Nonlinear compensation using the gauss-newton method for noise-robust speech recognition

IEEE Transactions on Audio, Speech and Language Processing

Volumn 20, Issue 8, 2012, Pages 2191-2206

  Zhao, Yong ^a   Juang, Biing Hwang ^a  

^a GEORGIA INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

Gauss Newton method; nonlinear compensation; robust speech recognition; vector Taylor series (VTS)

Indexed keywords

CROSS-COVARIANCE; GAUSS-NEWTON; GAUSS-NEWTON METHODS; GAUSSIAN MIXTURE MODEL; ITERATIVE ESTIMATION; JACOBIANS; NOISE ESTIMATION; NOISE ESTIMATION ALGORITHM; NOISE PARAMETERS; NOISE ROBUST SPEECH RECOGNITION; NOISE VARIANCE ESTIMATION; NONLINEAR COMPENSATION; PARALLEL MODEL COMBINATIONS; PERFORMANCE IMPROVEMENTS; ROBUST SPEECH RECOGNITION; SAMPLING-BASED; UNIFIED APPROACH; UNSCENTED TRANSFORM; VECTOR TAYLOR SERIES;

ALGORITHMS; ESTIMATION; GAUSSIAN DISTRIBUTION; NEWTON-RAPHSON METHOD; SPEECH RECOGNITION;

PARAMETER ESTIMATION;

EID: 84865208051     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2012.2199107     Document Type: Article

References (55)

