DISCRIMINATIVE LINEAR TRANSFORMS FOR FEATURE NORMALIZATION AND SPEAKER ADAPTATION IN HMM ESTIMATION

7th International Conference on Spoken Language Processing, ICSLP 2002

Volumn 2002-September, Issue , 2002, Pages 2585-2588

  Tsakalidis, Stavros ^a   Doumpiotis, Vlasios ^a   Byrne, William ^a  

^a Johns Hopkins University   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

MATHEMATICAL TRANSFORMATIONS; SPEECH RECOGNITION;

DISCRIMINATIVE TRAINING; FEATURE NORMALIZATION; HMM ESTIMATION; HMM-BASED; INFORMATION CRITERION; LINEAR TRANSFORM; MAXIMUM MUTUAL INFORMATION; SPEAKER ADAPTATION; SPEAKER ADAPTIVE TRAININGS; TRAINING PROCEDURES;

SPEECH COMMUNICATION;

EID: 0141477730     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (15)

1. T. Anastasakos, J. McDonough, R. Schwartz, and J. Makhoul. A compact model for speaker-adaptive training. In ICSLP, 1996.
2. W. Byrne. The JHU March 2001 Hub-5 Conversational Speech Transcription System. In Proceedings of the NIST LVCSR Workshop. NIST, 2001.
3. M. J. F. Gales. Maximum likelihood liner transformations for hmm-based speech recognition. Comp. Spch. & Lang., 12, 1998.
4. M. J. F. Gales. Semi-tied covariance matrices for hidden markov models. IEEE Trans. Spch. & Aud. Proc., 7(3), 1999.
5. R. A. Gopinath. Maximum likelihood modeling with gaussian distributions for classification. In ICASSP. IEEE, 1998.
6. A. Gunawardana. Maximum mutual information estimation of acoustic hmm emission densities. Technical Report CLSP Research Note No. 40, CLSP, JHU, 2001.
7. A. Gunawardana and W. Byrne. Discriminative speaker adaptation with conditional maximum likelihood linear regression. In Eurospeech, 2001.
8. A. Ljolje. The AT&T LVCSR-2001 system. In Proceedings of the NIST LVCSR Workshop. NIST, 2001.
9. J. McDonough, T. Schaaf, and A. Waibel. On maximum mutual information speaker-adapted training. In ICASSP. IEEE, 2002.
10. Y. Normandin. Maximum mutual information estimation of hidden Markov models. In C.-H. Lee, F. Soong, and K. Paliwal, editors, Automatic Speech and Speaker Recognition: Advanced Topics. Kluwer, 1996.
11. S. Tsakalidis, V. Doumpiotis, and W. Byrne. Discriminative linear transforms for feature normalization and speaker adaptation in HMM estimation. Technical Report CLSP Research Note No. 47, CLSP, JHU, 2002.
12. L. F. Uebel and P. C. Woodland. Discriminative linear transforms for speaker adaptation. In Proc. ITRW ASR. ISCA, 2001.
13. L. F. Uebel and P. C. Woodland. Improvements in linear transforms based speaker adaptation. In ICASSP. IEEE, 2001.
14. P. C. Woodland and D. Povey. Large scale discriminative training for speech recognition. In Proc. ITRW ASR. ISCA, 2000.
15. S. Young, D. Kershaw, J. Odell, D. Ollason, V. Valtchev, and P. Woodland. The HTK Book, Version 3.0, July 2000.