On adaptive decision rules and decision parameter adaptation for automatic speech recognition

Proceedings of the IEEE

Volumn 88, Issue 8, 2000, Pages 1241-1268

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

^a LUCENT TECHNOLOGIES   (United States)

^b UNIVERSITY OF HONG KONG   (Hong Kong)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 0000159105     PISSN: 00189219     EISSN: None     Source Type: Journal    
DOI: 10.1109/5.880082     Document Type: Article

References (182)

1. A. Acero, Acoustical and Environmental Robustness in Automatic Speech Recognition. Norwell, MA: Kluwer, S 993.
2. S. M. Ahadi and P. C. Woodland, "Combined Bayesian and predictive techniques for rapid speaker adaptation of continuous density hidden Markov models,'" Cjinpnt. Speech. Lung., vol. 11, pp.187-206, 1997.
3. J. Aitchison and I. R. Dunsmore, Statistical Prediction Analysis. Cambridge, U.K.: Cambridge Univ. Press, 1975.
4. S. Amari, "A theory of adaptive pattern classifiers,"IEEE Trans. Electron. Comput., vol. EC-16, no. 3, pp.299-307, 1967.
5. T. Aaastasakos, J. McDonough, R. Schwartz, and J. Makhoul, "A compact model for speaker adaptive training,"InProc. ICSLP-96, Philadelphia, PA, 1996, pp.1137-1140.
6. B. S. Atal, "Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification," J. Acous!. Soc. Amer., vol. 55, no. 6, pp.1304-13;2, 1974.
7. L. R. Bah!, F. Jelinek, and R. L. Mercer, "A maximum likelihood approach to continuous speech recognition,"IEEE Trans. Pattern Anal. Machine lute!!., vol. PAMI-5, no. 2r pp.179-190, 1983.
8. L. R. Bahl, P. F. Brown, P. V. De Souza, und R. L. Mercer, "Maximum mutual information estimation of hidden Markov model parameters for speech recognition,"InProc. ICASSP-86, Tokyo, japan. 1986, pp.49-52.
9. _, "Tree-based language model for natural language speech recognition,"IEEE Trans. ACùUS!., Speech. Signa! Processing, vol. 37, pp.1001-1008, July 1989.
10. L. R. Bahl, P. V. De Souza, P. S. Gopalakrtshnan, and M. A. Picheny, "Context dependent vector quantization for continuous speech recognition,"InProc. 1CASSP-93, Minneapolis, MN, 1993, pp.II-632-II-635.
11. L. R. Bahl, P. F. Brown, P. V. De Souza, and R. L. Mercer, "Estimating hidden Markov model parameters so as to maximize speech recognition accuracy,"IEEE Trans. Speech Audio Processing, vol. l.no. i.pp.77-83, 1993.
12. J. K. Baker, "Stochastic modeling for automatic speech understanding,"InSpeech Recognition, D. R. Ready. Ed. New York: Academic, 1975, pp.521-542.
13. _, "The Dragon system-An overview,"IEEE Trans. Acousi., Speech, Signal Processing, vol. ASSP-23, pp.24-29, Jan. 1975.
14. L. E. Baum. T. Pétrie, G. Soûles, and N. Weiss, "A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains," Math. Statist., vol. 41, pp.164-171, 1970.
15. 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.
16. J. B. Beliegarda and D. Nahamoo. "Tied mixture continuous parameter modeling for speech recognition,"Ir'.EE Iran:;. Acf,u:,L, Speed'., Signal Pmcessinj, vol. 38, pp.2033-2045, Dec 1990.
17. J. R. Bellegarua, P. V. Do Souza, A. J. Nadas, D. Nahamoo, vI. A. Pichenv and L. R. Bahl, "The metamorphic algorithm: A speaker mapping approach 10 data augmentation,"IEKE Tranx. Speed', Audio Processing, vol. 2, pp.413-420, July 1994.
18. J. R. Bellegarda, "A multispan statistical language modeling for large vocabulary speech récognition,"IEEE Trans. Speech Audio Processing, vol. 6, pp.456-467, Sept. 1998.
19. _, "Exploiting latent semantic information in statistical language modeling," Proc. IEEE, vol. 88, pp.1279-1296, Aug. 2000.
20. I. M. Bernardo and F. J. Giron. "A Bayesian analysis of simple mixture problems," \nBa\esiai Statistical, J. M. Bernardo, M. H. DeGroot.'u. V. Lindley, and A. F. M. Smith, Eds. Oxford, U.K.: Oxford Univ. Press, 1988, pp.67-78.
