On-Line Adaptive Learning of the Continuous Density Hidden Markov Model Based on Approximate Recursive Bayes Estimate

IEEE Transactions on Speech and Audio Processing

Volumn 5, Issue 2, 1997, Pages 161-172

  Huo, Qiang ^a,b   Lee, Chin Hui ^a  

^a ADVANCED TELECOMMUNICATIONS RESEARCH INSTITUTE INTERNATIONAL   (Japan)

^b LUCENT TECHNOLOGIES   (United States)

Author keywords

Automatic speech recognition, speaker adaptation; Em algorithm; Hidden markov model; Incremental maximum likelihood estimation; Recursive bayesian estimation

Indexed keywords

ADAPTIVE ALGORITHMS; LEARNING SYSTEMS; LOUDSPEAKERS; MARKOV PROCESSES; ONLINE SYSTEMS; RECURSIVE FUNCTIONS; TIME VARYING SYSTEMS;

HIDDEN MARKOV MODELS (HMM); MAXIMUM LIKELIHOOD ESTIMATION; RECURSIVE BAYESIAN ESTIMATION;

SPEECH RECOGNITION;

EID: 0031103160     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/89.554778     Document Type: Article

References (42)

1. A. Acero, Acoustical and Environmental Robustness in Automatic Speech Recognition. Norwell, MA: Kluwer, 1993.
2. B. S. Atal, "Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification," J. Acoust. Soc. Amer., vol. 55, pp. 1304-1312, 1974.
3. L. E. Baum, "An inequality and associated maximization techniques in statistical estimation for probabilistic functions of Markov processes," Inequalities, vol. 3, pp. 1-8, 1972.
4. L. E. Baum, T. Pétrie, G. Soûles, and N. Weiss, "A maximization technique occurring in the statistical analysis of probabilistic function of Markov chains," Ann. Math. Stat., vol. 41, pp. 164-171, 1970.
5. J. M. Bernardo, "Approximations in statistics from a decision-theoretical viewpoint," in Probability and Bayesian Statistics, R. Viertl, Ed. New York: Plenum, pp. 53-60, 1987.
6. J. M. Bernardo and F. J. Giron, "A Bayesian analysis of simple mixture problems," Bayesian Statistics 3, J. M. Bernardo, M. H. DeGroot, D. V. Lindley, and A. F. M. Smith, Eds. Oxford, UK: Oxford Univ. Press, 1988, pp. 67-78.
7. S. Cox and J. Bridle, "Unsupervised speaker adaptation by probabilistic spectrum fitting," in Proc. 1CASSP-89, pp. 294-297.
8. M. H. DeGroot, Optimal Statistical Decisions. New York: McGraw-Hill, 1970.
9. A. P. Dempster, N. M. Laird, and D. B. Rubin, "Maximum likelihood from incomplete data via the EM algorithm," J. Roy. Slat. Soc, Ser. B, vol. 39, no. 1, pp. 1-38.
10. V. V. Digalakis, D. Rtischev, and L. Neumeyer, "Speaker adaptation using constrained estimation of Gaussian mixtures," IEEE Trans. Speech Audio Processing, vol. 3, no. 5, pp. 357-366.
11. E. Eide and H. Gish, "A parametric approach to vocal tract length normalization," in Proc. 1CASSP-96, Atlanta, GA, May 1996, pp. 346-349.
12. J.-L. Gauvain and C.-H. Lee, "Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains," IEEE Trans. Speech Audio Processing, vol. 2, pp. 291-298, Apr. 1994.
13. Y. Gotoh, M. M. Hochberg, D. J. Mashao, and H. F. Silverman, "Incremental MAP estimation of HMM's for efficient training and improved performance," in Proc. ICASSP-95, Detroit, MI, pp. I-457-I-460.
14. Q. Huo, C. Chan, and C.-H. Lee,'"Bayesian adaptive learning of the parameters of hidden Markov model for speech recognition," IEEE Trans. Speech Audio Processing, vol. 3, no. 5, pp. 334-345.
15. _, "On-line adaptation of the SCHMM parameters based on the segmental quasi-Bayes learning for speech recognition," IEEE Trans. Speech Audio Processing, vol. 4, pp. 141-144, 1996.
16. Q. Huo and C.-H. Lee, "On-line adaptive learning of the correlated continuous density hidden Markov models for speech recognition," in Proc. ICSLP-96, Philadelphia, PA, Oct. 1996, pp. 985-988.
17. B.-H. Juang, S. E. Levinson, and M. M. Sondhi, "Maximum likelihood estimation for multivariate mixture observations of Markov chains," IEEE Trans. Inform. Tlieory, vol. IT-32, no. 2, pp. 307-309.
18. V. Krishnamurthy and J. B. Moore, "On-line estimation of hidden Markov model parameters based on the Kullback-Leibler information measure," IEEE Trans. Signal Processing, vol. 41, no. 8, pp. 2557-2573.
