Noise adaptive training for robust automatic speech recognition

IEEE Transactions on Audio, Speech and Language Processing

Volumn 18, Issue 8, 2010, Pages 1889-1901

  Kalinli, Ozlem ^a   Seltzer, Michael L ^b   Droppo, Jasha ^b   Acero, Alex ^b  

^a Sony Computer Entertainment Inc   (United States)

^b MICROSOFT RESEARCH   (United States)

Author keywords

Model adaptation; noise adaptive training; robust speech recognition; vector Taylor series (VTS)

Indexed keywords

ACOUSTIC MODEL; ADAPTIVE TRAINING; AURORA 3; AUTOMATIC SPEECH RECOGNITION; CLEAN SPEECH; FEATURE ENHANCEMENT; MODEL ADAPTATION; MODEL PARAMETERS; MODEL TRAINING; NOISE-ROBUST AUTOMATIC SPEECH RECOGNITION; POINT ESTIMATE; ROBUST SPEECH RECOGNITION; TEST TIME; TRAINING DATA; VECTOR TAYLOR SERIES; VECTOR TAYLOR SERIES (VTS);

DECODING; TAYLOR SERIES;

SPEECH RECOGNITION;

EID: 77956296425     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2010.2040522     Document Type: Article

References (30)

1. S. Boll, "Suppression of acoustic noise in speech using spectral subtraction," IEEE Trans. Acoust., Speech, Signal Process., vol. ASSP-27, no. 2, pp. 113-120, Apr. 1979.
2. D. Yu, L. Deng, J. Droppo, J. Wu, Y. Gong, and A. Acero, "A minimum- mean-square-error noise reduction algorithm on mel-frequency cepstra for robust speech recognition," in Proc. ICASSP, Las Vegas, NV, 2008, pp. 4041-4044.
3. L. Deng, A. Acero, M. Plumpe, and X. Huang, "Large-vocabulary speech recognition under adverse acoustic environments," in Proc. ICSLP, Beijing, China, 2000, pp. 806-809.
4. C. J. Leggetter and P. C. Woodland, "Maximum likelihood linear regression for speaker adaptation of continuous density hidden markov models," Comput. Speech Lang., vol. 9, no. 2, pp. 171-185, 1995.
5. J.-L. Gauvain and C.-H. Lee, "Maximum a posteriori estimation for multivariate gaussian mixture observations of Markov chains," IEEE Trans. Speech Audio Process., vol. 2, pp. 291-298, Apr. 1994.
6. V. Digalakis, D. Rtischev, L. Neumeyer, and E. Sa, "Speaker adaptation using constrained estimation of Gaussian mixtures," IEEE Trans. Speech Audio Process., vol. 3, no. 5, pp. 357-366, Sep. 1995.
7. M. J. F. Gales, "Maximum likelihood linear transformations for HMMbased speech recognition," Comput. Speech Lang., vol. 12, pp. 75-98, 1998.
8. M. K. Omar, "Regularized feature-based maximum likelihood linear regression for speech recognition," in Proc. Interspeech, Antwerp, Belgium, 2007, pp. 1561-1564.
9. G. Saon, J. M. Huerta, and E. E. Jan, "Robust digit recognition in noisy environments: The IBM Aurora 2 system," in Proc. Interspeech, Aalborg, Denmark, 2001, pp. 629-632.
10. X. Cui and A. Alwan, "Noise robust speech recognition using feature compensation based on polynomial regression of utterance SNR," IEEE Trans. Speech Audio Processing, vol. 13, no. 6, pp. 1161-1172, Nov. 2005.
11. M. Gales, S.Young, and S. J. Young, "Robust continuous speech recognition using parallel model combination," IEEE Trans. Speech Audio Process., vol. 4, no. 5, pp. 352-359, Sep. 1996.
12. P. J. Moreno, B. Raj, and R. M. Stern, "A vector Taylor series approach for environment-independent speech recognition," in Proc. ICASSP, 1996, pp. 733-736.
