Acoustic model adaptation for speech recognition

IEICE Transactions on Information and Systems

Volumn E93-D, Issue 9, 2010, Pages 2348-2362

  Shinoda, Koichi ^a  

^a TOKYO INSTITUTE OF TECHNOLOGY   (Japan)

Author keywords

Acoustic model adaptation; Hidden Markov models; Speech recognition

Indexed keywords

DEEP NEURAL NETWORKS; HIDDEN MARKOV MODELS; MARKOV PROCESSES; MAXIMUM LIKELIHOOD; MAXIMUM LIKELIHOOD ESTIMATION;

ACOUSTIC MODEL ADAPTATION; ADAPTATION TECHNIQUES; CONTINUOUS DENSITY HIDDEN MARKOV MODELS; INPUT DATAS; MAXIMUM A POSTERIORI ESTIMATION; MAXIMUM LIKELIHOOD LINEAR REGRESSION; RECOGNITION ACCURACY; TRAINING DATA;

SPEECH RECOGNITION;

EID: 77956865237     PISSN: 09168532     EISSN: 17451361     Source Type: Journal    
DOI: 10.1587/transinf.E93.D.2348     Document Type: Article

References (104)

1. T. Anastasakos, J. McDonough, R. Schwartz, and J. Makhoul, "A compact model for speaker-adaptive training," Proc. ICSLP96, vol.2, FrP2L1.3, 1996.
2. B. Atal, "Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification," J. Acoust. Soc. Am., vol.55, pp.1304-1312, 1974.
3. J.R. Bellegarda, "Statistical language model adaptation: Review and perspectives," Speech Commun., vol.42, no.1, pp.93-108, 2004.
4. C. Cerisara, L. Rigazio, and J.C. Janqua, "α-Jacobian environmental adaptation," Speech Commun., vol.42, no.1, pp.25-41, 2004.
5. K. Chen, W. Liau, H. Wang, and L. Lee, "Fast speaker adaptation using Eigenspace-based maximum likelihood linear regression," Proc. ICSLP-2000, 2000.
6. C. Chesta, O. Siohan, and C.-H. Lee, "Maximum a posteriori linear regression for hidden Markov model adaptation," Proc. EuroSpeech99, pp.211-214, 1999.
7. J.-T. Chien, C.-H. Lee, and H.-C. Wang, "Improved Bayesian learning of hidden Markov models for speaker adaptation," Proc. ICASSP-97, pp.1027-1039, 1997.
8. J.-T. Chien, "Quasi-Bayes linear regression for sequential learning of hidden Markov models," IEEE Trans. Speech Audio Process., vol.10, no.4, pp.268-278, 2002.
9. W. Chou, "Maximum a posteriori linear regression with ellipticallysymmetric matrix variance priors," Proc. Eurospeech-99, vol.1, pp.1-4, 1999.
10. S. Cox, "Predictive speaker adaptation in speech recognition," Comput. Speech Lang., vol.9, pp.1-17, 1995.
11. X. Cui and A. Alwan, "Efficient adaptation text design based on the Kullback-Leibler measure," Proc. ICASSP-2002, pp.I-613-616, 2002.
12. X. Cui and A. Alwan, "Robust speaker adaptation by weighted model averaging based on the minimum description length criterion," IEEE Trans. Audio, Speech, and Language Processing, vol.15, no.2, pp.652-660, 2007.
13. M.H. DeGroot, Statistical Decision Theory and Bayesian Analysis, McGraw-Hill, 1970.
14. V.V. Digalakis, D. Rtishev, and L.G. Neumeyer, "Speaker adaptation using constrained estimation of Gaussian mixtures," IEEE Trans. Speech Audio Process., vol.3, no.5, pp.357-366, 1995.
15. V.V. Digalakis and L.G. Neumeyer, "Speaker adaptation using combined transformation and Bayesian methods," IEEE Trans. Speech Audio Process., vol.4, no.4, pp.294-300, 1996.
16. J. Duchateau, T. Leroy, K. Demuynck, and H. Van homme, "Fast speaker adaptation using non-negative matrix factorization," ICASSP '08, pp.4269-4272, 2008.
17. E. Eide and H. Gish, "A parametric approach to vocal tract length normalization," Proc. ICASSP96, vol.1, pp.346-3483, 1996.
18. T. Emori and K. Shinoda, "Rapid vocal tract length normalization using maximum likelihood estimation," Proc. Eurospeech-2001, pp.1649-1652, 2001.
