A maximum-likelihood approach to stochastic matching for robust speech recognition

IEEE Transactions on Speech and Audio Processing

Volumn 4, Issue 3, 1996, Pages 190-202

  Sankar, Ananth ^a,b   Lee, Chin Hui ^a  

^a LUCENT TECHNOLOGIES   (United States)

^b SRI INTERNATIONAL   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; ESTIMATION; FEATURE EXTRACTION; MARKOV PROCESSES; MATHEMATICAL MODELS; MATHEMATICAL TRANSFORMATIONS; RANDOM PROCESSES; SIGNAL DISTORTION; TRANSDUCERS;

EXPECTATION MAXIMIZATION ALGORITHM; HIDDEN MARKOV MODELS; INVERSE DISTORTION FUNCTION; SPEECH RECOGNITION SYSTEM; WORD ERROR RATE;

SPEECH RECOGNITION;

EID: 0030149866     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/89.496215     Document Type: Article

References (48)

1. B.-H. Juang, "Speech recognition in adverse environments," Comput. Speech Lang., vol. 5, pp. 275-294, 1991.
2. B.-H. Juang, L. R. Rabiner, and J. G. Wilpon, "On the use of bandpass liftering in speech recognition," IEEE Trans. Acoiist., Speech. Signal. Processing, vol. ASSP-35, pp. 947-954, July 1987.
3. B. 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, June 1974.
4. H. Hermansky, N. Morgan, A. Bayya, and P. Kohn, "Compensation for The effect of the communication channel in auditory-like analysis of speech (RASTA-PLP)," in Proc. EVROSPEECH, 1991, pp. 1367-1370.
5. O. Ghitza, "Auditory nerve representation as a basis for speech processing," in Advances in Speech and Signal Processing, S. Furui and M. Sondhi, Eds. New York: Marcel Dekker, 1991, pp. 453-485.
6. S. Seneff, "A joint synchrony/mean-rate model of auditory speech processing," J. Phonetics, vol. 16, pp. 55-76, 1990.
7. C.-H. Lee and C.-H. Lin, "On the use of a family of signal limiters for recognition of noisy speech," Speech Commun., vol. 12, pp. 383-392, 1993.
8. S. Das et al., "Influence of background noise and microphone on the performance of the IBM TANGORA speech recognition system," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, 1993, pp. 11-71.
9. D. Van Compernolle, "Spectral estimation using a log-distance error criterion applied to speech recognition," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing. 1989, pp. 258-261.
10. _, "Noise adaptation in a hidden Markov model speech recognition system," Compiit. Speech Lang., vol. 3, pp. 151-167, 1989.
11. J. E. Porter and S. F. Boll, "Optimal estimators for spectral restoration of noisy speech," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, 1984, pp. 18.
12. Y. Ephraim and D. Malah, "Speech enhancement using a minimum mean square error short-time spectral amplitude estimator," IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-32, pp. 1109-1121, Dec. 1984.
13. -, "Speech enhancement using a minimum mean square error log-spectral amplitude estimator," IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-33, pp. 443-445, Apr. 1985.
14. A. Ereil and M. Weintraub, "Estimation using log-spectral-distance criterion for noise-robust speech recognition," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, 1990, pp. 853-856.
15. Y. Ephraim, "A minimum mean square error approach for speech enhancement," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, 1990, pp. 829-832.
16. A. Ereil and M. Weintraub, "Filterbank-energy estimation using mixture and Markov models for recognition of noisy speech," IEEE Trans. Speech Audio Processing, vol. 1, pp. 68-76, Jan. 1993.
17. D. Klatt, "A digital filterbank for spectral matching," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, 1976, pp. 573-576.
18. J. Holmes and N. Sedgwick, "Noise compensation for speech recognition using probabilistic models," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, pp. 14, 1986.
19. A. Nadas, D. Nahamoo, and M. Picheny, "Speech recognition using noise-adaptive prototypes," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing. 1988, pp. 517-520.
20. A. Varga, R. Moore, J. Bridle, K. Ponting, and M. Russell, "Noise compensation algorithms for use with hidden Markov model based speech recognition," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, 1988, pp. 481-484.
21. A. Varga and R. Moore, "Hidden Markov model decomposition of speech and noise," in Proc. IEEE Int. Conf. Acousl., Speech, Signal Processing, 1990, pp. 845-848.
22. M. Wang and S. Young, "Speech recognition using hidden Markov model decomposition and a general background speech model," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, 1992, pp. I-253-I-256.