21. B. P. Carlin and T. A. Louis, Bayes and Empirical Bayes Methods for Data Analysis. London, U.K.: Chapman & Hall, 1996.
22. S. Chen and P. V. De Souza, "Speaker adaptation by correlation (ABC),"InProc. DARPA SI.T Workshop, 1997.
23. J.-T. Chien and H.-C. Wang, "Telephone speech recognition based on Bayesian adaptation of hidden Markov models," Speech Commun., vol. 22, pp.369-384, 1997.
24. J.-T. Chien, C.-H. Lee, and H.-C. Wang, "A hybrid algorithm for speaker adaptation using MAP transformation and adaptation,"IEEE Signal Processing Lett., vol. 4. pp.167-168, June 1997.
25. _, "Improved Bayesian learning of hidden Markov models for speaker adaptation,"InProc. ICASSP-97, Munich, Germany, 1997, pp.1027-1030.
26. J.-T. Chien, "On-line hierarchical transformation of hidden Markov models for speech recognition,"IEEE Trans. Speech Audi:) Processing, vol. 7, pp.656-667, Nov. 1999.
27. W. Chou, B.-H. Juaiig, and C.-H. Lee, "Segmentai GPD training of HMM based speech recognizer,"InProc. ICASSP-92, San Francisco, ÇA, 1992, pp.473-476.
28. W. Chou, C.-H. Lee, and B.-H. Juang, "Minimum error rate training based on the N-best string models,"InProc. ICASSP-93, Minneapolis, MM, 1993, pp.11-652-0-655.
29. _, "Minimum error rate training of inter-word context dependent acoustic model units in speech recognition,"InProc. 1CSLP-94, Yokohama, Japan, 1994, pp.439-442.
30. W. Chou, "Maximum posterior linear regression with elliptically symmetric matrix variate priors,"InProc. F.woSpeech-99, Budapest, Hungary, 1999, pp.1-4.
31. S. J. Cox and J. S. Bridle, "L'nsupervised speaker adaptation by probabilistic fitting,"InProc. 1CASSP-89, Glasgow, U.K., 1989, pp.294-297.
32. S. J. Cox, "Predictive speaker adaptation in speech recognition," Comput. Speech Ltmv., vol. 9, pp.1-17, 1995.
33. M. DeGrooi, Optima! Statistical Decisions. New York: McGrawHill, 1970.
34. J. S. A. Delia Pietra, v. J. Delia Pietra, R. L. Mercer, and S. Roukos, "Adaptive language modeling using minimum discriminant estimation,"InProc. ICASSP-92, San Francisco, ÇA, 1992, pp.633-636.
35. L. Delphin-Poulat, C. Vlokbel, and J. Idier, "Frame-synchronous stochastic matching based on the Kullbuck-Leibler information,"InProc. 1CASSP-98, Seattle, WA, 1998, pp.S9-92.
36. R. De Mori, Ed., Spoken Dialogues with Computers. New York: Academic, 1998.
37. A. Dempster, N. Laird, and D. Rubin, "Maximum likelihood from incomplete data via the EM algorithm," J. Rov. Starisl. Soc. B, vol. 39, no. 1, pp.1-38, 1977.
38. L. Deng, "A dynamic feature based approach to the interface between phonology and phonetics for speech modeling and recognition," Speech Commun., vol. 24, no. 4, pp.299-323, 1998.
39. V. V. Digalakis, D. Ritchev, and L. Ci. Neumeyer, "Speaker adaptation using constrained estimation of Gaussian mixtures,"IEEE Trans. Speech Audio Pioeessing, vol. 3, pp.357-366, Sept. 1995.
40. V. V. Digalakis and L. G. Keumeyer, "Speaker adaptation using combined transformation and Bayesian methods,"IEEE Trans. Speech Audio Processing, vol. 4, pp.294-300, July 1996.
41. V. V. Digalakis, "Online adaptation of Hidden Markov models using incremental estimation algorithms."IEEE Trans. Speech Audio Processing, vol. 7, pp.253-261, May 1999.
42. R. O. Duda and P. E. Hart, Pattern Classification uiul Scene Annliis. New York: Wiley, 1973.
43. Y. Ephraim, A. Dembo, and L. R. Rabmer, "A minimum discrimination information approach for hidden Markov modeling,"IEEE Trans. Inform. Theory. vol. 35, pp.1001-1013, Sept. 1989.
