Maximum-likelihood nonlinear transformation for acoustic adaptation

IEEE Transactions on Speech and Audio Processing

Volumn 12, Issue 6, 2004, Pages 572-578

  Padmanabhan, Mukund ^a,b   Dharanipragada, Satya ^a  

^a IBM T J WATSON RESEARCH CENTER   (United States)

^b Renaissance Technologies   (United States)

Author keywords

Acoustic adaptation; Maximum likelihood estimation; Nonlinear tranforms; Speech recognition

Indexed keywords

DATA TRANSFER; MATHEMATICAL MODELS; MAXIMUM LIKELIHOOD ESTIMATION; PARAMETER ESTIMATION; SPEECH RECOGNITION; VECTORS;

ACOUSTIC ADAPTATION; NONLINEAR TRANSFORMS; NONSTATIONARITY; POSTFILTERING;

ACOUSTIC NOISE;

EID: 7544235206     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/TSA.2003.822629     Document Type: Conference Paper

References (10)

1. C. J. Legetter and P. C. Woodland, "Maximum likelihood linear regression for speaker adaptation of continuous density HMM's," Comput. Speech Long., vol. 9, pp. 171-186, 1996.
2. 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.
3. S. Dharanipragada and M. Padmanabhan, "A nonlinear unsupervised adaptation technique for speech recognition," in Proc. Int. Conf. Spoken Language Processing, Oct. 2000, pp. 556-559.
4. M. Padmanabhan and S. Dharanipragada, "Maxium likelihood nonlinear transformation for acoustic adaptation in speech recognition systems," in Proc. Eurospeech, 2001, pp. 2359-2362.
5. M. J. F. Gales, "Maximum likelihood linear transforms for HMM-based speech recognition," Comput., Speech, Lang., vol. 12, no. 2, pp. 75-98, 1998.
6. _, "Semi-tied covariance matrices for hidden Markov models," IEEE Trans. Speech Audio Processing, vol. 7, pp. 272-281, May 1999.
7. Numerical Algebra Group, FORTRAN Library.
8. L. R. Bahl, P. V. deSouza, P. S. Gopalakrishnan, D. Nahamoo, and M. A. Picheny, "Robust methods for context-dependent features and models in a continuous speech recognizer," in Proc. Int. Conf. Acoustics, Speech, and Signal Processing, 1994, pp. I-533-536.
9. P. S. Gopalakrishnan, L. R. Bahl, and R. Mercer, "A tree search strategy for large vocabulary continuous speech recognition," in Proc. Int. Conf. Acoustics, Speech, and Signal Processing, vol. 1, May 1995, pp. 572-575.
10. M. Padmanabhan, L. R. Bahl, and D. Nahamoo, "Partitioning the feature space of a classifier with linear hyperplanes," IEEE Trans. Speech Audio Processing, vol. 7, pp. 282-288, May 1999.