19. M. J. Lasry and R. M. Stem, "A posteriori estimation of correlated jointly Gaussian mean vectors," IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-6, no. 4, pp. 530-535.
20. C.-H. Lee, L. R. Rabiner, R. Pieraccini, and J. G. Wilpon, "Acoustic modeling for large vocabulary speech recognition," Coinpul. Speech Lang., vol. 4, pp. 127-165, 1990.
21. C.-H. Lee, C.-H. Lin, and B.-H. Juang, "A study on speaker adaptation of the parameters of continuous density hidden Markov models," IEEE Trans. Signal Processing, vol. 39, pp. 806-814, Apr. 1991.
22. L. Lee and R. C. Rose, "Speaker normalization using efficient frequency warping procedures," in Proc. ICASSP-96, Atlanta, GA, pp. 353-356.
23. C. J. Leggetter and P. C. Woodland, "Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models," Comput. Speech Lang., vol. 9, pp. 171-185, 1995.
24. L. R. Liporace, "Maximum likelihood estimation for multivariate observations of Markov sources," IEEE Trans. Inform. Tlieory, vol. IT-28, pp. 729-734.
25. U. E. Makov and A. F. M. Smith, "A quasi-Bayes unsupervised learning procedure for priors," IEEE Trans. Inform. Tlieory, vol. IT-23, no. 6, pp. 761-764.
26. J. S. Maritz and T. Lwin, Empirical Bayes Methods, 2nd ed. London, UK: Chapman & Hall, 1989.
27. J. J. Martin, Bayesian Decision Problems and Markov Chains. New York: Wiley, 1967.
28. T. Matsuoka and C.-H. Lee, "A study of on-line Bayesian adaptation for HMM-based speech recognition," in Proc. EUROSPEECH-93, Berlin, Germany, pp. 815-818.
29. L. R. Rabiner, "A tutorial on hidden Markov models and selected applications in speech recognition," in Proc. IEEE, vol. 77, no. 2, pp. 257-286.
30. M. G. Rahim and B.-H. Juang, "Signal bias removal by maximum likelihood estimation for robust telephone speech recognition," IEEE Trans. Speech Audio Processing, vol. 4, pp. 19-30, Jan. 1996.
31. M. G. Rahim, B.-H. Juang, W. Chou, and E. Buhrke, "Signal conditioning techniques for robust speech recognition," IEEE Signal Processing Lett., vol. 3, pp. 107-109, Apr. 1996.
32. H. Robbins, "The empirical Bayes approach to statistical decision problems," Ann. Math. Stat., vol. 35, pp. 1-20, 1964.
33. A. Sankar and C.-H. Lee, "A maximum likelihood approach to stochastic matching for robust speech recognition," IEEE Trans. Speech Audio Processing, vol. 4, no. 3, pp. 190-202.
34. A. F. M. Smith and U. E. Makov, "A quasi-Bayes sequential procedure for mixtures," J. Roy. Slat. Soc., Ser. B, vol. 40, no. 1, pp. 106-112.
35. J. Spragins, "A note on the iterative application of Bayes' rule," IEEE Trans. Inform. Theory, vol. IT-11, no. 4, pp. 544-549.
36. J. Takahashi and S. Sagayama, "Vector-field-smoothed Bayesian learning for incremental speaker adaptation," in Proc. ICASSP-95, Detroit, MI, pp. I-696-I-699.
37. D. M. Titterington, "Recursive parameter estimation using incomplete data," J. Roy. Stat. Soc., Ser. B, vol. 46, no. 2, pp. 257-267.
38. M. Tonomura, T. Kosaka, and S. Matsunaga, "Speaker adaptation based on transfer vector field smoothing using maximum a posteriori probability estimation," in Proc. ICASSP-95, Detroit, MI, pp. I-688-I-691.
39. S. Wegmann, D. McAlIaster, J. Orloff, and B. Peskin, "Speaker normalization on conversational telephone speech," in Proc. ICASSP-96, Atlanta, GA, pp. 339-341.
40. E. Weinstein, M. Feder, and A. V. Oppenheim, "Sequential algorithms for parameter estimation based on the Kullback-Leibler information measure," IEEE Trans. Acoust, Speech, Signal Processing, vol. 38, no. 9, pp. 1652-1654.
41. Y.-X. Zhao, "An acoustic-phonetic-based speaker adaptation technique for improving speaker-independent continuous speech recognition," IEEE Trans. Speech Audio Processing, vol. 2, no. 3, pp. 380-394.
42. Y.-X.' Zhao, "Self-learning speaker and channel adaptation based on spectral variation source decomposition," Speech Commun., vol. 18, pp. 65-77, 1996.