44. Y. Ephraim and L. R. Rabiner, "On the relations between modeling approaches for speech recognition,"IEEE Trans. Inform. Theory, vol. 36, pp.372-380, Mar. 1990.
45. Y. Ephraim, "Statistical model based speech enhancement systems," Proc. IEEE, vol. 80, pp.S526-1555, Oct. 1992.
46. M. Federico, "Bayesian estimation method of A'-gram language model adaptation,"InProc. 1CSLP-96, Philadelphia. PA, 1996, pp.240-243.
47. J J. Ferguson, Ed., Hidden Markov Models for Speech. Princeton, KJ: IDA, 1980.
48. T. S. Ferguson, Maihematica! Statistics: A Decision Theoretic Approach. New York: Academic, 1967.
49. J S. Furui, "A training procedure for isolated word recognition systems,"IEEE Trans. Aeons'., Speech, Signal Processing, vol. ASSP-28, no. 2, pp.129-136, 1980.
50. _, "L'nsupervised speaker adaptation method based on hierarchical spectral clustering,"IEEE Trans. Acoust., Speech, Signal Processing. 37, pp.1923-1930, Dec. 1989.
51. M J. F. Gales and S. J. Young, "Robust speech recognition in additive and convolutionai noise using parallel model combination," Comput. Speech Lang., vol. 9, pp.289-307, 1995.
52. _, "Robust continuous speech recognition using parallel model combination,"IEEE Trans. Speech Audio Processing, vol. 4, pp.352-359, Sept. 1996.
53. M. J. F. Gales and P. C. Woodland, "Mean and variance adaptation within the MLLR Framework," Comput. Speech Lang., vol. 10, pp.249-264, 1996.
54. Y.-Q. Gao, M. Padtnanabhan, and M. A. Picheny, "Speaker adaptation based on pre-clustering training speakers,"InProc. EuroSpeech-97, Rhodes, Greece, 1997, pp.2091-2094.
55. J.-L. Gauvain and C.-H. Lee, "Bayesian learning tor hidden Markov models with Gaussian mixture state observation densities," Speech Commun., vol. 11, no. 2-3, pp.205-214, 1992.
56. _, "Maximum A posteriori estimation for multivariate Gaussian mixture observations of Markov chains,'1 IEEE Trans. Speech Audio Processing, vol. 2, pp.291-298, Apr. 1994.
57. S. Geisser, Predictive Inference: An Introduction. New York: Chapman & Hall, 1993.
58. J N. Click, "Sample-based classification procedures derived from density estimators,"J. Amer: Statist. Assoc., vol. 67,pp.116-122, 1972.
59. _, "Sample-based classification procedures related to empiric distributions,"IEEE Trans. Inform. Theory, vol. IT-22, pp.454-461, 1976.
60. I. J. Good, "The population frequencies species and the estimation of population parameters." Biometrika, vol. 40, pp.237-264, 1953.
61. Y. Gong, "Stochastic trajectory modeling and sentence searching for continuous speech recognition,"IEEE Trans. Speech Audio Processing, vol. 5, pp.33-44, Jan. 1997.
62. P. S. Gopalakrishnan, D. Kanevsky, A. Nadas, D. Nahamoo, and M. A. Picheny, "Decoder selection based on cross-entropies,"InProc. 1CASSP-SS, New York, 1988, pp.20-23.
63. A. K. Gupta and T. Varga. Ellipticalty Contoured Models in Stalistica. Norwell, MA: Kluwer, 1993.
64. J. D. Hamilton, "A quasi-Bayesian approach to estimating parameters for mixtures of normal distributions," J. Bus. Econ. Statist., vol. 9, no. L pp.27-39, 1991.
65. H. Hattori and S. Sagayama, "Vector field smoothing principle for speaker adaptation,"InProc. ICSLP-92, Banff, Alberta, Canada, 1992, pp.381-384.
66. H.-W. Hon, "Vocabulary-independent speech recognition: The VOCIND System," Ph.D. dissertation, School of Comput. Sei., Carnegie-Mellon Univ., Pittsburgh, PA, 1992.
67. X. Huang and M. A. Jack, "Semi-continuous hidden Markov models for speech signal," Comput. Speech Lang., vol. 3, no. 3, pp.239-251, 1989.
68. X. Huang and K.-F. Lee, "On speaker-independent speaker dependent and speaker-adaptive speech recognition,"IEEE Trans. Speech Audio Processing, vol. 1, pp.150-157, Apr. 1993.
69. 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, pp.334-345, Sept. 1995.