23. M. Gales and S. Young, "An improved approach to the hidden Markov model decomposition of speech and noise," in Proc. IEEE Int. Conf. Acomt., Speech, Signal Processing, 1992, pp. I-233-I-236.
24. R. Rose, E. Hofstetter, and D. Rey nolds"lntegrated models of speech and background with application to speaker identification in noise," IEEE Trans. Speech Audio Processing, vol. 2, pp. 245-257, Apr. 1994.
25. Y. Ephraim, "Gain-adapted hidden Markov models for recognition of clean and noisy speech," IEEE Trans. Signal Processing, vol. 40, pp. 1303-1316, June 1992.
26. N. Merhav and C.-H. Lee, "A minimax classification approach with application to robust speech recognition," IEEE Trans. Speech Audio Processing, vol. 1, pp. 90-100, Jan. 1993.
27. S. Cox and J. Bridle, "Unsupervised speaker adaptation by probabilistic spectrum fitting," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, 1989, pp. 294-297.
28. -, "Simultaneous speaker normalization and utterance labeling using Bayesian/neural net techniques," in Proc. IEEE Int. Conf. Acousl., Speech, Signal Processing, 1990, pp. 161-164.
29. Y. Zhao, "A new speaker adaptation technique using very short calibration speech," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, 1993, pp. II-562-II-565.
30. M. Rahim and B.-H. Juang, "Signal bias removal for robust telephone speech recognition in adverse environments," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, 1994.
31. A. Acero and R. Stern, "Environmental robustness in automatic speech recognition," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, 1990, pp. 849-852.
32. A. Acero, Acoustical and Environmental Robustness in Automatic Speech Recognition. Boston, MA: Kluwer, 1992.
33. C.-H. Lee, L. R. Rabiner, R. Pieraccini, and J. Wilpon, "Acoustic modeling for large vocabulary speech recognition," Comput. Speech Lang., vol. 4, pp. 127-165, Jan. 1990.
34. L. R. Rabiner, "A tutorial on hidden Markov models and selected applications in speech recognition," Proc. IEEE, vol. 77, pp. 257-286, Feb. 1989.
35. L. Bahl, F. Jelinek, and R. Mercer, "A maximum likelihood approach to continuous speech recognition," IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-5, pp. 179-190, Mar. 1983.
36. H. Sakoe, 'Two-level DP-matching-A dynamic programming-based pattern matching algorithm for connected word recognition," IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-27, pp. 588-595, Dec. 1979.
37. C. Myers and L. Rabiner, "A level building dynamic time warping algorithm for connected word recognition," IEEE Trans. Acoust., Speech Signal Processing, vol. ASSP-29, pp. 284-297, Apr. 1981.
38. C.-H. Lee and L. Rabiner, "A frame-synchronous network search algorithm for connected word recognition," IEEE Trans. Acoust., Speech, Signal Processing, vol. 37, pp. 1649-1658, Nov. 1989.
39. A. Dempster, N. Laird, and D. Rubin, "Maximum likelihood from incomplete data via the EM algorithm," J. Royal Statist. Soc., vol. 39, pp. 1-38, 1977.
40. L. Baum, T. Pétrie, G. Soûles, and N. Weiss, "A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains," Ann. Math. Statist., vol. 41, no. 1, pp. 164-171, 1970.
41. B.-H. Juang, "Maximum-likelihood estimation for mixture multivariate stochastic observations of Markov chains," AT&T Tech. J., vol. 64, no. 6, pp. 1235-1249, 1985.
42. L. R. Rabiner, J. Wilpon, and B.-H. Juang, "A segmental K-means training procedure for connected word recognition," AT&T Tech. J., vol. 64, pp. 21, May 1986.
43. G. Forney, "The Viterbi algorithm," Proc. IEEE, vol. 61, pp. 268-278, Mar. 1973.
44. P. Price, W. Fisher, J. Bernstein, and D. Pallet!, "A database for continuous speech recognition in a 1000-word domain," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, 1988, pp. 651-654.
45. C.-H. Lee, E. Giachin, L. Rabiner, R. Pieraccini, and A. Rosenberg, "Improved acoustic modeling for large vocabulary continuous speech recognition," Comput. Speech Lang., vol. 6, pp. 103-127, 1992.
46. J. Gauvain and C.-H. Lee, "Maximum a posterior estimation for multivariate Gaussian mixture observations of Markov chains," IEEE Trans. Speech Audio Processing, vol. 2, pp. 291-298, Apr. 1994.
47. C.-H. Lee, J.-L. Gauvain, R. Pieraccini, and L. Rabiner, "Large vocabulary speech recognition using subword units," Speech Commun., vol. 13, pp. 263-279, 1993.
48. C.-H. Lee and J.-L. Gauvain, "Speaker adaptation based on MAP estimation of HMM parameters," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, 1993, pp. II-558-II-561.