Robust speech recognition based on adaptive classification and decision strategies

Speech Communication

Volumn 34, Issue 1-2, 2001, Pages 175-194

  Huo, Qiang ^a   Lee, Chin Hui ^b  

^a UNIVERSITY OF HONG KONG   (Hong Kong)

^b LUCENT TECHNOLOGIES   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ADAPTIVE FILTERING; DATA STRUCTURES; DECISION THEORY; ERROR ANALYSIS; MATHEMATICAL MODELS; PROBABILITY DISTRIBUTIONS; ROBUSTNESS (CONTROL SYSTEMS);

BAYESIAN PREDICTIVE CLASSIFICATIONS; MINIMAX DECISION RULES;

CONTINUOUS SPEECH RECOGNITION;

EID: 0034831586     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-6393(00)00053-4     Document Type: Article

References (69)

1. Acero, A., 1993. Acoustical and environmental robustness in automatic speech recognition. Kluwer Academic Publishers, Dordrecht.
2. Aitchison, J., Dunsmore, I.R., 1975. Statistical Prediction Analysis. Cambridge University Press, UK.
3. Atal, B.S., 1974. Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification. J. Acoust. Soc. Am. 55 (6), 1304-1312.
4. Chesta, C., Siohan, O., Lee, C.-H., 1999. Maximum a posterior linear regression for hidden Markov model adaptation. In: Proc. Eurospeech-99. Budapest, Hungary.
5. Chien, J.-T., 1999. Online hierarchical transformation of hidden markov models for speech recognition. IEEE Trans. Speech Audio Process. 7 (6), 656-667.
6. Chien, J.-T., Wang, H.-C., 1997. Telephone speech recognition based on Bayesian adaptation of hidden Markov models. Speech Communication 22, 369-384.
7. Chien, J.-T., Lee, C.-H., Wang, H.-C., 1997. A hybrid algorithm for speaker adaptation using MAP transformation and adaptation. IEEE Signal Process. Lett. 4 (6), 167-168.
8. Chou, W., 1999. Maximum a posterior linear regression with elliptically symmetric matrix variate priors. In: Proc. Eurospeech-99. Budapest, Hungary.
9. Dempster, A., Laird, N., Rubin, D., 1977. Maximum likelihood from incomplete data via the EM algorithm. J. Roy. Statist. Soc. B 39 (1), 1-38.
10. Diakoloukas, V.D., Digalakis, V. V., 1999. Maximum-likelihood stochastic-transformation adaptation of hidden Markov models. IEEE Trans. Speech Audio Process. 7 (2), 177-187.
11. Digalakis, V.V., 1999. Online adaptation of hidden Markov models using incremental estimation algorithms. IEEE Trans. Speech Audio Process. 7 (3), 253-261.
12. Digalakis, V.V., Neumeyer, L.G., 1996. Speaker adaptation using combined transformation and Bayesian methods. IEEE Trans. Speech Audio Process. 4 (4), 294-300.
13. Digalakis, V.V., Rtischev, D., Neumeyer, L.G., 1995. Speaker adaptation using constrained estimation of Gaussian mixtures. IEEE Trans. Speech Audio Process. 3 (5), 357-366.
14. Gales, M.J.F., 1998. Maximum likelihood linear transformations for HMM-based speech recognition. Comput. Speech Language 12, 75-98.
15. Gales, M.J.F., Woodland, P.C., 1996. Mean and variance adaptation within the MLLR framework. Comput. Speech Language 10, 249-264.
16. Gauvain, J.-L., Lee, C.-H., 1994. Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains. IEEE Trans. Speech Audio Process. 2 (2), 291-298.
17. Geisser, S., 1993. Predictive Inference: An Introduction. Chapman & Hall, New York.
18. Hermansky, H., 1998. Should recognizers have ears?. Speech Communication 25, 3-27.
19. Hunt, M.J., 1999. Spectral signal processing for ASR. In: Proc. 1999 IEEE Workshop on Automatic Speech Recognition and Understanding. Keystone, CO.
20. Huo, Q., 1999. An introduction to decision rules for automatic speech recognition. Technical Report TR-99-07, Department of Computer Science and Information Systems, The University of Hong Kong (available at URL: http:// www.csis.hku.hk/publications/).
21. Huo, Q., Lee, C.-H., 1997a. On-line adaptive learning of the continuous density hidden Markov model based on approximate recursive Bayes estimate. IEEE Trans. Speech Audio Process. 5 (2), 161-172.
22. Huo, Q., Lee, C.-H., 1997b. Combined on-line model adaptation and Bayesian predictive classification for robust speech recognition. In: Proc. Eurospeech-97. Rhodes, Greece.
