Noisy constrained maximum-likelihood linear regression for noise-robust speech recognition

IEEE Transactions on Audio, Speech and Language Processing

Volumn 19, Issue 2, 2011, Pages 315-325

  Kim, D K ^a   Gales, M J F ^b  

^a Chonnam National University   (South Korea)

^b UNIVERSITY OF CAMBRIDGE   (United Kingdom)

Author keywords

Adaptive training; noise robustness; speaker adaptation; speech recognition

Indexed keywords

ADAPTIVE TRAINING; ADAPTIVE TRAINING SCHEME; BACKGROUND NOISE; CLEAN SPEECH; EXPECTATION-MAXIMIZATION APPROACHES; FACTOR ANALYSIS; GENERATIVE MODEL; LINEAR TRANSFORM; MINIMUM PHONE ERROR; MODEL-BASED; NEW APPROACHES; NEW FORMS; NOISE ROBUST SPEECH RECOGNITION; NOISE ROBUSTNESS; NOISY OBSERVATIONS; NON-HOMOGENEOUS; RESOURCE MANAGEMENT; SPEAKER ADAPTATION; SPEECH RECOGNITION SYSTEMS; TRAINING DATA;

ACOUSTIC NOISE; COVARIANCE MATRIX; MATHEMATICAL TRANSFORMATIONS; MAXIMUM LIKELIHOOD;

SPEECH RECOGNITION;

EID: 78049302682     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2010.2047756     Document Type: Article

References (36)

