Minimum phone error training of precision matrix models

IEEE Transactions on Audio, Speech and Language Processing

Volumn 14, Issue 3, 2006, Pages 882-889

  Sim, Khe Chai ^a,b   Gales, Mark J F ^a,b  

^a IEEE   (United Kingdom)

^b UNIVERSITY OF CAMBRIDGE   (United Kingdom)

Author keywords

Discriminative training; Large vocabulary continuous speech recognition (LVCSR); Minimum phone error; Precision matrix modeling

Indexed keywords

DISCRIMINATIVE TRAINING; GAUSSIAN MIXTURE MODELS (GMM); LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION (LVCSR); MINIMUM PHONE ERROR; PRECISION MATRIX MODELING;

CORRELATION METHODS; ERROR ANALYSIS; PROBLEM SOLVING; VECTOR QUANTIZATION;

APPROXIMATION THEORY;

EID: 34047275940     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TSA.2005.858062     Document Type: Article

References (32)

1. L. E. Baum and J. A. Eagon, "An inequality with applications to statistical estimation for probabilistic functions of Markov processes and to a model for ecology," Bull. Amer. Math. Soc., vol. 73, pp. 360-363, 1967.
2. S. J. Young, "Large vocabulary continuous speech recognition: a review," in Proc. IEEE Workshop Automatic Speech Recognition Understanding, Snowbird, UT, Dec. 1995, pp. 3-28.
3. S. B. Davis and P. Mermelstein, "Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences," IEEE Trans. Acoustic, Speech, Signal Process., vol. ASSP-28, no. 4, pp. 357-366, Aug. 1980.
4. H. Hermansky, "Perceptual Linear Predictive (PLP) analysis of speech," J. Acoust. Soc. Amer., vol. 87, no. 4, pp. 1738-1752, 1990.
5. G. Saon, M. Padmanabhan, R. Gopinath, and S. Chen, "Maximum likelihood discriminant feature spaces," in Proc. ICASSP, 2000, pp. 1129-1130.
6. N. Kumar, "Investigation of silicon-auditory models and generalization of linear discriminant analysis for improved speech recognition," Ph.D. dissertation, Dept. Elect. Comp. Eng., Johns Hopkins Univ., Baltimore, MD, 1997.
7. N. K. Goel and A. G. Andreou, "Heteroscedastic discriminant analysis and reduced-rank HMMs for improved speech recognition," Speech Commun., vol. 26, pp. 283-297, 1998.
8. A.-V. I. Rosti and M. J. F. Gales, "Factor analyzed hidden Markov models for speech recognition," Cambridge Univ., Cambridge, U.K., Tech. Rep. CUED/F-INFENG/TR453 [Online]. Available: (via anonymous) ftp://svr-www.eng.cam.ac.uk, 2003.
9. M. J. F. Gales, "Semi-tied covariance matrices for hidden Markov models," IEEE Trans. Speech Audio Process., vol. 7, no. 3, pp. 272-281, May 1999.
10. P. Olsen and R. A. Gopinalh, "Modeling inverse covariance matrices by basis expansion," in Proc. ICASSP, 2002, pp. 945-948.
11. S. Axelrod, R. Gopinath, and P. Olsen, "Modeling with a subspace constraint on inverse covariance matrices," in Proc. ICSLP, 2002, pp. 2177-2180.
12. J. Huang, V. Goel, R. A. Gopinath, B. Kingsbury, P. Olsen, and K. Visweswariah, "Large vocabulary conversational speech recognition with the extended maximum likelihood linear transformation (EMLLT) model," in Proc. ICSLP, 2002, pp. 2597-2600.
13. S. Axelrod, V. Goel, B. Kingsbury, K. Visweswariah, and R. A. Gopinath, "Large vocabulary conversational speech recognition with a subspace constraint on inverse covariance matrices," in Proc. Eurospeech, 2003, pp. 1613-1616.
14. P. C. Woodland and D. Povey, "Large scale discriminative training of hidden Markov models in speech recognition," Comput. Speech Lang., vol. 16, no. 1, pp. 25-48, Jan. 2002.