70. _, "On-line adaptation of the SCHMM parameters based on the segmental quabi-Bayes learning for speech recognition,'"IEEE Trans. Speech Audio Processing, vol. 4, pp.141-144, Mar. 1996.
71. Q. Huo and C.-H. Lee, "On-line adaptive learning of the continuous density hidden Markov model based on approximate recursive Bayes estimate,"IEEE Trans. Speech Audio Processing, vol. 5, pp.161-172, Mar. 1997.
72. _, "On-iine adaptive learning of the correlated continuous density hidden Markov models for speech recognition,"IEEE Trans. Speech Audio Processing, vol. 6, pp.386-397, July 1998.
73. Q. Huo and B. Via, ''On-line adaptive learning of CDHMM parameters based on multiple-stream prior evolution and posterior pooling,"InProc. EnroSpeerh-99. Budapest. Hungary, 1999, pp.2721-2724.
74. Q. HUO and C.-H. Lee, "A Bayesian predictive classification approach to robust speech recognition,"IEEE Trans. Speech Audio Processing, vol. 8, pp.200-204, Mar. 2000.
75. _, "Robust speech recognition based on adaptive classification and decision strategies," Speech Commun., to be published.
76. Q. Huo, N. Smith, and B. Ma, "Efficient ML training of CDHMM parameters based on prior evolution posterior intervention and feedback,"InProc. /CAW-2000, Turkey, to be published.
77. M.-Y. Hwang, "Subphonetic acoustic modeling for speaker-independent continuous speech recognition," Ph.D. dissertation, School of Comput. Sei., Caniegie-Mellon Univ., Pittsburgh, PA, 1993.
78. F. Jelinek, "Continuous speech recognition by statistical methods," Proc. IEEE, vol. 64, pp.532-556, Apr. 1976.
79. F. Jelinek, R. L. Mercer, and S. Roukos, "Principles of lexical language modeling for speech recognition,"InAdvances in Speech Signal Processing, S. Furui and M. M. Sondhi, Eds, New York: Marcel Dekker, 1991, pp.651-699.
80. F. Jelinek, B. Merialdo, S. Roukos, and M. Strauss, "A dynamic language model for speech recognition,"InProc. DARPA Speech and Natural Language Workshop, Pacific Grove, CA, 1991, pp.293-295.
81. (81]F. Jelinek, Statistical Method for Speech Recognition. Cambridge, MA: MIT Press, 1997.
82. H. Jiang, K. Hirose, and Q. Huo, "A rninimax search algorithm for CDHMM based robust continuous speech recognition,"InProc. ICSLP-98, Sydney, Australia, 1998, pp.11-389-11-392.
83. _, "Robust speech recognition based on a Bayesian prediction approach,"IEEE Trans. Speech Audio Processing, vol. 7, pp.426-440, July 1999.
84. _, "Improving Viterbi Bayesian predictive classification via sequential Bayesian learning in robust speech recognition," Speech Commun., vol. 28, no. 4, pp.313-326, 1999.
85. B.-H. Juang, S. E. Levinson, and M. M. Sondhi, "Maximum likelihood estimation for multivariate mixture observations of Markov chains,"IEEE Trans. Inform. Theory, vol. IT-32, no. 2, pp.307-309, 1986.
86. B.-H. Juang and L. R. Rabiner, "The segmentai A'-means algorithm for estimating parameters of hidden Markov models,"IEEE Trans. Acoust., Speech, Signal Processing, vol. 38, pp.1639-1641, Sept. 1990.
87. B.-H. Juang and S. Katagiri, "Discriminative learning for minimum error classification,"IEEE Trans. Signal Processing, vol. 40, pp.3043-3054, Dec. 1992.
88. B.-H. Juang, "Automatic speech recognition: problems progress & prospects," presented at the 1996 IEEE Workshop on Neural Networks For Signal Processing, Kyoto, Japan, 1996.
89. B.-H. Juang, W. Chou, and C.-H. Lee, "Minimum Classification Error Rate Methods for Speech Recognition,"IEEE Trans. Speech Audio Processing, vol. 5, pp.257-265, May 1997.
90. J.-C. Junqua and J.-P. Haton, Robustness in Automatic Speech Recognition: Fundamentals and Applications. Norwell, MA: Kluwer, 1996.
91. S. Katagiri, C.-H. Lee, B.-H. Juang, and T. Komori, "New discriminative training algorithms based on a generalized probabilistic descent method," presented at the Proc. IEEE-SP Workshop Neural Networks for Signal Processing, Princeton, NJ, 1991.
