SOURCE NORMALIZATION TRAINING FOR HMM APPLIED TO NOISY TELEPHONE SPEECH RECOGNITION

5th European Conference on Speech Communication and Technology, EUROSPEECH 1997

Volumn , Issue , 1997, Pages 1555-1558

  Gong, Yifan ^a  

^a TEXAS INSTRUMENTS   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

MARKOV PROCESSES; MAXIMUM LIKELIHOOD; SPEECH COMMUNICATION; SPEECH RECOGNITION; SPEECH TRANSMISSION; TELEPHONE SETS;

ACOUSTICS MODEL; BACKGROUND CONDITIONS; CONDITION; ENVIRONMENT DATA; MULTI-ENVIRONMENTS; NORMALISATION; SPEECH RECOGNIZER; TELEPHONE SPEECH RECOGNITION; TRANSMISSION CHANNELS; TRANSMISSION NOISE;

LINEAR TRANSFORMATIONS;

EID: 0347321460     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. A. Acero and X. Huang. Speaker and gender normalization for continuous-density hidden Markov models. In Proc. ofIEEE Internat. Conf. on Acoustics, Speech and Signal Processing, pages 342-345, Atlanta, 1996.
2. T. Anastasakos, J. McDonough, R. Schwartz, and J. Makhoul. A compact model for speaker-adaptive training. In Internat. Conf. on Spoken Language Processing, volume 2, October 1996.
3. A. P. Dempster, N. M. Laird, and D. B. Rubin. Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society, 39(1):1-38, 1977.
4. B. Juang. Maximum-likelihood estimation for mixture multivariate stochastic observations of Markov chains. The Bell System Technical Journal, pages 1235-1248, July-August 1985.
5. C. J. Leggetter and P. C. Woodland. Maximum likelihood linear regression for speaker adaptation of continuous density HMMs. Computer, Speech and Language, 9(2):171-185, 1995.
6. A. Sankar and C.-H. Lee. A maximum-likelihood approach to stochastic matching for robust speech recognition. IEEE Trans. on Speech and Audio Processing, 4(3):190-202, 1996.
7. O. Siohan, Y. Gong, and J.-P. Haton. Comparative experiments of several adaptation approaches to noisy speech recognition using stochastic trajectory models. Speech Communication, 18:335-352, 1996.