Overall risk criterion estimation of hidden Markov model parameters

Speech Communication

Volumn 38, Issue 3-4, 2002, Pages 383-398

  Kaiser, Janez ^a   Horvat, Bogomir ^b   Kačič, Zdravko ^b  

^a HERMES SoftLab   (Slovenia)

^b UNIVERSITY OF MARIBOR   (Slovenia)

Author keywords

Continuous speech recognition; Discriminative training; Extended Baum Welch algorithm; Hidden Markov models; Overall risk

Indexed keywords

ALGORITHMS; DATABASE SYSTEMS; MARKOV PROCESSES; MATHEMATICAL MODELS; MAXIMUM LIKELIHOOD ESTIMATION; PARAMETER ESTIMATION; RISK ASSESSMENT;

HIDDEN MARKOV MODELS (HMM);

CONTINUOUS SPEECH RECOGNITION;

EID: 0036836844     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-6393(02)00009-2     Document Type: Article

References (27)

1. Bahl L.R., Brown P.F., de Souza P.V., Mercer R.L. Maximum mutual information estimation of hidden Markov model parameters for speech recognition. Proc. ICASSP'86. 1986;49-52.
2. Chen J.-K., Soong F.K. An N-best candidates-based discriminative training for speech recognition applications. IEEE Trans. Speech and Audio Process. 2(1):1994;206-216.
3. Chow Y.-L. Maximum mutual information estimation of HMM parameters for continuous speech recognition using the N-best algorithm. Proc. ICASSP'90. 1990;701-704.
4. Duda R.O., Hart P.E. Pattern Classification and Scene Analysis. 1973;Wiley, New York.
5. Gopalakrishnan P., Kanevsky D., Nadas A., Nahamoo D. A generalization of the Baum algorithm to rational objective functions. Proc. ICASSP'89, Glasgow. 1989;631-634.
6. Huang X., Ariki Y., Jack M.A. Hidden Markov Models for Speech Recognition. 1990;Edinburgh University Press, Edinburgh.
7. Huang X.D., Lee K.F., Hon H.W., Hwang M.Y. Improved acoustic modeling with the SPHINX speech recognition system. Proc. ICASSP'91, Toronto, Canada. 1991;345-348.
8. Johansen F.T. Global discriminative modelling for automatic speech recognition, Ph.D. thesis. 1996;The Norwegian University of Science and Technology, Trondheim, Norway.
9. Juang B.-H., Katagiri S. Discriminative learning for minimum error classification. IEEE Trans. Signal Process. 40(12):1992;3043-3054.
10. Juang B.-H., Chou W., Lee C.-H. Minimum classification error rate methods for speech recognition. IEEE Trans. Speech and Audio Process. 5(3):1997;257-265.
11. Kaiser J., Horvat B., Kačič Z. A novel loss function for the overall risk criterion based discriminative training of HMM models. Proc. ICSLP 2000, Beijing, China. 2000.
12. Kapadia S., Valtchev V., Young S.J. MMI training for continuous phoneme recognition on the TIMIT database. Proc. ICASSP'93. 1993;491-494.
13. Lamel L., Gauvain J.-L. Continuous speech recognition at LIMSI. Final Review of the DARPA Artificial Neural Network Technology (ANNT) Speech Program, Stanford, CA. 1992;59-64.
14. Lamel L.F., Kassel R.H., Seneff S. Speech database development: Design and analysis of the acoustic-phonetic corpus. Proc. of the DARPA Speech Recognition Workshop. 1987;26-32.
15. Lee K. Automatic Speech Recognition: The Development of the SPHINX System. 1989;Kluwer Academic Publishers, Boston, MA.
16. Lee K.-F., Hon H.-W. Speaker-independent phone recognition using hidden Markov models. IEEE Trans. Acoust. Speech Signal Process. 37(11):1989;1641-1648.
17. Levenshtein A. Binary codes capable of correcting deletions, insertions and reversals. Soviet Phys. Dokl. 10:1966;707-710.
18. Lin M., Spanias A., Loizou P. An improved approach to robust speech recognition using minimum error classification. Speech Communication. 30(1):2000;27-36.
19. Na K., Jeon B., Chang D., Chae S., Ann S. Discriminative training of hidden Markov models using overall risk criterion and reduced gradient method. Proc. Eurospeech'95, Madrid. 1995;97-100.
20. Nadas A. A decision-theoretic formulation of a training problem in speech recognition and a comparison of training by unconditional versus conditional maximum likelihood. IEEE Trans. Acoust. Speech Signal Process. ASSP-31(4):1983;814-817.
21. Normandin Y. Hidden Markov models, maximum mutual information estimation, and the speech recognition problem, Ph.D. thesis. 1991;McGill University, Montreal.
22. Price P., Fisher W., Bernstein J., Pallet D. The DARPA 1000-word resource management database for continuous speech recognition. Proc. ICASSP'88. 1988;651-654.
23. Robinson A.J. An application of recurrent nets to phone probability estimation. IEEE Trans. Neural Networks. 5(2):1994;298-305.
24. Valtchev V., Odell J.J., Woodland P.C., Young S.J. Lattice-based discriminative training for large vocabulary speech recognition. Proc. ICASSP'96. 1996;605-608.
25. Woodland P., Young S. The HTK tied-state continuous speech recogniser. Proc. Eurospeech'93, Berlin, Germany. 1991;2207-2210.
26. Young S., Kershaw D., Odell J., Ollason D., Valtchev V., Woodland P. The HTK Book. 1999;Entropic.
27. Zavaliagkos G., Zhao Y., Schwartz R., Makhoul J. A hybrid segmental neural net/hidden Markov model system for continuous speech recognition. IEEE Trans. Speech and Audio Process. 2(1, Part 2):1994;151-160.