1. D. Kim and M. J. F. Gales, "Adaptive training with noisy constrained maximum likelihood linear regression for noise robust speech recognition", in Proc. Interspeech, 2009, pp. 2383-2386.
2. R. P. Lippmann, E. A. Martin, and D. B. Paul, "Multi-style training for robust isolated-word speech recognition", in Proc. ICASSP, 1987, pp. 705-708.
3. T. Anastasakos, J. McDonough, R. Schwartz, and J. Makhoul, "A compact model for speaker-adaptive training", in Proc. ICSLP, 1996.
4. M. J. F. Gales, "Maximum likelihood linear transformations for HMM-based speech recognition", Comput. Speech Lang., vol. 12, Jan. 1998.
5. C. J. Leggetter and P. C. Woodland, "Maximum likelihood linear regression for speaker adaptation of continuous density HMMs", Comput. Speech Lang., vol. 9, pp. 171-186, 1995.
6. R. van Dalen and M. J. F. Gales, "Transforming features to compensate speech recogniser models for noise", in Proc. Interspeech, 2009.
7. L. Deng, A. Acero, M. Plumpe, and X. D. Huang, "Large vocabulary speech recognition under adverse acoustic environments", in Proc. ICSLP, Beijing, China, Oct. 2000, pp. 806-809.
8. W.-T. Hong and S.-H. Chen, "A robust training algorithm for adverse speech recognition", Speech Commun., vol. 30, pp. 273-293, 2000.
9. W.-T. Hong, "A discriminative and robust training algorithm for noisy speech recognition", in Proc. ICASSP, 2003, pp. 8-11.
10. B.-O. Kang, H.-Y. Jung, and Y.-K. Lee, "Discriminative noise adaptive training approach for an environment migration", in Proc. Interspeech, 2007.
11. M. J. F. Gales, "Model-based techniques for noise robust speech recognition", Ph. D. dissertation, Cambridge Univ., Cambridge, U. K., 1995.
12. A. Acero, L. Deng, T. T. Kristjansson, and J. Zhang, "HMM adaptation using vector Taylor series for noisy speech recognition", in Proc. ICSLP, Beijing, China, Oct. 2000.
13. H. Liao and M. J. F. Gales, "Issues with uncertainty decoding for noise robust speech recognition", Speech Commun., Apr. 2008.
14. P. J. Moreno, "Speech recognition in noisy environments", Ph. D. dissertation, Carnegie Mellon Univ., Pittsburgh, PA, 1996.
15. H. Liao and M. J. F. Gales, "Adaptive training with joint uncertainty decoding for robust recognition of noisy data", in Proc. ICASSP, 2007, pp. 389-392.
16. J. Li, L. Deng, Y. Gong, and A. Acero, "HMM adaptation with joint compensation of additive and convolutive distortions via vector Taylor series", in Proc. ASRU, Kyoto, Japan, 2007.
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, 2007.
18. O. Kalinli, M. L. Seltzer, and A. Acero, "Noise adaptive training using a vector Taylor series approach for noise robust automatic speech recognition", in Proc. ICASSP, 2009, pp. 3825-3828.
19. B.-H. Juang, W. Hou, and C.-H. Lee, "Minimum classification error rate methods for speech recognition", IEEE Trans. Speech Audio Process., vol. 5, no. 3, pp. 257-265, May 1997.
20. L. R. Bahl, P. F. Brown, P. V. De Souza, and R. L. Mercer, "Maximum mutual information estimation of hidden Markov model parameters for speech recognition", in Proc. ICASSP, 1986, vol. 1, pp. 49-52.
21. D. Povey and P. C. Woodland, "Improved discriminative training techniques for large vocabulary continuous speech recognition", in Proc. ICASSP, 2001, pp. 45-48.
22. J. Mcdonough, T. Schaaf, and A. Waibel, "On maximum mutual information speaker-adapted training", in Proc. ICASSP, 2002, pp. 601-604.
23. L. Wang, "Discriminative linear transforms for adaptation and adaptive training", Ph. D. dissertation, Cambridge Univ., Cambridge, U. K., 2006.
24. K. Yu and M. J. F. Gales, "Discriminative cluster adaptive training", IEEE Trans. Speech Audio Process., vol. 14, no. 5, pp. 1694-1703, Sep. 2006.
25. A. Sankar and C.-H. Lee, "A maximum-likelihood approach to stochastic matching for robust speech recognition", IEEE Trans. Speech Audio Process., vol. 4, pp. 190-202, May 1996.
26. D. B. Rubin and D. T. Thayer, "EM algorithms for ML factor analysis", Psychometrica, vol. 47, no. 1, pp. 69-76, 1982.
27. R. A. Gopinath, B. Ramabhadran, and S. Dharanipragada, "Factor analysis invariant to linear transformations of data", in Proc. ICSLP, 1998, pp. 397-400.
28. A.-V. I. Rosti and M. J. F. Gales, "Factor analysed hidden Markov models for speech recognition", Comput. Speech Lang., vol. 18, no. 3, pp. 181-200, 2004.
29. R. C. Rose, E. M. Hofstetter, and D. A. Reynolds, "Integrated models of signal and background with application to speaker identification in noise", IEEE Trans. Speech Audio Process., vol. 2, no. 2, pp. 245-257, Apr. 1994.
30. H. Liao, "Uncertainty decoding for noise robust speech recognition", Ph. D. dissertation, Cambridge Univ., Cambridge, U. K., 2007.
31. M. J. F. Gales and R. C. van Dalen, "Predictive linear transforms for noise robust speech recognition", in Proc. ASRU, 2007, pp. 59-64.
32. D. Povey, "Discriminative training for large vocabulary speech recognition", Ph. D. dissertation, Cambridge Univ., Cambridge, U. K., 2003.
33. R. Schluter and W. Macherey, "Comparison of discriminative training criteria", in Proc. ICASSP, 1998, pp. 493-496.
34. 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, no. 2, pp. 291-298, Apr. 1994.
35. G. Saon and D. Povey, "Feature and model space speaker adaptation with full covariance Gaussians", in Proc. Interspeech, 2006.
36. S. Young, G. Evermann, M. J. F. Gales, T. Hain, D. Kershaw, X. A. Liu, G. Moore, J. J. Odell, D. Ollason, D. Povey, V. Valtchev, and P. C. Woodland, The HTK Book (for HTK Version 3.4). Cambridge, U. K.: Univ. of Cambridge, Dec. 2006.