13. D. Y. Kim, C. K. Un, and N. S. Kim, "Speech recognition in noisy environments using first-order vector Taylor series," Speech Commun., vol. 24, no. 1, pp. 39-49, 1998.
14. A. Acero, L. Deng, T. Kristjansson, and J. Zhang, "HMM adaptation using vector Taylor series for noisy speech recognition," in Proc. ICSLP, Beijing, China, 2000, pp. 869-872.
15. J. Li, L. Deng, D. Yu, Y. Gong, and A. Acero, "High-performance HMM adaptation with joint compensation of additive and convolutive distortions via vector Taylor series," in Proc. ASRU, Kyoto, Japan, 2007, pp. 65-70.
16. T. Anastasakos, J. McDonough, R. Schwartz, and J. Makhoul, "A compact model for speaker-adaptive training," in Proc. ICSLP, Philadelphia, PA, 1996, pp. 1137-1140.
17. Y. Hu and Q. Huo, "Irrelevant variability normalization based HMM training using VTS approximation of an explicit model of environmental distortions," in Proc. Interspeech, Antwerp, Belgium, 2007, pp. 1042-1045.
18. H. Liao and M. J. F. Gales, "Adaptive training with joint uncertainty decoding for robust recognition of noisy data," in Proc. ICASSP, Honolulu, HI, 2007, pp. 389-392.
19. H. Liao and M. J. F. Gales, "Joint uncertainty decoding for noise robust speech recognition," in Proc. Interspeech, Lisbon, Portugal, 2005, pp. 3129-3132.
20. A. Acero, Acoustical and Environmental Robustness in Automatic Speech Recognition. Norwell, MA: Kluwer, 1993.
21. R. A. Gopinath, M. Gales, P. S. Gopalakrishnan, S. Balakrishnan- Aiyer, and M. A. Picheny, "Robust speech recognition in noise: Performance of the IBM continuous speech recognizer on the ARPA noise spoke task," in Proc. ARPA Workshop Spoken Lang. Syst. Technol., 1995.
22. A. P. Dempster, N. M. Laird, and D. B. Rubin, "Maximum likelihood from incomplete data via the EM algorithm," J. R. Statist. Soc., vol. 39, no. 1, pp. 1-38, 1977.
23. L. R. Rabiner, "A tutorial on hidden Markov models and selected applications in speech recognition," Proc. IEEE, vol. 77, no. 2, pp. 257-286, 1989.
24. J. E. Dennis and R. B. Schnabel, Numerical Methods for Unconstrained Optimization and Nonlinear Equations. Englwood Cliffs, NJ: Prentice- Hall, 1983.
25. H. Liao and M. J. F. Gales, "Joint uncertainty decoding for robust large vocabulary speech recognition," Cambridge Univ., 2006, Tech. Rep. CUED/F-INFENG/TR-522.
26. S. J. Young, The HTK Hidden Markov Model Toolkit: Design and Philosophy. Cambridge, U.K.: Univ. of Cambridge, Dept. of Eng., 1994.
27. H. G. Hirsch and D. Pearce, "The aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions," in Proc. ISCA ITRW ASR, Paris, France, Sep. 2000, pp. 181-188.
28. D. Pierce and A. Gunawardana, "Aurora 2.0 Speech Recognition in Noise: Update 2. Complex Backend Definition for Aurora 2.0," 2002 [Online]. Available: http://icslp2002.colorado.edu/special-sessions/ aurora
29. A. Moreno, B. Lindberg, C. Draxler, G. Richard, K. Choukri, J. Allen, and S. Euler, "Speechdat-car: A large speech database for automotive environments," in Proc. LREC, Athens, Greece, 2000.
30. D. Macho, L. Mauuary, B. Noé, 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, Denver, CO, 2002, pp. 17-20.