High-performance HMM adaptation with joint compensation of additive and convolutive distortions via Vector Taylor Series

2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007, Proceedings

Volumn , Issue , 2007, Pages 65-70

  Li, Jinyu ^a   Deng, Li ^a   Yu, Dong ^a   Gong, Yifan ^a   Acero, Alex ^a  

^a MICROSOFT   (United States)

Author keywords

Additive and convolutive distortions; Joint compensation; Robust ASR; Vector taylor series

Indexed keywords

ADAPTATION ALGORITHMS; AUTOMATIC SPEECH RECOGNITION (ASR); CEPSTRAL DOMAIN; CHANNEL PARAMETERS; DISCRIMINATIVE TRAINING; DISTORTION MODELLING; EXPERIMENTAL EVALUATIONS; EXPERIMENTAL RESULTS; HIGH PERFORMANCE; HIGH RECOGNITION PERFORMANCE; JOINT COMPENSATION; LINEARIZATION TECHNIQUES; MODEL ADAPTATION; RECENT DEVELOPMENT; SPEECH RECOGNIZERS; STATIC AND DYNAMIC; VECTOR TAYLOR SERIES (VTS);

ALGORITHMS; BOOLEAN FUNCTIONS; COMPUTER NETWORKS; DYNAMIC ANALYSIS; DYNAMICAL SYSTEMS; DYNAMICS; ESTIMATION; EVOLUTIONARY ALGORITHMS; FEEDBACK LINEARIZATION; FOOD ADDITIVES; HIDDEN MARKOV MODELS; LINEARIZATION; MATHEMATICAL MODELS; MECHANICS; MULTITASKING; PARAMETER ESTIMATION; SCHEDULING ALGORITHMS; SPEECH; SPEECH ANALYSIS; STANDARDIZATION; STANDARDS; TAYLOR SERIES; VECTORS;

SPEECH RECOGNITION;

EID: 44849125798     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (19)

1. A. Peinado and J. Segura, Speech Recognition over Digital Channels -Robustness and Standards. John Wiley and Sons Ltd (West Sussex, England), 2006.
2. D. Macho, L. Mauuary, B. Noe, Y. M. Cheng, D. Ealey, D. Jouvet, H. Kelleher, D. Pearce, and F. Saadoun, "Evaluation of a noise-robust DSR front-end on Aurora databases," in Proc. ICSLP, pp. 17-20, 2002.
3. L. Deng, A. Acero, M. Plumpe, and X. Huang, "Large vocabulary speech recognition under adverse acoustic environments," Proc. ICSLP, Vol.3, pp.806-809, 2000.
4. M. J. F. Gales and S. Young, "An improved approach to the hidden Markov model decomposition of speech and noise," Proc. ICASSP, Vol. I, pp. 233-236, 1992.
5. Y. Gong, "A method of joint compensation of additive and convolutive distortions for speaker-independent speech recognition," IEEE Trans. Speech and Audio Proc., Vol. 13, No. 5, pp. 975-983, 2005.
6. A. Acero, L. Deng, T. Kristjansson, and J. Zhang, "HMM adaptation using vector Taylor series for noisy speech recognition," Proc. ICSLP, Vol.3, pp. 869-872, 2000.
7. A. Dempster, N. Laird, and D. Rubin, "Maximum likelihood from incomplete data via the EM algorithm," Journal of the Royal Statistical Society, Series B, 39(1): 1-38, 1977.
8. D. Y. Kim, C. K. Un, and N. S. Kim, "Speech recognition in noisy environments using first order vector Taylor series," Speech Communication, Vol. 24, pp. 39-49, 1998.
9. L. Deng, J. Droppo, and A. Acero, "Recursive estimation of nonstationary noise using iterative stochastic approximation for robust speech recognition," IEEE Trans. Speech and Audio Proc., Vol.11, No.6, pp. 568-580, 2003.
10. P. Moreno, Speech Recognition in Noisy Environments. PhD. Thesis, Carnegie Mellon University, 1996.
11. H. Liao and M. J. F. Gales, "Adaptive training with joint uncertainty decoding for robust recognition of noisy data," Proc. ICASSP, Vol. IV, pp. 389-392, 2007.
12. C. J. Leggetter and P. C. Woodland, "Maximum likelihood linear regression for speaker adaptation of continuous density HMMs," Comput, Speech, Lang., Vol. 9, No. 2, pp. 171-185, 1995.
13. Y. Li, H. Erdogan, Y. Gao, and E. Marcheret, "Incremental online feature space MLLR adaptation for telephony speech recognition," Proc Interspeech, pp. 1417-1420, 2002.
14. M.J.F. Gales, "Maximum likelihood linear transformations for HMM-based speech recognition," Computer Speech and Language, Vol. 12, pp. 75-98, 1998.
15. X. Cui and A. Alwan, "Noise robust speech recognition using feature compensation based on polynomial regression of utterance SNR," IEEE Trans. Speech and Audio Proc., Vol. 13, No. 6, pp. 1161-1172, 2005.
16. G. Saon, H. Huerta, and E. E. Jan, "Robust digit recognition in noisy environments: the IBM Aurora 2 system," Proc Interspeech, pp. 629-632, 2001.
17. H. G. Hirsch and D. Pearce, "The Aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions," Proc. ISCA ITRW ASR, 2000.
18. Y. Hu and Q. Huo, "Irrelevant variability normalization based HMM training using VTS approximation of an explicit model of environmental distortions," Proc. Interspeech, pp. 1042-1045, 2007.
19. G. Saon, G. Zweig, and M. Padmanabhan, "Linear feature space projections for speaker adaptation," Proc ICASSP, vol., pp.325-328, 2001.