Speaker Adaptation Using Constrained Transformation

IEEE Transactions on Speech and Audio Processing

Volumn 12, Issue 2, 2004, Pages 168-174

  Wu, Xintian ^a   Yan, Yonghong ^a  

^a INTEL CORPORATION   (United States)

Author keywords

Dependency modeling; Knowledge constraints; Markov random field; MLLR; Speaker adaptation

Indexed keywords

ACOUSTIC NOISE; ADAPTIVE ALGORITHMS; HUMAN COMPUTER INTERACTION; MARKOV PROCESSES; MATHEMATICAL MODELS; PROBLEM SOLVING; REGRESSION ANALYSIS;

DEPENDENCY MODELING; KNOWLEDGE CONSTRAINTS; MARKOV RANDOM FIELD; MLLR; SPEAKER ADAPTATION;

SPEECH RECOGNITION;

EID: 2142715607     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/TSA.2003.818029     Document Type: Article

References (22)

1. V. Nagesha and L. Gillick, "Studies in transformation-based adaptation," in Proc. 1997 Int. Conf. Acoustics, Speech, Signal Processing, vol. 2, 1997, pp. 1031-1034.
2. S. Nakamura and K. Shikano, "A comparative study of spectral mapping for speaker adaptation," in Proc. 1990 Int. Conf. Acoustics, Speech, Signal Processing, 1990, pp. 157-160.
3. C. J. Leggetter and P. C. Woodland, "Maximum likelihood linear regression for speaker adaptation of HMMs," Comput. Speech Lang., vol. 9, pp. 171-186, 1995.
4. V. Abrash, A. Sankar, H. Franco, and M. Cohen, "Speaker adaptation using nonlinear transformations of HMM parameters," in Proc. 1996 Int. Conf. Acoustics, Speech, Signal Processing, vol. 2, 1996, pp. 729-732.
5. C. J. Leggetter and P. C. Woodland, "Speaker Adaptation Using Linear Regression," Cambridge University Engineering Department, Tech. Rep. CUED/F-INFENG/TR.181, 1994.
6. 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, 1991.
7. 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, 1994.
8. J.-T. Chien, C.-H. Lee, and H. H. Wang, "Improved Bayesian learning of hidden Markov models for speaker adaptation," in Proc. 1997 Int. Conf. Acoustics, Speech, Signal Processing, vol. 2, 1997, pp. 1027-1030.
9. E. Bocchieri, V. Digalakis, A. Corduneanu, and C. Boulis, "Correlation modeling of MLLR transform biases for rapid HMM adaptation to new speakers," in Proc. 1999 Int. Conf. Acoustics, Speech, Signal Processing, vol. 2, 1999, pp. 773-776.
10. V. Digalakis, S. Berkowitz, E. Bocchieri, C. Boulis, W. Byrne, H. Collier, A. Corduneanu, A. Kannan, S. Khudanpur, and A. Sankar, "Rapid speech recognizer adaptation to new speakers," in Proc. 1999 Int. Conf. Acoustics, Speech, Signal Processing, vol. 2, 1999, pp. 765-768.
11. B. M. Shahshahani, "A Markov Random Field Approach to Bayesian Speaker Adaptation,", IBM Tech. Rep. TR54.885, Jan. 1995.
12. M. Gales and P. Woodland, "Variance Compensation Within the MLLR Frame Work," Cambridge University Engineering Department, Tech. Rep. CUED/F-INFENG/TR.242, Feb. 1996.
13. M. J. F. Gales, "The Generation and Use of Regression Class Trees for MLLR Adaptation," Cambridge Univ. Eng. Dept., Tech. Rep. CUED/F-INFENG/TR.263, Aug. 1996.
14. R. L. Dobrushin, "The description of a Random field by means of conditional probabilities and conditions of its regularity," Theory Prob. Applicat., vol. 13, pp. 197-224, 1968.
15. B. M. Shahshahani, "A Markov random field approach to Bayesian speaker adaptation," in Proc. 1996 Int. Conf. Acoustics, Speech, Signal Processing, vol. 2, 1996, pp. 697-700.
16. _, "A Markov random field approach to Bayesian speaker adaptation," IEEE Trans. Speech Audio Processing, vol. 5, pp. 183-191, 1997.
17. J. Besag, "Spatial interaction and the statistical analysis of lattice systems," J. R. Statist. Soc., vol. 36, pp. 192-236, 1974.
18. R. Chellappa and R. L. Kashyap, "Digital image restoration using spatial interaction models," IEEE Trans. Acoust., Speech, Signal Processing, vol. 1, pp. 461-472, 1982.
19. F. Spitzer, "Markov random fields and Gibbs ensembles," Amer. Math. Monthly, vol. 78, pp. 142-154, 1971.
20. M. Hassner and J. Sklansky, "The use of Markov random fields as models of texture," Comput. Graph. Image Process., vol. 12, pp. 357-370, 1980.
21. W. H. Press, B. P. Flannery, S. A. Teukolsky, and W. T. Vetterling, Numerical Recipes in C. Cambridge, U.K.: Cambridge Univ. Press, 1990.
22. X. Wu, C. Liu, Y. Yan, D. Kim, S. Cameron, and R. Parr, "The 1998 OGI-FONIX broadcast news transcription system," in Proc. Broadcast News Transcription and Understanding Workshop, 1999.