Mean and variance adaptation within the MLLR framework

Computer Speech and Language

Volumn 10, Issue 4, 1996, Pages 249-264

  Gales, M J F ^a   Woodland, P C ^a  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

ADAPTIVE ALGORITHMS; ESTIMATION; MARKOV PROCESSES; MATHEMATICAL MODELS; MATHEMATICAL TRANSFORMATIONS; PATTERN RECOGNITION SYSTEMS; REGRESSION ANALYSIS;

GAUSSIAN VARIANCES; MAXIMUM LIKELIHOOD LINEAR REGRESSION; SPEAKER INDEPENDENT RECOGNITION SYSTEMS; WORD ERROR RATE;

SPEECH RECOGNITION;

EID: 0030263447     PISSN: 08852308     EISSN: None     Source Type: Journal    
DOI: 10.1006/csla.1996.0013     Document Type: Article

References (23)

1. Dempster, A. P., Laird, N. M. & Rubin, D. B. (1977). Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society 39, 1-38.
2. Digalakis, V. V., Rtischev, D. & Neumeyer, L. G. (1995). Speaker adaptation using constrained estimation of Gaussian mixtures. IEEE Transactions on Speech and Audio Processing 3, 357-366.
3. Gales, M. J. F. (1996). Model-based techniques for noise robust speech recognition. Ph.D. Thesis, Cambridge University, Cambridge, U.K.
4. Gales, M. J. F. & Woodland, P. C. (1996). Variance compensation within the MLLR framework. Technical Report CUED/F-INFENG/TR242, Cambridge University, Cambridge, U.K. Available via anonymous ftp from: svr-ftp.eng.cam.ac.uk.
5. Gales, M. J. F. & Young, S. J. (1995a). A fast and flexible implementation of parallel model combination. Proceedings of the ICASSP 1, 133-136.
6. Gales, M. J. F. & Young, S. J. (1995e). Robust speech recognition in additive and convolutional noise using parallel model combination. Computer Speech and Language 9, 289-307.
7. Gauvain, J. L. & Lee, C. H. (1994). Maximum a-posteriori estimation for multivariate Gaussian mixture observations of Markov chains. IEEE Transactions on Speech and Audio Processing 2, 291-298.
8. Hewett, A. J. (1989). Training and speaker adaptation in template-based speech recognition. Ph.D. Thesis, Cambridge University, Cambridge, U.K.
9. Jaschul, J. (1982). Speaker adaptation by a linear transformation with optimized parameters. Proceedings of the ICASSP 3, 1657-1670.
10. Kenny, P., Lenning, M. & Mermelstein, P. (1990). Speaker adaptation in a large-vocabulary Gaussian HMM recogniser. IEEE Transactions on Pattern Analysis and Machine Intelligence 12, 917-920.
11. Lee, C. H., Lin, C. H. & Juang, B. H. (1990). A study of speaker adaptation of continuous density HMM parameters. Proceedings of the ICASSP 1, 145-148.
12. Leggetter, C. J. (1995). Improved acoustic modelling for HMMs using linear transformations. Ph.D. Thesis, Cambridge University, Cambridge, U.K.
13. Leggetter, C. J. & Woodland, P. C. (1994). Speaker adaptation of continuous density HMMs using linear regression. Proceedings of the ICSLP 2, 451-454.
14. Leggetter, C. J. & Woodland, P. C. (1995a). Flexible speaker adaptation for large vocabulary speech recognition. Proceedings of Eurospeech 2, 1155-1158.
15. Leggetter, C. J. & Woodland, P. C. (1995b). Maximum likelihood linear regression for speaker adaptation of continuous density HMMs. Computer Speech and Language 9, 171-186.
16. Neumeyer, L. R., Sankar, A. & Digalakis, V. V. (1995). A comparative study of speaker adaptation techniques. Proceedings of Eurospeech 2, 1127-1130.
17. Odell, J. J., Valtchev, V., Woodland, P. C. & Young, S. J. (1994). A one pass decoder design for large vocabulary recognition. In Proceedings of the ARPA Workshop on Human Language Technology, pp. 405-410.
18. Pallett, D. S., Fiscus, J. G., Fisher, W. M., Garofolo, J. S., Lund, B. A., Martin, A. & Przybocki, M. A. (1995). 1994 benchmark tests for the ARPA spoken language program. In Proceedings of the ARPA Workshop on Spoken Language Systems Technology, pp. 5-36.
19. Rose, R. C., Hofstetter, E. M. & Reynolds, D. A. (1994). Integrated models of signal and background with application to speaker identification in noise. IEEE Transactions on Speech and Audio Processing 2, 245-257.
20. Varga, A. P. & Moore, R. K. (1990). Hidden Markov model decomposition of speech and noise. Proceedings of the ICASSP 2, 845-848.
21. Woodland, P. C., Gales, M. J. F. & Pye, D. (1996). Improving environmental robustness in large vocabulary speech recognition. Proceedings of the ICASSP, 1, 65-68.
22. Woodland, P. C., Odell, J. J., Valtchev, V. & Young, S. J. (1995). The development of the 1994 HTK large vocabulary speech recognition system. In Proceedings of the ARPA Workshop on Spoken Language Systems Technology, pp. 104-109.
23. Young, S. J., Odell, J. J. & Woodland, P. C. (1994). Tree-based state tying for high accuracy acoustic modelling. In Proceedings of the ARPA Workshop on Human Language Technology, pp. 307-312.