A maximum likelihood approach to unsupervised online adaptation of stochastic vector mapping function for robust speech recognition

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 4, Issue , 2007, Pages

  Donglai, Zhu ^a   Huo, Qiang ^b  

^a INSTITUTE FOR INFOCOMM RESEARCH   (Singapore)

^b UNIVERSITY OF HONG KONG   (Hong Kong)

Author keywords

Feature compensation; Hidden Markov model; Maximum likelihood; Online adaptation; Robust speech recognition

Indexed keywords

FEATURE EXTRACTION; HIDDEN MARKOV MODELS; MAXIMUM LIKELIHOOD; ONLINE SYSTEMS; RANDOM PROCESSES; SUPPORT VECTOR MACHINES; VECTOR QUANTIZATION;

FEATURE COMPENSATION; ONLINE ADAPTATION; ROBUST SPEECH RECOGNITION;

SPEECH RECOGNITION;

EID: 34547550743     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2007.367027     Document Type: Conference Paper

References (19)

1. Aurora document AU/217/99, "Availability of Finnish speechdat-car database for ETSl STQ WI008 front-end standardisation," Nokia Nov 1999.
2. L. Deng. A. Acero, M. Plumpe, and X.-D. Huang, "Large-vocabulary speech recognition under adverse acoustic environments," Proc. IC-SLP 2000, pp.III-806-809.
3. L. Deng, A. Acero, L. Jiang, J. Droppo, and X.-D. Huang, "High-performance robust speech recognition using stereo training data," Proc. ICASSP 2001, pp. 301-304.
4. L. Deng, J. Wu, J. Droppo, and A. Acero, "Analysis and comparison of two speech feature extraction/compensation algorithms," IEEE Signal Processing Letters, vol. 12, no. 6, pp. 477-480, 2005.
5. J. Droppo and A. Acero, "Joint discriminative front end and back end training for improved speech recognition accuracy," Proc. ICASSP 2006, pp. 281-284.
6. ETSI standard document, "Speech processing, transmission and quality aspects (STQ); distributed speech recognition; advanced front-end feature extraction algorithm; compression algorithms," ETSI ES 202 050 v 1.1.1 (2002-10), 2002.
7. M. J. F. Gales, "Maximum likelihood linear transformations for HMM-based speech recognition," Computer Speech and Language, vol. 12, pp. 75-98, 1998.
8. H. C. Hirsch and D. Pearce, "The AURORA experimental framework for the performance evaluations of speech recognition systems under noisy conditions," ISCA ITRW ASR-2000, Paris, France, 2000.
9. Q. Huo and D. Zhu, "A maximum likelihood training approach to irrelevant variability compensation based on piecewise linear transformations," Proc. Interspeech 2006 - ICSLP, pp.1129-1132.
10. P. Kenny, V. Gupta, O. Boulianne, P. Ouellet, and P. Dumouchel, "Feature normalization using smoothed mixture transformations," Proc. Interspeech 2006 - ICSLP, pp.25-28.
11. S. S. Kozat, K. Visweswariah, and R. Gopinath, "Feature adaptation based on Gaussian posteriors," Proc. ICASSP 2006, pp. 221-224.
12. D. Povey, B. Kingsbury, L. Mangu, G. Saon, H. Soltau, and G. Zweig, "fMPE: Discriminatively trained features for speech recognition," Proc. ICASSP 2005, pp. 961-964.
13. A. Sankar and C.-H. Lee. "A maximum-likelihood approach to stochastic matching for robust speech recognition," IEEE Trans. on Speech and Audio Pmcessing, Vol. 4, No. 3, pp. 190-202, 1996.
14. J. Wu and Q. Huo, "An environment compensated minimum classification error training approach and its evaluation on AURORA2 database." Proc. ICSLP 2002, pp. 453-456.
15. J. Wu and Q. Huo, "Several HKU approaches for robust speech recognition and their evaluation on AURORA connected digit recognition tasks," Proc. Eurospeech 2003, pp. 21-24.
16. J. Wu, D. Zhu, and Q. Huo, "A study of minimum classification error training for segmental switching linear Gaussian hidden Markov models," Proc. ICSLP 2004.
17. J. Wu, Q. Huo, and D. Zhu. "An environment compensated maximum likelihood training approach based on stochastic vector mapping," Proc. ICASSP 2005, pp. 429-432.
18. S. J. Young, et al., The HTK Book (for HTK Version 3.3), 2005.
19. B. Zhang, S. Matsoukas, and R. Schwartz, "Discriminatively trained region dependent feature transforms for speech recognition," Proc. ICASSP 2006, pp. 313-316.