19. S. Furui, "A training procedure for isolated word recognition systems," IEEE Trans. Acoust. Speech Signal Process., vol.ASSP-28, no.2, pp.129-136, 1980.
20. S. Furui, "Unsupervised speaker adaptation method based on hierarchical spectral clustering," Proc. ICASSP-89, pp.286-289, Glasgow, 1989. (Pubitemid 20604111)
21. S. Furui, "Generalization Problem in ASR Acoustic Model Training and Adaptation," IEEE ASRU Workshop, Merano, pp.1-10, 2009.
22. M.J.F. Gales and P.C. Woodland, "Mean and covariance adaptation within MLLR framework," Comput. Speech Lang., vol.10, pp.249-264, 1996.
23. M.J.F. Gales, "Maximum likelihood linear transformations for HMM-based speech recognition," Comput. Speech Lang., vol.12, pp.75-98, 1998.
24. M.J.F. Gales, "Cluster adaptive training for hidden Markov models," IEEE Trans. Audio and Speech Processing, vol.8, no.4, pp.417-428, 2000.
25. J.-L. Gauvain and C.-H. Lee, "Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains," IEEE Trans. Speech Audio Process., vol.2, no.2, pp.291-298, April 1994.
26. R. Gomez, T. Toda, H. Saruwatari, and K. Shikano, "Techniques in rapid unsupervised speaker adaptation based on HMM-sufficient statistics," Speech Commun., vol.51, pp.42-57, 2004.
27. S. Hahm, A. Ito, S. Makino, and M. Suzuki, "A fast speaker adaptation method using aspect model," Interspeech '08, pp.1221-1224, 2008.
28. T.J. Hazen, "A comparison of novel techniques for rapid speaker adaptation," Speech Commun., vol.31, pp.15-33, 2000.
29. C. Huang, T. Chen, S. Li, E. Chang, and J. Zhou, "Analysis of speaker variability," EuroSpeech-2001, 2001.
30. Q. Huo and C. Chan, "Bayesian adaptive training of the parameters of hidden Markov model for speech recognition," IEEE Trans. Speech Audio Process., vol.3, no.5, pp.334-345, 1995.
31. 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. Audio and Speech Processing, vol.5, no.2, pp.161-172, March 1997.
32. Q. Huo and C.-H. Lee, "On-line adaptive learning of the corre-lated continuous-density hidden Markov model for speech recognition," IEEE Trans. Speech Audio Process., vol.6, no.4, pp.386-397, 1998.
33. A. Kannan and M. Ostendorf, "Modeling dependency in adaptation of acoustic models using multiscale tree processes," Proc. EuroSpeech-97, pp.1863-1866, 1997.
34. P. Kenny, G. Boulianne, and P. Dumouchel, "Bayesian adaptation revisited," Workshop ISCAITRW ASR2000, pp.112-119, 2000.
35. P. Kenny, G. Boulianne, and P. Dumouchel, "Inter-speaker correlations, intra-speaker correlations and Bayesian adaptation," Proc. Isca ITR-Workshop2001, Sophia-Antipolis, 2001.
36. P. Kenny, G. Boulianne, and P. Dumouchel, "What is the best type of prior distribution for EMAP speaker adaptation," EuroSpeech-2001,pp.1207- 1210, 2001.
37. P. Kenny, G. Boulianne, and P. Dumouchel, "Eigenvoice modeling with sparse training data," IEEE Trans. Speech Audio Process., vol.13, no.3, pp.345-354, 2005.
38. D.K. Kim and N.S. Kim, "Maximum a posteriori adaptation of HMM parameters based on probabilistic component analysis," Proc. ISCA ITR-Workshop 2001, pp.25-28, 2001.
39. D.K. Kim and N.S. Kim, "Maximum a posteriori adaptation of HMM parameters based on speaker space projection," Speech Commun., vol.42, pp.59-73, 2004.
40. D.K. Kim and N.S. Kim, "Rapid online adaptation based on transformation space model evolution," IEEE Trans. Speech Audio Process., vol.13, no.2, pp.194-202, 2005.