23. Huo, Q., Lee, C.-H., 1998a. On-line adaptive learning of the correlated continuous density hidden Markov models for speech recognition. IEEE Trans. Speech Audio Process. 6 (4), 386-397.
24. Huo, Q., Lee, C.-H., 1998b. A study of prior sensitivity for Bayesian predictive classification based robust speech recognition. In: Proc. ICASSP-98. Seattle, pp. 741-744.
25. Huo, Q., Lee, C.-H., 2000. A Bayesian predictive classification approach to robust speech recognition. IEEE Trans. Speech Audio Process. 8 (2), 200-204.
26. Huo, Q., Ma, B., 1999. On-line adaptive learning of continuous density hidden Markov models based on multiple-stream prior evolution and posterior pooling. Submitted to IEEE Trans. Speech Audio Process. See also a condensed version in: Proc. Eurospeech-99. Budapest, Hungary, pp. 2721- 2724.
27. Huo, Q., Ma, B., 1999. On-line adaptive learning of continuous density hidden Markov models based on multiple-stream prior evolution and posterior pooling. Submitted to IEEE Trans. Speech Audio Process. See also a condensed version in: Proc. Eurospeech-99. Budapest, Hungary, pp. 2721-2724.
28. Huo, Q., Chan, C., Lee, C.-H., 1995. Bayesian adaptive learning of the parameters of hidden Markov model for speech recognition. IEEE Trans. Speech Audio Process. 3 (5), 334-345.
29. Huo, Q., Jiang, H., Lee, C.-H., 1997. A Bayesian predictive classification approach to robust speech recognition. In: Proc. ICASSP-97. Munich, pp. 1547-1550.
30. Jelinek, F., Mercer, R.L., Roukos, S., 1991. Principles of lexical language modeling for speech recognition. In: Furui, S., Sondhi, M.M., (Eds.), Advances in Speech Signal Processing. Marcel Dekker, New York, pp. 651-699.
31. Jiang, H., Hirose, K., Huo, Q., 1998. A minimax search algorithm for CDHMM based robust continuous speech recognition. In: Proc. ICSLP-98. Sydney, pp. II-389-392.
32. Jiang, H., Hirose, K., Huo, Q., 1999a. Robust speech recognition based on a Bayesian prediction approach. IEEE Trans. Speech Audio Process. 7 (4), 426-440.
33. Jiang, H., Hirose, K., Huo, Q., 1999b. Improving Viterbi Bayesian predictive classification via sequential Bayesian learning in robust speech recognition. Speech Communication 28 (4), 313-326.
34. Kharin, Y., 1996. Robustness in Statistical Pattern Recognition. Kluwer Academic Publishers, Boston.
35. Lasry, M.J., Stern, R.M., 1984. A posteriori estimation of correlated jointly Gaussian mean vectors. IEEE Trans. Pattern Anal. Machine Intell. 6 (4), 530-535.
36. Lawrence, C., Rahim, M., 1999. Integrated bias removal techniques for robust speech recognition. Comput. Speech Language 13, 283-298.
37. Lee, C.-H., 1998. On stochastic feature and model compensation approaches to robust speech recognition. Speech Communication 25 (1-3), 29-47.
38. Lee, C.-H., Rabiner, L.R., Pieraccini, R., Wilpon, J.G., 1990. Acoustic modeling for large vocabulary speech recognition. Comput. Speech Language 4, 127-165.
39. Lee, C.-H., Lin, C.-H., Juang, B.-H., 1991. A study on speaker adaptation of the parameters of continuous density hidden Markov models. IEEE Trans. Signal Process. 39 (4), 806-814.
40. Lee, C.-H., Soong, F.-K., Paliwal K.-K. (Eds.), 1996. Automatic Speech and Speaker Recognition: Advanced Topics. Kluwer Academic Publishers, Boston.
41. Leggetter, C.J., Woodland, P.C., 1995a. Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models. Comput. Speech Language 9, 171-185.
42. Leggetter, C.J., Woodland, P.C., 1995b. Flexible speaker adaptation for large vocabulary speech recognition. In: Proc. Eurospeech-95. Madrid, Spain, pp. 1155-1158.
43. Merhav, N., Ephraim, Y., 1991. A Bayesian classification approach with application to speech recognition. IEEE Trans. Signal Process. 39 (10), 2157-2166.
44. Merhav, N., Lee, C.-H., 1993. A minimax classification approach with application to robust speech recognition. IEEE Trans. Speech Audio Process. 1 (1), 90-100.
45. Mokbel, C., Delphin-Poulat, L., 1999. A unified framework for auto-adaptive speech recognition. In: Proc. Workshop on Robust Methods for Speech Recognition in Adverse Conditions. Tampere, pp. 227-230.