92. J S. Katagiri, B.-H. Juang, and C.-H. Lee, "Pattern recognition using a family of design algorithms based upon the generalized probabilistic descent method," Proc. IEEE, vol. 86, pp.2345-2373, Nov. 1998.
93. S. M. Katz, "Estimation of probabilities from sparse data for the language model component of a speech recognizer,"IEEE Trans. Acoust., Speech, Signa! Processing, vol. ASSP-35, pp.400-401, Mar. 1987.
94. R. Kneser, J. Peters, and D. Kiakow, "Language model adaptation using dynamic marginals,"InProc. EuroSpeech-97, Rhodes, Greece, 1997, pp.1971-1974.
95. Y. Kharin, Robustness in Statistical Pattern Recognition. Norwell, MA: Kluwer, 1996.
96. V. Krishnamurthy and J. B. Moore, "On-line estimation of Hidden Markov model parameters based on the Kullback-Leibler Information measure,"IEEE Trans. Signa! Processing, vol. 41, pp.2557-2573, Aug. 1993.
97. S. Kuliback. Information Theory ana Statistics. New York: Wiley, 1959.
98. R. Kühn and R. De Mori, "A cache-based natural language model for speech recognition,"IEEE Trans. Pattern Anul. Machine Inlell., vol. 12, pp.570-583, June 1990.
99. M. J. Lasry and R. M. Stern, "A posteriori estimation of correlated jointly Gaussian mean vectors,"IEEE Trans. Pattern Anal. Machine Intel!., vol. PAM1-6, pp.530-535, Apr. 1984.
100. R. Lau, R. Rosenficld, and S. Roukos, "Trigger-based language models. A maximum entropy approach."In Proc. ICASSP-93, Minneapolis, MM, 1993, pp.11-45-11-48.
101. C.-H. Lee, L. R. Rabiner, R. Pieraccini, and J. G. Wilpon, "Acoustic modeling for large vocabulary speech recognition," Compul. Speech Lang., vol. 4, pp.127-165, 1990.
102. 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.
103. C.-H. Lee and J.-L. Gauvain, "Speaker adaptation based on MAP estimation of HMM parameters,"InProc. ICASSP-93, Minneapolis, MN, 1993, pp.11-652-11-655.
104. C.-H. Lee, F.-K. Soong, and K.-K. Paliwal, Eds., Automatic Speech and Speaker Recognition: Advanced Topics. Norwell, MA: Kluwer, 1996.
105. C.-H. Lee, B.-H. Juang, W. Chou, and J. J. Molina-Perez, "A study on task-independent subword selection and modeling for speech recognition,"InProc. 1CSLP-96, Philadelphia, PA, 1996, pp.1816-1819.
106. C.-H. Lee, "On stochastic feature and model compensation approaches to robust speech recognition," Speech Commun., vol. 25, pp.29-47, 1998.
107. K.-R Lee, Automatic Speech Recognition-The Development of She SPH/NX-System. Norwell, MA: Kluwer, 1989.
108. L. Lee and R. C. Rose, "Speaker normalization using efficient frequency warping procedures,"InProc. 1CASSP-96, Atlanta, GA, 1996, pp.353-356.
109. C. J. Leggetter and P. C. Woodland, "Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models," Compul. Speech Lang., vol. v, pp.171-185, 1995.
110. _, "Flexible speaker adaptation using maximum likelihood linear regression,"InProc. ARPA SLS Technology Workshop, 1995, pp.110-115.
111. S. E. Levinson, "Structural methods in automatic speech recognition," Proc. IEEE, vol. 73, pp.1625-1650. 1985.
112. L. R. Liporace, "Maximum likelihood estimation for multivariate observations of Markov sources,"IEEE Trans. Inform. Theory, vol. IT-28, no. 5, pp.729-734, 1982.
113. C.-S. Liu, C.-H. Lee, W. Chou, A. E. Rosenberg, and B.-H. Juang, "A study on minimum error discriminative training for speaker recognition,"J. Acousi. Soc. Amer., vol. 97, no. I. pp.637-648, 1995.
114. F.-H. Liu, "Environment adaptation for robust speech recognition." Ph.D. dissertation. School of Comput. Sei. Carnegie-Mellon Univ., Pittsburgh, PA, 1994.
115. A. Ljolje, Y. Ephraim, and L. R. Rabiner, "Estimation of hidden Markov model parameters by minimizing empirical error rate,"InProc. ICASSP-9Ü, 1990, pp.709-712.