41. M. Kirby and L. Sirovich, "Application of the Karhunen-Lo'eve procedure for the characterization of human faces," IEEE Trans. Pattern Anal. Mach. Intell., vol.12, no.1, pp.103-108, 1990.
42. T. Kosaka and S. Sagayama, "Tree-structured speaker clustering for fast speaker adaptation," ICASSP-94, vol.1, pp.245-248, Adelaide, 1994.
43. R. Kuhn, P. Nguyen, J.-C. Janqua, L. Goldwasser, N. Niedzielski, S. Finke, K. Field, and M. Contolini, "Eigenvoices for speaker adaptation," Proc. ICSLP-98, pp.1771-1774, 1998.
44. R. Kuhn, J.-C. Janqua, R. Boman, N. Niedzielski, S. Fincke, K. Field, and M. Contolini, "Fast speaker adaptation using a priori knowledge," Proc. ICASSP-99, 2001.
45. R. Kuhn, J.-C. Janqua, P. Nguyen, and N. Niedzielski, "Rapid speaker adaptation in Eigenvoice space robust speech recognition," IEEE Trans. Speech Audio Process., vol.8, no.6, pp.695-707, 2000.
46. M.J. Lasry and R.M. Stern, "A posteriori estimation of correlated jointly Gaussian mean vectors," IEEE Trans. Pattern Anal. Mach. Intell., vol.6, no.4., pp.530-535, 1984.
47. 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 Process., vol.39, no.4, pp.806-814, April 1991.
48. L. Lee and R.C. Rose, "Speaker normalization using efficient frequency warping procedures," Proc. ICASSP96, vol.1, pp.353-356, 1996.
49. C.-H. Lee and Q. Huo, "On adaptive decision rules and decision parameter adaptation for automatic speech recognition," Proc. IEEE, vol.88, pp.1241-1269, 2000.
50. 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.
51. J. Li, L. Deng, D. Yu, Y. Gong, and A. Acero, "A unified framework of HMM adaptation with joint compensation of additive and convolutive distortions," Comput. Speech Lang., vol.23, pp.389-405, 2009.
52. J. Loof, C. Gollan, and H. Ney, "Speaker adaptive training using Shift-MLLR," Proc. Interspeech2008, pp.1701-1704, Brisbane, 2008.
53. B. Mak, J.T. Kwak, and S. Ho, "Kernel eigenvoice speaker adaptation," IEEE Trans. Audio, Speech, and Language Processing, vol.13, no.5, pp.984-992, 2005.
54. B.K.-W. Mak, R.W.-H. Hsiao, S.K.-L. Ho, and J.T. Kwak, "Embedded kernel eigenvoice speaker adaptation and its implication to reference speaker weighting," IEEE Trans. Audio, Speech, and Language Processing, vol.14, no.4, pp.1267-1280, 2006.
55. B.K.-W. Mak, T.-C. Lai, I.W. Tsang, and J.T.-Y. Kwak, "Maximum penalized likelihood kernel regression for fast adaptation," IEEE Trans. Audio, Speech, and Language Processing, vol.17, no.7, pp.1372-1381, 2006.
56. A. Mandal, M. Ostendorf, and A. Stolcke, "Improving robustness of MLLR adaptation with speaker-clustered regression class trees," Comput. Speech Lang., vol.23, pp.176-199, 2009.
57. T. Matsui and S. Furui, "N-best-based unsupervised speaker adaptation for speech recognition," Comput. Speech Lang., vol.12, pp.41-50, 1998.
58. J. McDonough, T. Schaaf, and A. Waibel, "Speaker adaptation with all-pass transforms," Speech Commun., vol.42, pp.75-91, 2004.
59. P.J. Moreno, B. Raj, and R.M. Stern, "A vector Taylor series approach for environment-independent speech recognition," Proc. ICASSP '96, pp.733-736, 1996.
60. H. Murakami, K. Shinoda, and S. Furui, "Speaker adaptation based on two-step active learning," Interspeech '09, pp.576-579, 2009.
61. N. Nishida and Y. Ariki, "Speaker recognition by separating phonetic space and speaker space," Proc. Eurospeech-2001, 2001.
62. P. Nguyen, C. Wellekens, and J.-C. Janqua, "Maximum likelihood eigenspace and MLLR for speech recognition in noisy environment," Proc. Eurospeech-99, pp.2519-2522, 1999.
