IMPROVEMENTS IN ACCURACY AND SPEED IN THE HTK BROADCAST NEWS TRANSCRIPTION SYSTEM

6th European Conference on Speech Communication and Technology, EUROSPEECH 1999

Volumn , Issue , 1999, Pages 1043-1046

  Woodland, P C ^a,b   Odell, J J ^b   Hain, T ^a   Moore, G L ^a   Niesler, T R ^a   Tuerk, Andreas ^a   Whittaker, E W D ^a  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

^b Entropic Ltd   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

SPEECH PROCESSING;

% REDUCTIONS; BROADCAST NEWS TRANSCRIPTIONS; CLUSTER-BASED; ERROR RATE; LANGUAGE MODEL; NORMALISATION; REAL- TIME; TRAINING DATA; VOCAL-TRACT LENGTH NORMALIZATIONS; WORD ERROR RATE;

SPEECH COMMUNICATION;

EID: 2642560241     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (11)

1. Fiscus, J.G. (1997) A Post-Processing System to Yield Reduced Word Error Rates: Recogniser Output Voting Error Reduction (ROVER). Proc. IEEE Workshop on Automatic Speech Recognition and Understanding, pp. 347-354, Santa Barbara.
2. Gales M.J.F. & Woodland P.C. (1996). Mean and Variance Adaptation Within the MLLR Framework. Computer Speech & Language, Vol. 10, pp. 249-264.
3. Gales M.J.F. (1997). Maximum Likelihood Linear Transformations for HMM-based Speech Recognition. Technical Report, CUED-F-INFENG TR.291, Cambridge University Engineering Dept.
4. Hain T, Johnson S.E., Tuerk A., Woodland P.C. & Young S.J. (1998) Segment Generation and Clustering in the HTK Broadcast News Transcription System. Proc. 1998 DARPA Broadcast News Transcription and Understanding Workshop, pp. 133-137.
5. Hain T., Woodland P.C., Niesler T.R. & Whittaker E.W.D. (1999). The 1998 HTK System for Transcription of Conversational Telephone Speech. Proc. ICASSP'99, pp. 57-60, Phoenix.
6. Leggetter C.J. & Woodland P.C. (1995). Flexible Speaker Adaptation Using Maximum Likelihood Linear Regression. Proc. ARPA Spoken Language Technology Workshop, pp. 104-109. Morgan Kaufmann.
7. Leggetter C.J. & Woodland P.C. (1995). Maximum Likelihood Linear Regression for Speaker Adaptation of Continuous Density Hidden Markov Models. Computer Speech & Language, Vol. 9, pp. 171-185.
8. Niesler T.R., Whittaker E.W.D & Woodland P.C. (1998). Comparison of Part-Of-Speech and Automatically Derived Category-Based Language Models for Speech Recognition. Proc. ICASSP'98, pp. 177-180, Seattle.
9. Pye, D. & Woodland P.C. (1997). Experiments in Speaker Normalisation and Adaptation for Large Vocabulary Speech Recognition. Proc. ICASSP'97, pp. 1047- 1050, Munich.
10. Wegmann S., Scattone F., Carp I., Gillick L., Roth R. & Yamron J. (1998) Dragon Systems' 1997 Broadcast News Transcription System. Proc. 1998 DARPA Broadcast News Transcription and Understanding Workshop, Lansdowne.
11. Woodland P.C, Hain T., Johnson S.E., Niesler T.R., Tuerk A., Whittaker E.W.D. & Young S.J. (1998). The 1997 HTK Broadcast News Transcription System. Proc. 1998 DARPA Broadcast News Transcription and Understanding Workshop, pp. 41-48, Lansdowne.