A basis representation of constrained MLLR transforms for robust adaptation

Computer Speech and Language

Volumn 26, Issue 1, 2012, Pages 35-51

  Povey, Daniel ^a   Yao, Kaisheng ^a  

^a MICROSOFT   (United States)

Author keywords

Speaker adaptation; Speech recognition

Indexed keywords

ASYMPTOTIC PERFORMANCE; MAXIMUM LIKELIHOOD LINEAR REGRESSION; SPEAKER ADAPTATION; TRANSFORMATION MATRICES; VARIABLE NUMBER; ZERO VALUES;

ESTIMATION; FEATURE EXTRACTION; LINEAR TRANSFORMATIONS; MAXIMUM LIKELIHOOD ESTIMATION;

SPEECH RECOGNITION;

EID: 79957856980     PISSN: 08852308     EISSN: 10958363     Source Type: Journal    
DOI: 10.1016/j.csl.2011.04.002     Document Type: Article

References (17)

1. H. Akaike A new look at the statistical model identification IEEE Transactions on Automatic Control 19 6 2002 716 723
2. K.T. Chen, W.W. Liau, H.M. Wang, and L.S. Lee Fast speaker adaptation using Eigenspace-based maximum likelihood linear regression Proc. ICSLP, vol. 3 2000 742 745
3. V. Digalakis, D. Rtischev, and L. Neumeyer Speaker adaptation using constrained estimation of Gaussian mixtures IEEE Transactions on Speech and Audio Processing 3 1995 357 366
4. M. Gales Maximum likelihood linear transformations for HMM-based speech recognition Computer Speech and Language 12 1997 75 98
5. M.J.F. Gales, and P.C. Woodland Mean and variance adaptation within the MLLR framework Computer Speech and Language 10 1996 249 264 (Pubitemid 126374488)
6. A. Ghoshal, D. Povey, M. Agarwal, P. Akyazi, L. Burget, K. Feng, O. Glembek, N. Goel, M. Karafiát, A. Rastrow, R.C. Rose, P. Schwarz, and S. Thomas A novel estimation of feature-space MLLR for full covariance models Proc. ICASSP 2010 4310 4313
7. L. Gillick, and S. Cox Some statistical issues in the comparison of speech recognition algorithms Proc. ICASSP, vol. 1 1989 532 535 (Pubitemid 20604171)
8. J. Huang, E. Marcheret, and K. Visweswariah Rapid feature space speaker adaptation for multi-stream HMM-based audio-visual speech recognition IEEE Intl. Conf. on Multimedia and Expo 2005 338 341 (Pubitemid 44668873)
9. B.-H. Juang, W. Chou, and C.-H. Lee Minimum classification error rate methods for speech recognition IEEE Transactions on Speech and Audio Processing 5 1997 257 265 (Pubitemid 127745998)
10. R. Kuhn, F. Perronnin, P. Nguyen, and L. Rigazzio Very fast adaptation with a compact context-dependent eigenvoice model Proc. ICASSP 2001 373 376 (Pubitemid 32839265)
11. X. Lei, J. Hamaker, and X. He Robust feature space adaptation for telephony speech recognition Proc. ICSLP 2006 773 776
12. G. Schwarz Estimating the dimension of a model The Annals of Statistics 6 2 1978 461 464
13. Shewchuk, J.R., 1994. An introduction to the conjugate gradient method without the agonizing pain. Tech. Rep., Carnegie Mellon University.
14. K.C. Sim, and M.J.F. Gales Adaptation of precision matrix models on large vocabulary continuous speech recognition Proc. ICASSP, vol. 1 2005 97 100
15. Visweswariah, K., Goel, V., Gopinath, R., 2002a. Maximum Likelihood Training of Bases for Rapid Adaptation. Available online.
16. K. Visweswariah, V. Goel, and R. Gopinath Structuring linear transforms for adaptation using training time information Proc. ICASSP 2002 3238 3241
17. Woodland, P., Povey, D., 2000. Large scale MMIE training for conversational telephone speech recognition. In: Proc. Speech Transcription Workshop.