A new look at discriminative training for hidden Markov models

Pattern Recognition Letters

Volumn 28, Issue 11, 2007, Pages 1285-1294

  He, Xiaodong ^a   Deng, Li ^a  

^a MICROSOFT RESEARCH   (United States)

Author keywords

Discriminative learning; Extended Baum Welch algorithm; Growth transformation; Hidden Markov model; Minimum classification error

Indexed keywords

ALGORITHMS; CLASSIFICATION (OF INFORMATION); ERROR DETECTION; HIDDEN MARKOV MODELS; OPTIMIZATION; PARAMETER ESTIMATION;

DISCRIMINATIVE LEARNING; EXTENDED BAUM-WELCH ALGORITHMS; GROWTH TRANSFORMATION; MINIMUM CLASSIFICATION ERRORS;

SPEECH RECOGNITION;

EID: 34249738104     PISSN: 01678655     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.patrec.2006.11.022     Document Type: Article

References (26)

1. Axelrod S., Goel V., Gopinath R., Olsen P., and Visweswariah K. Discriminative estimation of subspace constrained Gaussian mixture models for speech recognition. IEEE Trans. Audio Speech Language Process. 15 (2007) 172-189
2. Bahl L., Jelinek F., and Mercer R. A Maximum likelihood approach to continuous speech recognition. IEEE Trans. Pattern Anal. Mach. Intell. PAMI-5 (1987) 179-190
3. Brown, P., 1987. The Acoustic Modeling Problem in Automatic Speech Recognition, Ph.D. thesis, Carnegie Mellon University.
4. Chou W. Minimum classification error approach in pattern recognition. In: Chou W., and Juang B.-H. (Eds). Pattern Recognition in Speech and Language Processing (2003), CRC Press 1-49
5. Deng L., Wu J., Droppo J., and Acero A. Analysis and comparison of two feature extraction/compensation algorithms. IEEE Signal Process. Lett. 12 6 (2005) 477-480
6. Deng, L., Yu, D., Acero, A., 2005. A generative modeling framework for structured hidden speech dynamics. In: Proc. of Neural Information Processing System (NIPS) Workshop, Whistler, BC, Canada, December 2005.
7. Deng L., and O'Shaughnessy D. SPEECH PROCESSING - A Dynamic and Optimization-Oriented Approach (2003), Marcel Dekker Inc., New York, NY, USA
8. Gopalakrishnan P., Kanevsky D., Nadas A., and Nahamoo D. An inequality for rational functions with applications to some statistical estimation problems. IEEE Trans. Inf. Theory. 37 (1991) 107-113
9. Gunawardana, A., Byrne, W., 2001. Discriminative speaker adaptation with conditional maximum likelihood linear regression. In: Proc. EUROSPEECH.
10. He, X., Chou, W., 2003. Minimum classification error linear regression for acoustic model adaptation of continuous density HMMs. In: Proc. ICASSP.
11. He, X., Deng, L., Chou, W., 2006. A novel learning method for hidden Markov models in speech and audio processing. In: Proc. IEEE Workshop on Multimedia Signal Processing, Victoria, BC.
12. Jensen J.L.W.V. Sur les fonctions convexes et les inegalites entre les valeurs moyennes. Acta Math. (1906) 175-193
13. Juang B.-H., and Katagiri S. Discriminative learning for minimum error classification. IEEE Trans. Signal Process. 40 12 (1992) 3043-3054
14. Juang B.-H., Chou W., and Lee C.-H. Minimum classification error rate methods for speech recognition. IEEE Trans. Speech Audio Process. 5 (1997)
15. Macherey, W., Haferkamp, L., Schluter, R., Ney, H., 2005. Investigations on error minimizing training criteria for discriminative training in automatic speech Recognition. In: Proc. Interspeech, Lisbon, Portugal, pp. 2133-2136.
16. McDermott E., Hazen T., Roux J.L., Nakamura A., and Katagiri S. Discriminative training for large vocabulary speech recognition using minimum classification error. IEEE Trans. Audio Speech Language Process 15 1 (2007) 203-223
17. Normandin, Y., 1991. Hidden Markov Models, Maximum Mutual Information Estimation, and the Speech Recognition Problem, Ph.D. dissertation, McGill University, Montreal.
18. Povey, D., 2004. Discriminative Training for Large Vocabulary Speech Recognition, Ph.D. thesis, Cambridge University, Cambridge, UK.
19. Povey, D., Gales, M.J.F., Kim, D.Y., Woodland, P.C., 2003. MMI-MAP and MPE-MAP for acoustic model adaptation, In: Proc. Eurospeech.
20. Povey, D., Kingsbury, B., Mangu, L., Saon, G., Soltau, H., Zweig, G., 2004. fMPE: Discriminatively trained features for speech recognition. In: Proc. DARPA EARS RT-04 Workshop, November 7-10, Palisades, NY, Paper No. 35.
21. Povey, D., Woodland, P.C., 2002. Minimum phone error and I-Smoothing for improved discriminative training. In: Proc. ICASSP.
22. Rabiner L., and Juang B.-H. Fundamentals of Speech Recognition (1993), Prentice Hall, Englewood Cliffs, New Jersey
23. Rathinavalu C., and Deng L. Speech trajectory discrimination using the minimum classification error learning. IEEE Trans. Speech Audio Process. 6 6 (1998) 505-515
24. Roux, J., McDermott, E., 2005. Optimization for discriminative training. In: Proc. INTERSPEECH.
25. Schluter R., Macherey W., Muller B., and Ney H. Comparison of discriminative training criteria and optimization methods for speech recognition. Speech Commun. 34 (2001) 287-310
26. Woodland, P.C., Povey, D., 2000. Large scale discriminative training for speech recognition. In: Proc. ITRW ASR, ISCA.