15. D. Povey and P. C. Woodland, "Minimum phone error and I-smoothing for improved discriminative training," in Proc. ICASSP, 2002, pp. 105-108.
16. G. Evermann, H. Y. Chan, M. J. F. Gales, T. Hain, X. Liu, D. Mrva, L. Wang, and P. C. Woodland, "Development of the 2003 CU-HTK conversational telephone speech transcription system," in Proc. ICASSP, 2004, pp. 249-252.
17. D. Y. Kim, G. Evermann, T. Hain, D. Mrva, S. E. Tranter, L. Wang, and P. C. Woodland, "Recent advances in broadcast news transcription," in Proc. ASRU, 2003, pp. 105-110.
18. J. McDonough and A. Waibel, "Maximum mutual information speaker adapted training with semi-tied covariance matrices," in Proc. ICASSP, 2003, pp. 128-131.
19. V. Goel, S. Axelrod, R. Gopinath, P. Olsen, and K. Visweswariah, "Discriminative estimation of Subspace Precision and Mean (SPAM) models," in P roc. EUROSPEECH, 2003, pp. 2617-2620.
20. K. C. Sim and M. J. F. Gales, "Basis superposition precision matrix modeling for large vocabulary continuous speech recognition," in Proc. ICASSP, 2004, pp. 801-804.
21. _, "Precision matrix modeling for large vocabulary continuous speech recognition," Cambridge Univ., Tech. Rep. CUED/F-IN-FENG/TR485 [Online]. Available: (via anonymous) ftp://svr-www.eng.cam.ac.uk, 2004.
22. K. Visweswariah, P. Olsen, R. Gopinath, and S. Axelrod, "Maximum likelihood training of subspaces for inverse covariance modeling," in Proc. ICASSP, 2003, pp. 896-899.
23. A. P. Dempster, N. M. Laird, and D. B. Rubin, "Maximum likelihood from incomplete data via the EM algorithm," J. Royal Statist. Soc., vol. 39, pp. 1-39, 1977.
24. S. Tsakalidis, V. Doumpiotis, and W. Byrne, "Discriminative linear transforms for feature normalization and speaker adaptation in hmm estimation," in Proc. ICSLP, 2002, pp. 2585-2588.
25. D. Povey, P. C. Woodland, and M. J. F. Gales, "Discriminative MAP for acoustic model adaptation," in Proc. ICASSP, 2003, pp. 312-315.
26. P. Gopalakrishnan, D. Kanevsky, A. Nadas, and D. Nahamoo, "An inequality for rational functions with applications to some statistical estimation problems," IEEE Trans. Inform. Theory, no. 1, pp. 107-113, Jan. 1991.
27. Y. Normandin, "Hidden Markov models, maximum mutual information estimation and the speech recognition problem," Ph.D. dissertation, Dept. Elect. Comp. Eng., McGill Univ., Montreal, QC, Canada, 1991.
28. E. Polak, Computational Methods in Optimization: A Unified Approach. New York: Academic, 1971.
29. S. J. Young, D. Kershaw, J. J. Odell, D. Ollason, V. Valtchev, and P. C. Woodland, The HTK Book (for HTK Version 3.0). Cambridge, U.K.: Cambridge Univ. Press, 1997.
30. M. J. F. Gales, "Maximum Likelihood Multiple Projection Schemes for Hidden Markov Models," Cambridge Univ., Cambridge, U.K., Tech. Rep. CUED/F-INFENG/TR365 [Online]. Available: (via anonymous) ftp://svr-www.eng.cam. ac.uk, 1999.
31. X. Liu and M. J. F. Gales, "Automatic model complexity control using marginalized discriminative growth functions," in Proc. IEEE Workshop Automatic Speech Recognition and Understanding (ASRU), 2003, pp. 37-42.
32. M. J. F. Gales, "The Generation and the Use of Regression Class Trees for MLLR Adaptation," Cambridge Univ.., Cambridge, U.K., Tech. Rep. CUED/F-INFENG/TR263 [Online]. Available: (via anonymous) ftp://svr-www.eng.cam. ac.uk, 1996.