A study on the generalization capability of acoustic models for robust speech recognition

IEEE Transactions on Audio, Speech and Language Processing

Volumn 18, Issue 6, 2010, Pages 1158-1169

  Xiao, Xiong ^a   Li, Jinyu ^b   Chng, Eng Siong ^a   Li, Haizhou ^a,c   Lee, Chin Hui ^d  

^a NANYANG TECHNOLOGICAL UNIVERSITY   (Singapore)

^b MICROSOFT   (United States)

^c INSTITUTE FOR INFOCOMM RESEARCH   (Singapore)

^d GEORGIA INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

Aurora task; discriminative training; large margin; robust speech recognition

Indexed keywords

ACOUSTIC MODEL; AURORA TASK; COMPETING MODELS; CONNECTED DIGITS; DISCRIMINATIVE TRAINING; FEATURE NORMALIZATION; GENERAL MODEL; GENERALIZATION CAPABILITY; LANGUAGE MODEL; LARGE MARGIN; LEARNING FRAMEWORKS; MACHINE LEARNING APPLICATIONS; MEAN AND VARIANCE NORMALIZATIONS; MODEL TRAINING; NOISY SPEECH RECOGNITION; ROBUST SPEECH RECOGNITION; ROBUSTNESS ISSUES; SPEECH RECOGNITION PERFORMANCE; SPEECH RECOGNITION ROBUSTNESS; STATISTICAL LEARNING THEORY; TESTING CASE; TESTING DATA; TRAINING DATA;

ABILITY TESTING; COMPUTATIONAL LINGUISTICS; FACE RECOGNITION;

SPEECH RECOGNITION;

EID: 77955810460     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2009.2031236     Document Type: Article

References (43)

