D. Mrva, D. Povey, S. E. Tranter, L. Wang and K. Yu 2003 CU-HTK English CTS System Rich Transcription Workshop, May 2003, Boston, MA.

P.C. Woodland, G. Evermann, M.J.F. Gales, T. Hain, A. Liu, G. Moore, D. Povey, L. Wang CU-HTK April 2002 Switchboard System Rich Transcription Workshop, 2002, Vienna, VA

P.C. Woodland, T. Hain, G. Evermann, D. Povey CU-HTK March 2001 Hub5 System LVCSR Hub5 Workshop 2001, Linthicum Heights

T Hain, P C Woodland, G Evermann and D Povey New Features in the CU-HTK System for Transcription of Conversational Telephone Speech Proceedings ICASSP 2001, Salt Lake City

G Evermann, P C Woodland Posterior Probability Decoding, Confidence Estimation and System Combination Proceedings Speech Transcription Workshop 2000

T Hain, P C Woodland, G Evermann and D Povey The CU-HTK March 2000 Hub5E Transcription System Proceedings Speech Transcription Workshop 2000

G Evermann, P C Woodland Large Vocabulary Decoding and Confidence Estimation using Word Posterior Probabilities Proceedings ICASSP 2000, Istanbul

Gunnar Evermann Minimum Word Error Rate Decoding MPhil Thesis, Cambridge University Engineering Department, 1999

Gunnar Evermann Gewichtung von Aussprachevarianten in der automatischen Erkennung von Spontansprache (in German) Studienarbeit Uni Hamburg (in collaboration with DaimlerBenz Research), 1998

Henrik Heine, Gunnar Evermann, and Uwe Jost An HMM-based probabilistic lexicon ESCA Tutorial and Research Workshop on modeling pronunciation variation for automatic speech recognition, Rolduc 1998

Uwe Jost, Henrik Heine, and Gunnar Evermann What's wrong with the lexicon? -- An attempt to model pronunciations probabilistically Proceedings of Eurospeech 1997

Bibliographies of Speech Conferences

I have created BibTeX-files for various scientific conferences related to Speech Recognition.


Gunnar Evermann