116. U. E. Makov and A. F. M. Smith, "A quasi-Bayes imsupervised learning procedure for priors,"IEEE Trans. Inform. Theory, vol. IT-23, no. 6, pp.761-764, 1977.
117. J. S. Maritz and T. Lwin, Empirical Bayes Methods, 2nd ed. New York: Chapman & Hall, 1989.
118. F. Martin, K. Shikano, and Y. Minami, "Recognition of noisy speech by composition of hidden Markov models,"InProc. EiimSpeech-93, Berlin, Germany, 1993, pp.1031-1034.
119. J. J. Martin, Bayesian Decision Problems and Markov Chains. New York: Wiley, 1967.
120. T. Matsuoka and C.-H. Lee, "A study of on-line Bayesian adaptation for HMM-based speech recognition,"In"roc. EuroSpeech-93, Berlin, Germany, 1993, pp.815-818.
121. N. Merhav and Y. Ephraim, "A Bayesian classification approach with application to speech recognition,"IEEE Tram. Signal Processing, vol. 39, pp.2157-2166, Oct. 1991.
122. N. Merhav and C.-H. Lee, "A mmiinax classification approach with application to robust speech recognition,"IEEE Trans. Speech Audio Processing, vol. 1, pp.90-100, Jan. 1993.
123. C. Mokbel and L. Delphin-Poulat, "A Unified framework for autoadaptive speech recognition,"InProc. Workshop Knbust Methods for Speech Recognition in Adverse Conditions, Tampere, Finland, 1999, pp.227-230.
124. S. Moon and J.-N. Hwang, "Robust speech recognition based on joint model and feature space optimization of hidden Markov models."IEEE Trans. ."Neural Networks, vol. 8, pp.194-204, Mar. 1997.
125. A. Nadas, "A decision theoretic formulation of a training problem in speech recognition and a comparison of training by unconditional versus conditional maximum likelihood."IEEE Trans. Acoiisi.. Speech, Signal Processing, voi. ASSP-31, pp.814-817, Apr. 1983.
126. _, "Optimal solution of a training problem in speech recognition,"IEEE Trans Acoitst., Speech. Siqnal Processing, vol. ASSP-33, pp.326-329, Jan. 1985.
127. A. Nadas, D. Nahamoo, and VI. A. Picheny, "On a Model-robust training method for speech recognition,"IEEE Trans. Acoust., Speech, Signal Processing, vol. 36, pp.1432-1436, Sept. 1988.
128. K. Ohkura, M. Sugiyama, and S. Sagayama, "Speaker adaptation based on transfer vector field smoothing with continuous mixture density HMMs,"InProc. ICSLP-92, Banff, Alberta, Canada, 1992, pp.369-372.
129. M. Ostendorf, v. V. Digalakis, and O. A. Kimhall, "From HMMs to segment models: A unified view of stochastic modeling for speech recognition,"IEEE Trans. Speech Audi;) Processing, vol. 4, pp.36CW78, Sept. 1996.
130. M. Padmanabhan, L. R. Bahl, D. Nahamoo, and M. A. Picheny, "Speaker Clustering and transformation for speaker adaptation in speech recognition systems,"IEEE Trans. Speech Audio Processing, vol. 6, pp.71-77, Jan. 1998.
131. P. Placeway, R. Schwanz, P. Fung, and L. Nguyen, "The estimation of powerful language models from small and large corpora,"InProc. 1CASSP-93, vol. 2, Minneapolis, MN, 1993, pp.33-36.
132. L. R. Rabiner, j. G. Wilpon, and B.-H. Juang, "A segmentai A'-means training procedure for connected word recognition," AT&T Tech. J., vol. 65, pp.21-31, 1986.
133. _, "A tutorial on hidden Markov models and selected applications in speech recognition,"Proc. IEEE, vol. 77. no. 2, pp.257-286, 1989.
134. L. R. Rabiner and B.-H. Juang, Fundamentals of Speech Recognition. Englewood Cliffs, \J: Prentice-Hall, 1993.
135. M. Raliim 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.
136. M. Rahim and C.-H. Lee, "Simultaneous feature and HMM design using string-based minimum classification error training criterion,"InProc. 1CSLP-96, Philadelphia, PA, 1996, pp.1820-1823.
137. M. Rahim, C.-H. Lee, and B.-H. Juang, "Discriminative utterance verification for connected digit recognition,"IEEE Trans, Speech Audio Processing, vol. 5, pp.266-277, May 1997.
