Discriminative linear transforms for feature normalization and speaker adaptation in HMM estimation

IEEE Transactions on Speech and Audio Processing

Volumn 13, Issue 3, 2005, Pages 367-376

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

^a Johns Hopkins University   (United States)

Author keywords

Adaptive training; Correlation modeling; Discrim inative training

Indexed keywords

ACOUSTIC SIGNAL PROCESSING; ALGORITHMS; CORRELATION METHODS; MARKOV PROCESSES; MATHEMATICAL MODELS; MATHEMATICAL TRANSFORMATIONS; MATRIX ALGEBRA; MAXIMUM LIKELIHOOD ESTIMATION; SPEECH PROCESSING; VECTORS;

ADAPTIVE TRAINING; CORRELATION MODELING; DISCRIMINATIVE TRAINING; HMM ESTIMATION;

FEATURE EXTRACTION;

EID: 18744406714     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/TSA.2005.845806     Document Type: Article

References (23)

1. R. A. Gopinath, "Maximum likelihood modeling with Gaussian distributions for classification," in Proc. Int. Conf. Acoustics, Speech, Signal Processing, vol. 2, May 1998, pp. 661-664.
2. M. J. F. Gales, "Semi-tied covariance matrices for hidden Markov models," IEEE Trans. Speech Audio Process., vol. 7, no. 5, pp. 272-281, May 1999.
3. T. Anastasakos, J. McDonough, R. Schwartz, and J. Makhoul, "A compact model for speaker-adaptive training," in Proc. Int. Conf. Spoken Language Processing, 1996, pp. 1137-1140.
4. M. J. F. Gales, "Maximum likelihood linear transformations for HMM-based speech recognition," Comput. Speech Lang., vol. 12, no. 2, pp. 75-98, Apr. 1998.
5. Y. Normandin, "Maximum mutual information estimation of hidden Markov models," in Automatic Speech and Speaker Recognition: Advanced Topics, C.-H. Lee, F. K. Soong, and K. K. Paliwal, Eds. Norwell, MA: Kluwer, 1996, ch. 3, pp. 57-81.
6. P. C. Woodland and D. Povey, "Large scale discriminative training for speech recognition," in Proc. Tutorial Research Workshop on Automatic Speech Recognition, 2000, pp. 7-16.
7. L. F. Uebel and P. C. Woodland, "Discriminative linear transforms for speaker adaptation," in Proc. Tutorial Research Workshop on Adaptation Methods for Speech Recognition, 2001, pp. 61-64.
8. _, "Improvements in linear transforms based speaker adaptation," in Proc. Int. Conf. Acoustics, Speech, Signal Processing, vol. 1, May 2001, pp. 49-52.
9. A. Gunawardana and W. Byrne, "Discriminative speaker adaptation with conditional maximum likelihood linear regression," in Proc. Eur. Conf. Speech Communication and Technology, 2001, pp. 1203-1206.
10. J. McDonough, T. Schaaf, and A. Waibel, "On maximum mutual information speaker-adapted training," in Proc. Int. Conf. Acoustics, Speech, Signal Processing, vol. 1, May 2002, pp. 601-604.
11. A. Ljolje, "The AT&T LVCSR-2001 system," presented at the NIST LVCSR Workshop, 2001.
12. M. Hunt and C. Lefèbvre, "A comparison of several acoustic representations for speech recognition with degraded and undegraded speech," in Proc. Int. Conf. Acoustics, Speech, Signal Processing, vol. 1, May 1989, pp. 262-265.
13. R. Schlüter, "Investigations on Discriminative Training Criteria," Ph.D. dissertation, RWTH Aachen- Univ. Technol., Aachen, Germany, 2000.
14. A. Gunawardana, "Maximum Mutual Information Estimation of Acoustic HMM Emission Densities," Johns Hopkins Univerisity, CLSP, Baltimore, MD, Tech. Rep. CLSP Reasearch Note no. 40, 2001.
15. M. J. F. Gales and P. Woodland, "Variance Compensation Within the MLLR Framework," Eng. Dept., Univ. Cambridge, Cambridge, U.K., Tech. Rep. CUED/F-INFENT/TR242, 1996.
16. S. Young, D. Kershaw, J. Odell, D. Ollason, V. Valtchev, and P. Woodland, The HTK Book, 3.0 ed., 2000.
17. W. Byrne, "The JHU march 2001 Hub-5 conversational speech transcription system," presented at the NIST LVCSR Workshop, 2001.
18. H. Hermansky, "Perceptual linear predictive (PLP) analysis of speech," J. Acoust. Soc. America, vol. 87, no. 4, pp. 1738-1752, Apr. 1990.
19. M. Mohri and M. Riley, "Integrated context-dependent networks in very large vocabulary speech recognition," in Proc. Eur. Conf. Speech Commun. Technol., 1999, pp. 811-814.
20. A. Stolcke, H. Bratt, J. Butzberger, H. Franco, V. R. Rao Gadde, M. Plauché, C. Richey, E. Shriberg, K. Sönmez, F. Weng, and J. Zheng, 'The SRI march 2000 Hub-5 conversational speech transcription system," presented at the Speech Transcription Workshop, 2000.
21. A. Martin, M. Przybocki, J. Fiscus, and D. Pallett, "The 2000 NIST evaluation for recognition of conversational speech over the telephone," presented at the Speech Transcription Workshop, 2000.
22. A. Martin, J. Fiscus, M. Przybocki, and B. Fisher, "The evaluation: Word error rates and confidence analysis," presented at the Hub-5 Workshop, Linthicum Heights, MD, 1998. [Online]. Available: http://www.nist.gov/speech/ tests/ctr/hub5e_98/hub5e_98.htm.
23. M. J. F. Gales, "Adaptive training for robust ASR," in Proc. IEEE Workshop on Automatic Speech Recognition and Understanding, Dec. 2001, pp. 15-20.