63. P. Nguyen, L. Rigazio, C. Wellekens, and J.C. Junqua, "LU factorization for feature transformation," Proc. ICSLP-2002, pp.73-76, 2001.
64. K. Ohkura, M. Sugiyama, and S. Sagayama, "Speaker adaptation based on transfer vector field smoothing with continuous mixture density HMMs," Proc. ICSLP '92, pp.369-372, 2002.
65. Y. Onishi and K. Iso, "Speaker adaptation by hierarchical eigen- voice," Proc. of ICASSP-2003, pp.1576-1579, 2003.
66. 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 Process., vol.6, no.1, pp.71-77, 1998.
67. M. Padmanabhan, G. Saon, and G. Zweig, "Lattice-based unsuper- vised MLLR for speaker adaptation," Proc. ISCA ITR-Workshop 2000, pp.128-131, 2000.
68. M. Padmanabhan and S. Dharanipragada, "Maximum-likelihood nonlinear transformation for acoustic adaptation," IEEE Trans. Speech Audio Process., vol.12, no.6, pp.572-578, 2004.
69. D.B. Pisoni, R.H. Bernacki, H.C. Nusbaum, and M. Yuchtman, "Some acoustic-phonetic correlates of speech produced in noise," Proc. ICASSP, pp.1581-1584, 1985.
70. M. Pitz, S. Molau, R. Schluter, and H. Ney, "Vocal tract normalization equals linear transformation in cepstral space," Proc. Eurospeech-2001, 2001.
71. D. Pye and P.C. Woodland, "Experiments in speaker normalization and adaptation for large vocabulary speech recognition," Proc. ICASSP97, vol.2, pp.1047-1050, 1997.
72. M. Rahim and B.-H. Juang, "Signal bias removal by maximum likelihood estimation for robust telephone speech recognition," IEEE Trans. Speech Audio Process., vol.4, no.1, pp.19-30, 1996.
73. S. Sagayama, Y. Yamaguchi, S. Takahashi, and J. Takahashi, "Jacobian approach to fast acoustic model adaptation," Proc. ICASSP '97, pp.835-838, 1997.
74. S. Sagayama, K. Shinoda, M. Nakai, and H. Shimodaira, "Analytic methods for acoustic model adaptation: A review," ISCA ITR-Workshop, pp.67-76, Sophia-Antiplois, 2001.
75. A. Sankar and C-.H. Lee, "A maximum likelihood approach to stochastic matching for robust speech recognition," IEEE Trans. Speech Audio Process., vol.4, no.3, pp.190-202, 1996.
76. B.M. Shahshahani, "A Markov random field approach to Bayesian speaker adaptation," IEEE Trans. Speech Audio Process., vol.5, no.2, pp.183-191, 1997.
77. K. Shinoda, K. Iso, and T. Watanabe, "Speaker adaptation for demi-syllable-based continuous-density HMM," Proc. ICASSP- 91, pp.857-860, Toronto, 1991.
78. K. Shinoda and T. Watanabe, "Speaker adaptation with autonomous control using tree structure," Proc. EuroSpeech-95, pp.1143-1146, 1995.
79. K. Shinoda and T. Watanabe, "Speaker adaptation with autonomous model complexity control by MDL principle," Proc. ICASSP '96, pp.717-720, Atlanta, 1996.
80. K. Shinoda and C.-H. Lee, "Structural MAP speaker adaptation using hierarchical priors," Proc. IEEE Workshop on Speech Recognition and Understanding, 1997.
81. K. Shinoda and C.-H. Lee, "A structural Bayes approach to speaker adaptation," IEEE Trans. Speech Audio Process., vol.9, no.3, pp.276-287, 2001.
82. T. Shinozaki, Y. Kubota, and S. Furui, "Unsupervised cross- validation adaptation algorithms for Improved adaptation performance," Proc. ICASSP '09, pp.4377-4380, 2009.
83. O. Siohan, T.-A. Myrvoll, and C.-H. Lee, "Structural maximum a posteriori linear regression for fast HMM adaptation," Workshop ISCA ITRW ASR2000, 2000.
84. R.M. Stern and M.J. Lasry, "Dynamic speaker adaptation for feature-based isolated word recognition," IEEE Trans. Audio Speech Process., vol.35, no.6, pp.751-763, 1987.