138. C. Rathinavelu and L. Deng, "Use of generalized dynamic feature parameters for speech recognition: Maximum likelihood and minimum classification error approaches,"InProc. ICASSP-95, Detroit, MI, 1995, pp.373-376.
139. _, "Speaker adaptation experiments using nonstationary-state hidden Markov models: A MAP approach,"InProc. 1CASSP-97, Munich, Germany, 1997, pp.1415-1413.
140. W. Reichl, "Language model adaptation using minimum discrimination information,"InProc. EuroSpeech-99, Budapest, Hungary, 1999, pp.1791-1794.
141. R. A. Redner and H. F. Walker, "Mixture densities maximum likelihood and the EM algorithm," SlAblRev., vol. 26, no. 2, pp.195-239, 1984.
142. B. D. Ripley, Pattern Recognition and Neural Networks. Cambridge, U.K.: Cambridge Univ. Press, 1996.
143. H. Robbins, "The empirical Bayes approach to statistical decision problems." Math. Staust., vol. 35, pp.1-20. 1964.
144. R. C. Rose, E. M. Hol'itetter, and D. A. Reynolds, "Integrated models of speech and background with application to speaker identification in noise,"IEEE Trans. Speech Audio Processing, vol. 2, pp.245-257, Apr. 1994.
145. R. Rosenfeld, "Adaptive statistical language modeling: A maximum entropy approach," Ph.D. dissertation, School of Comput. Sei., Camegic-Mcllon Univ., Pittsburgh, PA, 1994.
146. _, "Two decades of statistical language modeling: Where do we go from here'?," Proc. IEEE. vol. 88, pp.1270-1278, Aug. 2000.
147. A. Sankar and C.-H. Lee, "A maximum likelihood approach to stochastic matching for robust speech recognition,"IEEE Trans. Speech Audio Processing, vol. 4, pp.190-202, May 1996.
148. R. Schwanz und F. Kubala, "Hidden Markov models and speaker adaptation."In Speech Recognition and Understanding-Recent Advances Trench und Applications, ser. NATO ASI F75, P. Laface and R. De Mon, Eds., 1991, pp.31-57.
149. B. M. Shahshahani, "A Markov random field approach to Bayesian speaker adaptation,"IEEE Trans. Speech Audio Processing, vol. 5, no. 2, pp.183-191, 1997.
150. K. Shinoda and T. Walanabe, "Speaker adaptation with autonomous model complexity control by MD1 principle,"InP roc. ICASSP-96, Atlanta, G A, 1996, pp.717-720.
151. K. Shinoda and C.-H. Lee, "Structural MAP speaker adaptation using hierarchical priors,"InProc. 1997 JEEE Workshop Automatic Speed; Recognition and Understanding, Santa Barbara, CA, 1997, pp.381-388.
152. _, "Unsupervised adaptation using structural Baves approach,"InProc. ICASSP-98, Seattle, WA, 1998, pp.793-796.
153. O. Siohan and C.-H. Lee, "Iterative Noise and channel estimation under the stochastic matching algorithm framework,"IEEE Signal Processing Lett., vol. 4, pp.304-306, Nov. 1997.
154. O. Siohan, C. Chesia, and C.-H. Lee, "Hidden Markov model adaptation using maximum a posteriori linear regression,"InProc. Workshop Robust Methods for Speech Recognition in Ac/verse Conditions. Tampere, Finland, 1999, pp.147-150.
155. _, "Joint maximum a posteriori adaptation of transformation and HMM parameters,"InProc. ICASSP-2000. Turkey, pp.965-968, to be published.
156. O, Siohan, T. A. Myrvoll, and C.-H. Lee, "Structural maximum a posteriori linear regression for fast HMM adaptation,", submitted for publication.
157. A. F. M. Smith and U. E. Makcv, "A quasi-Bayes sequential procedure for mixtures," Roy. Statist. Soc. J. B, vol. 40, no. 1, pp.106-112, 1978.
158. "Special issue on Robust speech recognition," Speech Communication, vol. 25, no. 1-3, 1998.
159. J. Spragins, "A note on the iterative application of Bayes' rule,"IEEE Trans. Inform. Theory, vol. IT-11, no. 4, pp.544-549, 1965.
160. R. M. Stern and M. J. Lasry. "Dynamic speaker adaptation for feature-based isolated word recognition,"IEEE Trans. Acoust., Speech, Signal Prot essing. vol. ASSP-35, pp.751-763, June 1937.