1. Y. Gong, "Speech recognition in noisy environments: A survey," Speech Commun., vol. 16, pp. 261-291, 1995.
2. C. H. Lee, "On stochastic feature and model compensation approaches to robust speech recognition," Speech Commun., vol. 25, pp. 29-47, 1998.
3. 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, pp. 171-186, 1995.
4. V. V. Digalakis, D. Rtischev, and L. G. Neumeyer, "Speaker adaptation using constrained estimation of Gaussian mixtures," IEEE Trans. Speech Audio Process., vol. 3, no. 5, pp. 357-366, Sep. 1995.
5. A. Acero, "Acoustical and environmental robustness in automatic speech recognition," Ph.D. dissertation, Carnegie Mellon Univ., Pittsburgh, PA, 1990.
6. P. J. Moreno, "Speech recognition in noisy environments," Ph.D. dissertation, Carnegie Mellon Univ., Pittsburgh, PA, 1996.
7. 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.
8. Y. Hu and Q. Huo, "An HMM compensation approach using unscented transformation for noisy speech recognition," in Proc. ISCSLP, Kent Ridge, Singapore, 2006, pp. 346-357.
9. M. J. F. Gales, "Model-based techniques for noise robust speech recognition," Ph.D. dissertation, Univ. of Cambridge, Cambridge, U.K., 1995.
10. B. Atal, "Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification," J. Acoust. Soc. Amer., vol. 55, no. 6, pp. 1304-1312, Jun. 1974.
11. A. P. Dempster, N. M. Laird, and D. B. Rubin, "Maximum likelihood from incomplete data via the EM algorithm," J. R. Statist. Soc. B, vol. 39, no. 1, pp. 1-38, 1977.
12. J. Li, L. Deng, D. Yu, Y. Gong, and A. Acero, "A unified framework of HMM adaptation with joint compensation of additive and convolutive distortions," Comput. Speech Lang., vol. 23, pp. 389-405, 2009.
13. H. Liao, "Uncertainty decoding for noise robust speech recognition," Ph.D. dissertation, Univ. of Cambridge, Cambridge, U.K., 2007.
14. J. Li, D. Yu, Y. Gong, and L. Deng, "Unscented transform with online distortion estimation for HMM adaptation," in Proc. Interspeech, Makuhari, Japan, 2010, pp. 1660-1663.
15. O. Kalinli, M. Seltzer, J. Droppo, and A. Acero, "Noise adaptive training for robust automatic speech recognition," IEEE Trans. Audio, Speech, Lang. Process., vol. 18, no. 8, pp. 1889-1901, Nov. 2010.
16. Y. Zhao and B. H. Juang, "On noise estimation for robust speech recognition using vector Taylor series," in Proc. ICASSP, Dallas, TX, 2010, pp. 4290-4293.
17. Y. Zhao and B. H. Juang, "Non-linear noise compensation for robust speech recognition using Gauss-Newton method," in Proc. ICASSP, Praque, Czech Republic, 2011, pp. 4796-4799.
18. L. Deng, J. Droppo, and A. Acero, "Enhancement of log mel power spectra of speech using a phase-sensitive model of the acoustic environment and sequential estimation of the corrupting noise," IEEE Trans. Speech Audio Process., vol. 12, no. 2, pp. 133-143, Mar. 2004.
19. 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.
20. T. T. Kristjansson, B. Frey, L. Deng, and A. Acero, "Towards nonstationary model-based noise adaptation for large vocabulary speech recognition," in Proc. ICASSP, Salt Lake City, UT, 2001, pp. 337-340. (Pubitemid 32839256)
21. C. K. Raut, T. Nishimoto, and S. Sagayama, "Model adaptation for long convolutional distortion by maximum likelihood based state filtering approach," in Proc. ICASSP, Toulouse, France, 2006, pp. 1133-1136.
22. 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.
23. 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, pp. 39-49, 1998. (Pubitemid 128435865)
24. Y. Zhao and B. H. Juang, "A comparative study of noise estimation algorithms for non-linear compensation in robust speech recognition," Speech Commun., submitted for publication.
25. M. J. F. Gales, "Model-based approaches to handling uncertainty," in Robust Speech Recognition of Uncertain or Missing Data, D. Kolossa and R. Haeb-Umbach, Eds. New York: Springer-Verlag, 2011.
26. J. P. Openshaw and J. S. Masan, "On the limitations of cepstral features in noise," in Proc. ICASSP, Adelaide, Australia, 1994, pp. 49-52.
27. R. A. Gopinath, M. J. F. Gales, P. S. Gopalakrishnan, S. Balakrishnan-Aiyer, and M. A. Picheny, "Robust speech recognition in noise - performance of the IBM continuous speech recogniser on the ARPA noise spoke task," in Proc. ARPA Workshop Spoken Lang. Syst. Technol., 1995, pp. 127-130.
28. V. Stouten, H. Van hamme, and P. Wambacq, "Effect of phase-sensitive environment model and higher order VTS on noisy speech feature enhancement," in Proc. ICASSP, Philadelphia, PA, 2005, pp. 433-436.
29. H. Xu and K. K. Chin, "Joint uncertainty decoding with the second order approximation for noise robust speech recognition," in Proc. ICASSP, Taipei, Taiwan, 2009, pp. 3841-3844.
30. J. Du and Q. Huo, "A feature compensation approach using high-order vector Taylor series approximation of an explicit distortion model for noisy speech recognition," IEEE Trans. Audio, Speech, Lang. Process., vol. 19, no. 8, pp. 2285-2293, Nov. 2011.
31. S. J. Julier and J. K. Uhlmann, "Unscented filtering and nonlinear estimation," Proc. IEEE, vol. 92, no. 3, pp. 401-422, Mar. 2005. (Pubitemid 40890750)
32. T. Kobayashi, T. Masuko, and K. Tokuda, "HMM compensation for noisy speech recognition based on cepstral parameter generation," in Proc. Eurospeech, Rhodes, Greece, 1997, pp. 1583-1586.
33. R. C. van Dalen and M. J. F. Gales, "Extended VTS for noise-robust speech recognition," IEEE Trans. Audio, Speech, Lang. Process., vol. 19, no. 4, pp. 733-743, May 2011.
34. J. Nocedal and S. J. Wright, Numerical Optimization. New York: Springer-Verlag, 1999.
35. R. A. Horn and C. R. Johnson, Topics in Matrix Analysis. Cambridge, U.K.: Cambridge Univ. Press, 1994.
36. M. J. F. Gales, "Semi-tied covariance matrices for hidden Markov models," IEEE Trans. Speech Audio Process., vol. 7, no. 3, pp. 272-281, May 1999.
37. P. A. Olsen and R. A. Gopinath, "Modeling inverse covariance matrices by basis expansion," IEEE Trans. Speech Audio Process., vol. 12, no. 1, pp. 37-46, Jan. 2004.
38. S. Axelrod, R. Gopinath, and P. Olsen, "Modeling with a subspace constraint on inverse covariance matrices," in Proc. ICSLP, Denver, CO, 2002, pp. 2177-2180.
39. L. K. Saul and M. G. Rahim, "Maximum likelihood and minimum classification error factor analysis for automatic speech recognition," IEEE Trans. Speech Audio Process., vol. 8, no. 2, pp. 115-125, Mar. 2000. (Pubitemid 30578364)
40. V. Vanhoucke and A. Sankar, "Mixtures of inverse covariances," IEEE Trans. Speech Audio Process., vol. 12, no. 3, pp. 250-264, May 2004.
41. R. A. Horn and C. R. Johnson, Matrix Analysis. Cambridge, U.K.: Cambridge Univ. Press, 1990.
42. 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, 2000, pp. 181-188.
43. S. Kullback and R. A. Leibler, "On information and sufficiency," Ann. Math. Stat., vol. 21, no. 1, pp. 79-86, Mar. 1951.
44. J. R. Blum, "Multidimensional stochastic approximation methods," Ann. Math. Stat., vol. 25, no. 4, pp. 737-744, 1954.
45. 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.
46. Y. Shinohara and M. Akamine, "Bayesian feature enhancement using a mixture of unscented transformation for uncertainty decoding of noisy speech," in Proc. ICASSP, Taipei, Taiwan, 2009, pp. 4569-4572.
47. H. Xu and K. K. Chin, "Comparison of estimation techniques in joint uncertainty decoding for noise robust speech recognition," in Proc. Interspeech, Brighton, U.K., 2009, pp. 2403-2406.
48. C. Yang, F. K. Soong, and T. Lee, "Static and dynamic spectral features: Their noise robustness and optimal weights for ASR," IEEE Trans. Audio, Speech, Lang. Process., vol. 15, no. 3, pp. 1087-1097, Mar. 2007.
49. 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.
50. T. T. Kristjansson, "Speech recognition in adverse environments: A probabilistic approach," Ph.D. dissertation, Univ. of Waterloo, Waterloo, ON, Canada, 2002.
51. H. Jiang and Q. Wang, "Nonlinear noise compensation in feature domain for speech recognition with numerical methods," in Proc. ICASSP, Montreal, QC, Canada, 2004, pp. 985-988.
52. J. R. Hershey, P. A. Olsen, and S. J. Rennie, "Signal interaction and the devil function," in Proc. Interspeech, Makuhari, Japan, 2010.
53. R. C. van Dalen and M. J. F. Gales, "Asymptotically exact noise-corrupted speech likelihoods," in Proc. Interspeech, Makuhari, Japan, 2010, pp. 709-712.
54. S. R. Searle, Matrix Algebra Useful for Statistics. New York: Wiley, 1982.
55. J. J. Bussgang, "Crosscorrelation functions of amplitude-distorted Gaussian signals," Mass. Inst. Technol, Cambridge, MA, Tech. Rep. 216, 1952.