1. Y. Gong, "Speech recognition in noisy environments: A survey," Speech Commun., vol.16, no.3, pp. 261-291, 1995.
2. Y. Ephraim and D. Malah, "Speech enhancement using a minimum mean square error short time spectral amplitude estimator," IEEE Trans. Acoust., Speech, Signal Process., vol.ASSP-32, no.6, pp. 1109-1121, Dec. 1984.
3. Y. Ephraim and D. Malah, "Speech enhancement using a minimum mean square error log-spectral amplitude estimator," IEEE Trans. Acoust., Speech, Signal Process., vol.33, no.2, pp. 443-445, Apr. 1985.
4. B. Raj, M. L. Seltzer, and R. M. Stern, "Reconstruction of missing features for robust speech recognition," Speech Commun., vol.43, no.4, pp. 275-296, 2004.
5. M. Afify, "Accurate compensation in the log-spectral domain for noisy speech recognition," IEEE Trans. Speech Audio Process., vol.13, no.3, pp. 388-398, May 2005.
6. 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.
7. L. Deng, J. Droppo, and A. Acero, "Estimating cepstrum of speech under the presence of noise using a joint prior of static and dynamic features," IEEE Trans. Speech Audio Process., vol.12, no.3, pp. 218-223, May 2004.
8. L. Deng, A. Acero, M. Plumpe, and X. D. Huang, "Large-vocabulary speech recognition under adverse acoustic environment," in Proc. ICSLP'00, Beijing, China, Oct. 2000, pp. 806-809.
9. S. Furui, "Cepstral analysis technique for automatic speaker verification," IEEE Trans. Acoust., Speech, Signal Process., vol.ASSP-29, no.2, pp. 254-272, Apr. 1981.
10. O. Viikki and K. Laurila, "Cepstral domain segmental feature vector normalization for noise robust speech recognition," Speech Commun., vol.25, pp. 133-147, 1998.
11. F. Hilger and H. Ney, "Quantile based histogram equalization for noise robust large vocabulary speech recognition," IEEE Trans. Audio, Speech, Lang. Process., vol.14, no.3, pp. 845-854, May 2006.
12. A. De La Torre, A. M. Peinado, J. C. Segura, J. L. Perez-Cordoba, M. C. Benitez, and A. J. Rubio, "Histogram equalization of speech representation for robust speech recognition," IEEE Trans. Speech Audio Process., vol.13, no.3, pp. 355-366, May 2005.
13. Y. Suh, M. Ji, and H. Kim, "Probabilistic class histogram equalization for robust speech recognition," IEEE Signal Process. Lett., vol.14, no.4,pp. 287-290, Apr. 2007.
14. J. C. Segura, C. Benítez, A. De La Torre, A. J. Rubio, and J. Ramírez, "Cepstral domain segmental nonlinear feature transformations for robust speech recognition," IEEE Signal Process. Lett., vol.11, no.5, pp. 517-520, May 2004.
15. H. Hermansky and N. Morgan, "RASTA processing of speech," IEEE Trans. Speech Audio Process., vol.2, no.4, pp. 578-589, Oct. 1994.
16. C.-P. Chen and J. A. Bilmes, "MVA processing of speech features," IEEE Trans. Audio, Speech, Lang. Process., vol.15, no.1, pp. 257-270, Jan. 2007.
17. X. Xiao, E. S. Chng, and H. Li, "Temporal structure normalization of speech feature for robust speech recognition," IEEE Signal Process. Lett., vol.14, no.7, pp. 500-503, Jul. 2007.
18. X. Xiao, E. S. Chng, and H. Li, "Normalization of the speech modulation spectra for robust speech recognition," IEEE Trans. Audio, Speech, Lang. Process., vol.16, no.8, pp. 1662-1674, Nov. 2008.
19. 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. 171-185, Apr. 1995.
20. 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.
21. M. J. F. Gales and S. J. Young, "Cepstral parameter compensation for HMM recognition," Speech Commun., vol.12, pp. 231-239, Jul. 1993.
22. Y. Tsao and C.-H. Lee, "An ensemble modeling approach to joint characterization of speaker and speaking environments," in Proc. Eurospeech '07, Antwerp, Belgium, Sep. 2007, pp. 1050-1053.
23. Y. Tsao and C.-H. Lee, "Two extensions to ensemble speaker and speaking environment modeling for robust automatic speech recognition," in Proc. ASRU'07, Kyoto, Japan, Dec. 2007, pp. 77-80.
24. Y. Gong, "A method of joint compensation of additive and convolutive distortions for speaker-independent speech recognition," IEEE Trans. Speech Audio Process., vol.13, no.5, pp. 975-983, Oct. 2005.
25. 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'07, Kyoto, Japan, Dec. 2007, pp. 65-70.
26. V. N. Vapnik, The Nature of Statistical Learning Theory. New York: Springer Verlag, 1995.
27. B.-H. Juang and S. Katagiri, "Discriminative learning for minimum error classification," IEEE Trans. Signal Process., vol.40, no.12, pp. 3043-3054, Dec. 1992.
28. B.-H. Juang, W. Chou, 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.
29. L. R. Bahi, 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'86, Tokyo, Japan, Apr. 1986, pp. 49-52.
30. V. Valtchev, J. J. Odell1, P. C. Woodland, and S. J. Young, "MMIE training of large vocabulary recognition systems," Speech Commun., vol.22, no.4, pp. 303-314, 1997.
31. D. Povey, "Discriminative training for large vocabulary speech recognition," Ph.D. dissertation, Univ. of Cambridge, Cambridge, U.K., 2003.
32. J. Wu and Q. Huo, "An environment compensated minimum classification error training approach based on stochastic vector mapping," IEEE Trans. Audio, Speech, Lang. Process., vol.14, no.6, pp. 2147-2155, Nov. 2006.
33. B.-W. Mak, Y.-C. Tam, and P. Li, "Discriminative auditory-based features for robust speech recognition," IEEE Trans. Speech Audio Process., vol.12, no.1, pp. 27-36, Jan. 2004.
34. J. Droppo and A. Acero, "Maximum mutual information SPLICE transform for seen and unseen conditions," in Proc. Interspeech'05, Lisbon, Portugal, Sep. 2005, pp. 989-992.
35. F. Sha and L. Saul, "Large margin gaussian mixture modeling for phonetic classification and recognition," in Proc. ICASSP'06, May 2006, vol.1, pp. I-I.
36. F. Sha and L. K. Saul, "Large margin hidden Markov models for automatic speech recognition," in Advances in Neural Information Processing Systems, B. Schölkopf, J. Platt, and T. Hofmann, Eds. Cambridge, MA: MIT Press, 2007, vol.19.
37. H. Jiang, X. Li, and C. Liu, "Large margin hidden Markov models for speech recognition," IEEE Trans. Audio, Speech, Lang. Process., vol.14, no.5, pp. 1584-1595, Oct. 2006.
38. J. Li, M. Yuan, and C.-H. Lee, "Approximate test risk bound minimization through soft margin estimation,"IEEE Trans. Audio, Speech, Lang. Process., vol.15, no.8, pp. 2393-2404, Nov. 2007.
39. J. Li and C.-H. Lee, "On a generalization of margin-based discriminative training to robust speech recognition," in Proc. Interspeech'08, Brisbane, Australia, Sep. 2008.
40. D. Pearce and H.-G. Hirsch, "The AURORA experimental framework for the performance evaluation of speech recognition systems under noisy conditions," in Proc. ICSLP'00, Beijing, China, Oct. 2000, vol.4, pp. 29-32.
41. A. Acero, "Acoustical and environmental robustness in automatic speech recognition," Ph.D. dissertation, Dept. Elec. Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, 1990.
42. P. J. Moreno, "Speech Recognition in Noisy Environments," Ph.D. dissertation, Dept. Elec. Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, 1996.
43. Baseline Results for Subsect of SpeechDat-Car Finnish Database for ETSI STQ WI008 Advance Front End Evaluation Nokia, 2000, Aurora document no. AU/255/00.