161. R. A. Sukkar and C.-H. Lee, "Vocabulary independent discriminative utterance verification for nonkeyword rejection in subword based speech recognition,"IEEE Irans. Speech Audio Processing, vol. 4, pp.420-429, Nov. 1996.
162. A.C. Surendran and C.-H. Lee, "Predictive adaptation and compensation for robust speech recognition,"InProc. ICSLP-98, Sydney, Australia, 1998.
163. _, "Bayesian predictive approach to adaptation of HMMs,"InProc. Workshop Robust Methods for Speech Recognition in Adverse Conditions, Tampere, Finland, 1999, pp.155-158.
164. A. C. Surendran, C.-H. Lee, and M. Rahirn, "Non-linear compensation for stochastic matching,"IEEE Trans. Speech Audio Processing, vol. 7, pp.643-655, Nov. 1999.
165. K. Takagi, H. Hattori, and T. Watanabe, "Speech recognition with rapid environment adaptation by spectrum equalization,"InProc. 1CSLP-94, Yokohama, Japan, 1994, pp.1023-1026.
166. J.-I. T'akahashi and S. Sagayama, "Vector-field-smoothed Bayesian learning for incremental speaker adaptation,"InProc. ICASSP-95, Detroit, MI, 1995, pp.696-699.
167. _, "Tied-Structure HMM based on parameter correlation for efficient model training,"InProc. ICASSP-96, Atlanta, GA, 1996, pp.467-670.
168. M. Tonomura, T. Kosaka, and S. Matsunaga, "Speaker adaptation based on transfer vector field smoothing using maximum a posteriori probability estimation,"InProc. ICASSP-95, Detroit, MI, 1995, pp.1-688-1-691.
169. S. Vascghi and B. Milner, "A comparative analysis of channel-robust features and channel equalization methods for speech recognition,"InProc. 1CSLP-96. Philadelphia, PA, 1996, pp.877-890.
170. A. Varga and R. Moore, "Hidden Markov model decomposition of speech and noise,"InProc. ICASSP-90, Albuquerque, NM, 1990, pp.845-848.
171. A. Wald, Statistical Decision Functions. New York: Wiley, 1950.
172. S. Wang and Y. Zhao, "On-line tree-structured transformation of hidden Markov models for speaker adaptation,"InPrat. 1999 IEEE Workshop Automatic Speech Recognition and Understanding, Keystone, 1999.
173. E. Weinstein, M. Feder, and A. V. Oppenheim, "Sequential algorithms for parameter estimation based on the Kullback-Leibler information measure,"IEEE Trans. Acoiisi, Speech, Signal Processing, vol. 38, pp.1652-1654, Sept. 1990.
174. P. C. Woodland, J. J. Odell, v. Valtchcv, and S. J. Young, "Large vocabulary continuous speech recognition using HTK,"InP roc. ICASSP-94, Adelaide, 1994. pp.II-125-II-128.
175. P. C. Woodland, D. Pye, and M. J. F. Gales. "Iterative unsupervised adaptation using maximum likelihood linear regression,"InProc. ICSLP-96, Philadelphia, PA, 1996, pp.1133-1136, submitted for publication.
176. _, "Speaker adaptation: Techniques and challenges,"InProc. 1999 IEEE Workshop Automatic Speech Récognition and Understanding, Keystone, 1999.
177. C. Yen, S.-S. Kuo, and C.-H. Lee, "Minimum error rate training for PHMM-based text recognition,"IEEE Trans. Image Processing, vol. 8, pp.1120-1124, Aug. 1999.
178. S. J. Young, J. i. Odell,-and P. C. Woodland, "Tree-based state tying for high accuracy acoustic modeling,"InProc. ARPA Human Language Technology Workshop, 1994, pp.307-312.
179. S. Young, j. Odell, D. Ollason, v. Valtchev, and P. Woodland, The HTK Hook {for HTK Version 2.1). Cambridge, U.K.: Cambridge Univ. Press, 1997.
180. [ISO]G. Zavaliagkos, R. Schwartz, and J. Makhoul, "Batch incremental and instantaneous adaptation techniques for speech recognition,"InProc. IC'ASSP-95, Detroit, MI, 1995, pp.I-676-I-679.
181. Y. Zhao, "An acoustic-phonetic-based speaker adaptation technique for improving speaker-independent continuous speech recognition,"IEEE Trans. Speech Audio Processing, vol. 2, pp.380-394, July 1994.
182. _, "Self-learning speaker and channel adaptation based on spectral variation source decomposition," Speech Commun., vol. 18, pp.65-77, 1996.