85. A.C. Surendran, M. Rahim, and C.-H. Lee, "Non-linear compensation for stochastic matching," IEEE Trans. Audio Speech Process., vol.6, no.7, pp.643-655, 1999.
86. A.C. Surendran and C.-H. Lee, "Transformation-based Bayesian prediction for adaptation of HMMs," Speech Commun., vol.34, pp.159-174, 2001.
87. Y. Tang and R. Rose, "Rapid speaker adaptation using clustered maximum-likelihood linear basis with sparse training data," IEEE Trans. Audio, Speech, and Language Processing, vol.16, no.3, pp.607-616, 2008.
88. S. Tanji, K. Shinoda, S. Furui, and A. Ortega, "Improvement of Eigenvoice-based speaker adaptation by parameter space clustering," Proc. Interspeech '08, pp.1229-1232, 2008.
89. S. Tsakalidis, V. Doumpiotis, and W. Byrne, "Discriminative linear transforms for feature normalization and speaker adaptation in HMM estimation," IEEE Trans. Audio, Speech, and Language Processing, vol.13, no.3, pp.367-376, 2005.
90. Y. Tsao, S.-M. Lee, and L.-S. Lee, "Segmental eigenvoice with delicate eigenspace for improved speaker adaptation," IEEE Trans. Audio, Speech, and Language Processing, vol.13, no.3, pp.399-411, 2005.
91. M. Tonomura, T. Kosaka, and S. Matsunaga, "Speaker adaptation based on transfer vector field smoothing using maximum a posteriori probability estimation," ICASSP-95, vol.1, pp.688-691, Detroit, 1995.
92. L. Wang and P.C. Woodland, "MPE-based discriminative linear transforms for speaker adaptation," Comput. Speech Lang., vol.22, pp.256-272, 2008.
93. S. Watanabe and A. Nakamura, "A unified interpretation of adaptation techniques based on a macroscopic time evolution system with indirect/direct approaches," Proc. ICASSP '08, pp.4285-4288, 2008.
94. P.C. Woodland, "Speaker adaptation for continuous density HMMs: A review," ISCA ITR-Workshop, pp.11-19, Sophia-Antipolis, 2001.
95. J. Wu and Q. Huo, "A study of minimum classification error (MCE) linear regression for supervised adaptation of MCE-trained continuous-density hidden Markov models," IEEE Trans. Audio, Speech, and Language Processing, vol.15, no.2, pp.478-488, 2007.
96. S. Yoshizawa, A. Baba, K. Matsunami, Y. Mera, M. Yamada, and K. Shikano, "Unsupervised speaker adaptation based on the sufficient HMM statistics of selected speakers," Proc. ICASSP2001, 2001.
97. K. Yu, M. Gales, and P.C. Woodland, "Unsupervised adaptation with discriminative mapping transforms," IEEE Trans. Audio, Speech, and Language Processing, vol.17, no.4, pp.714-723, 2009.
98. K. Yu and M.J.F. Gales, "Bayesian adaptive inference and adaptive training," IEEE Trans. Audio, Speech, and Language Processing, vol.15, no.6, pp.1932-1943, 2007.
99. K. Yu and M. Gales, "Discriminative cluster adaptive training," IEEE Trans. Audio, Speech, and Language Processing, vol.14, no.5, pp.1694-1703, 2006.
100. P. Zhan and M. Westohal, "Speaker normalization based on frequency warping," Proc. ICASSP97, pp.1039-1042, 1997.
101. G. Zavaliagkos, R. Schwartz, and J. Makhoul, "Batch, incremental and instantaneous adaptation techniques for speech recognition," Proc. ICASSP-95, pp.676-679, Detroit, May 1995.
102. G. Zavaliagkos, "Maximum a posteriori adaptation for large-scale HMM recognizers," Proc. ICASSP-96, pp.725-728, Detroit, May 1995.
103. Z. Zhang and S. Furui, "Piecewise-linear transformation-based HMM adaptation for noisy speech," Speech Commun., vol.42, pp.43-58, 2004.
104. B. Zhou and J.H.L. Hansen, "A novel algorithm for rapid speaker adaptation based on structural maximum likelihood eigenspace mapping," Proc. Eurospeech-2001, pp.1215-1218, Aalborg, 2001.