46. Moon, S., Hwang, J.-N., 1997. Robust speech recognition based on joint model and feature space optimization of hidden Markov models. IEEE Trans. Neural Networks 8 (2), 194-204.
47. Morgan, N., 1999. Temporal signal processing for ASR. In: Proc. 1999 IEEE Workshop on Automatic Speech Recognition and Understanding. Keystone, CO.
48. Nadas, A., 1985. Optimal solution of a training problem in speech recognition. IEEE Trans. Acoust. Speech Signal Process. 33 (1), 326-329.
49. Paul, D.B., 1997. Extensions to phone-state decision-tree clustering: single tree and tagged clustering. In: Proc. ICASSP-97. Munich, Germany, pp. II-1487-1490.
50. Rabiner, L.R., 1989. A tutorial on hidden Markov models and selected applications in speech recognition. Proc. IEEE 77 (2), 257-286.
51. Rahim, M.G., Juang, B.-H., 1996. Signal bias removal by maximum likelihood estimation for robust telephone speech recognition. IEEE Trans. Speech Audio Process. 4 (1), 19-30.
52. Rahim, M.G., Juang, B.-H., Chou, W., Buhrke, E., 1996. Signal conditioning techniques for robust speech recognition. IEEE Signal Process. Lett. 3 (4), 107-109.
53. Ripley, B.D., 1996. Pattern Recognition and Neural Networks. Cambridge University Press, UK.
54. Sankar, A., Lee, C.-H., 1996. A maximum likelihood approach to stochastic matching for robust speech recognition. IEEE Trans. Speech Audio Process. 4 (3), 190-202.
55. Shahshahani, B.M., 1997. A markov random field approach to Bayesian speaker adaptation. IEEE Trans. Speech Audio Process. 5 (2), 183-191.
56. Shinoda, K., Lee, C.-H., 1997. Structural MAP speaker adaptation using hierarchical priors. In: Proc. 1997 IEEE Workshop on Automatic Speech Recognition and Understanding. Santa Barbara, pp. 381-388.
57. Shinoda, K., Lee, C.-H., 1998. Unsupervised adaptation using structural Bayes approach. In: Proc. ICASSP-98. Seattle, pp. 793-796.
58. Siohan, O., Chesta, C., Lee, C.-H., 1999. Hidden Markov model adaptation using maximum a posteriori linear regression. In: Proc. Workshop on Robust Methods for Speech Recognition in Adverse Conditions. Tampere, pp. 147-150.
59. Siohan, O., Chesta, C., Lee, C.-H., 2000. Joint maximum a posteriori adaptation of transformation and HMM parameters, In: Proc. ICASSP-2000. Istanbul, Turkey.
60. Stern, R.M., Lasry, M.J., 1987. Dynamic speaker adaptation for feature-based isolated word recognition. IEEE Trans. Acoust. Speech Signal Process. 35 (6), 751-763.
61. Surendran, A., Lee, C.-H., 1998. Predictive adaptation and compensation for robust speech recognition. In: Proc. ICSLP-98. Sydney.
62. Surendran, A., Lee, C.-H., 1999. Bayesian predictive approach to adaptation of HMMs. In: Proc. Workshop on Robust Methods for Speech Recognition in Adverse Conditions. Tampere, pp. 155-158.
63. Surendran, A.C., Lee, C.-H., Rahim, M., 1999. Nonlinear compensation for stochastic matching. IEEE Trans. Audio Speech Process. 7 (6), 643-655.
64. Takahashi, J., Sagayama, S., 1997. Vector-field-smoothed Bayesian learning for fast and incremental speaker/telephone-channel adaptation. Comput. Speech Language 11, 127-146.
65. Wang, S.-J., Zhao, Y.-X., 1999. On-line Bayesian tree-structured transformation of hidden Markov models for speaker adaptation. In: Proc. IEEE Automatic Speech Recognition and Understanding Workshop. Keystone, CO.
66. Zavaliagkos, G., Schwartz, R., Makhoul, J., 1995a. Batch, incremental and instantaneous adaptation techniques for speech recognition. In: Proc. ICASSP-95. Detroit, pp. 676-679.
67. Zavaliagkos, G., Schwartz, R., McDonough, J., Makhoul, J., 1995b. Adaptation algorithms for large scale HMM recognizers, In: Proc. Eurospeech-95. Madrid, Spain, pp. 1131-1134.
68. Zhao, Y.-X., 1994. An acoustic-phonetic based speaker adaptation technique for improving speaker independent continuous speech recognition. IEEE Trans. Speech Audio Process. 2 (3), 380-394.
69. Zhao, Y.-X., 1996. Self-learning speaker and channel adaptation based on spectral variation source decomposition. Speech Communication 18, 65-77.