An environment-compensated minimum classification error training approach based on stochastic vector mapping

IEEE Transactions on Audio, Speech and Language Processing

Volumn 14, Issue 6, 2006, Pages 2147-2155

  Wu, Jian ^a,b   Huo, Qiang ^a  

^a UNIVERSITY OF HONG KONG   (Hong Kong)

^b MICROSOFT   (United States)

Author keywords

Feature compensation; Hidden Markov model (HMM); Minimum classification error training (MCE); Noise robustness; Robust speech recognition; Stochastic vector mapping

Indexed keywords

FEATURE COMPENSATION; HIDDEN MARKOV MODEL (HMM); MINIMUM CLASSIFICATION ERROR TRAINING (MCE); NOISE ROBUSTNESS; ROBUST SPEECH RECOGNITION; STOCHASTIC VECTOR MAPPING;

ACOUSTIC NOISE; ERROR COMPENSATION; HIDDEN MARKOV MODELS; MAXIMUM LIKELIHOOD; OBJECT RECOGNITION; RANDOM PROCESSES; SPEECH ANALYSIS; STOCHASTIC MODELS; VECTORS;

SPEECH RECOGNITION;

EID: 44849090158     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2006.872616     Document Type: Article

References (40)

1. A. Acero, Acoustic and Environment Robustness in Automatic Speech Recognition. Norwell, MA: Kluwer, 1993.
2. T. Anastasakos, J. McDonough, R. Schwartz, and J. Makhoul, "A compact model for speaker-adaptive training," in Proc. ICSLP, 1996, pp. 1137-1140.
3. A. Biem and S. Katagiri, "Feature extraction based on minimum classification error/generalized probabilistic descent method," in Proc. ICASSP, 1993, pp. II-275-II-278.
4. A. Biem, S. Katagiri, E. McDermott, and B.-H. Juang, "An application of discriminative feature extraction to filter-bank-based speech recognition," IEEE Trans. Speech Audio Process., vol. 9, no. 2, pp. 96-110, Mar. 2001.
5. R. Chengalvarayan and L. Deng, "HMM-based speech recognition using state-dependent, discriminatively derived transforms on Mel-Warped DFT features," IEEE Trans. Speech Audio Process., vol. 5, no. 3, pp. 243-256, May 1997.
6. R. Chengalvarayan, "Evaluation of front-end features and noise compensation methods for robust Mandarin speech recognition," in Proc. Eurospeech, Aalborg, Denmark, 2001, pp. 897-900.
7. W. Chou, M. G. Rahim, and E. Buhrke, "Signal conditioned minimum error rate training," in Proc. Eurospeech, 1995, pp. 495-498.
8. A. Dempster, N. Laird, and D. Rubin, "Maximum likelihood from incomplete data via the EM algorithm," in J. Roy. Statist. Soc. Ser. B, 1977, vol. 39, no. 1, pp. 1-38.
9. L. Deng, A. Acero, M. Plumpe, and X.-D. Huang, "Large-vocabulary speech recognition under adverse acoustic environments," in Proc. ICSLP, Oct. 2000, pp. III-806-809.
10. L. Deng, A. Acero, L. Jiang, J. Droppo, and X.-D. Huang, "High-performance robust speech recognition using stereo training data," in Proc. ICASSP, 2001, pp. I-301-I-304.
11. L. Deng, J. Droppo, and A. Acero, "Recursive estimation of nonstationary noise using iterative stochastic approximation for robust speech recognition," IEEE Trans. Speech Audio Process., vol. 11, no. 6, pp. 568-580, Nov. 2003.
12. J. Droppo, L. Deng, and A. Acero, "Evaluation of the SPLICE algorithm on the Aurora2 database," in Proc. Eurospeech, Aalborg, Denmark, Sep. 2001, pp. 217-220.
13. Speech Processing, Transmission and Quality Aspects (STQ); Distributed Speech Recognition; Advanced Front-End Feature Extraction Algorithm; Compression Algorithms, ETSI ES 202 050 v1.1.1 (2002-10), Oct. 2002, ETSI standard document.
14. M. J. F. Gales, "Maximum likelihood linear transformations for HMMbased speech recognition," in Comput. Speech Lang., 1998, vol. 12, pp. 75-98.
15. Y. Gong, "Source normalization training for HMM applied to noisy telephone speech recognition," in Proc. Eurospeech, 1997, pp. 1555-1558.
16. H. G. Hirsch and D. Pearce, "The AURORA experimental framework for the performance evaluations of speech recognition systems under noisy conditions," in ISCA ITRW ASR, Paris, France, Sep. 2000, pp. 181-188.
17. W.-T. Hong and S.-H. Chen, "A robust training algorithm for adverse speech recognition," Speech Commun., vol. 30, no. 4, pp. 273-293, 2000.
18. W.-T. Hong, "A discriminative and robust training algorithm for noisy speech recognition," in Proc. ICASSP, 2003, pp. I-8-I-11.
19. 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.
20. 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.
21. C. Lawrence and M. Rahim, "Integrated bias removal techniques for robust speech recognition," in Comput. Speech . Lang., 1999, vol. 13, pp. 283-298.
22. R. G. Leonard, "A database for speaker-independent digit recognition," in Proc. ICASSP, 1984, pp. 42.11.1-42.11.4.
23. 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.
24. B. 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.
25. J. McDonough, T. Schaaf, and A. Waibel, "On maximum mutual information speaker-adapted training," in Proc. ICASSP, 2002, pp. I-601-I-604.
26. P. Moreno, "Speech Recognition in Noisy Environments," Ph.D. dissertation, Dept. Elect. Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, 1996.
27. K. K. Paliwal, M. Bacchini, and Y. Sagisaka, "Simultaneous design of feature extractor and pattern classifier using the minimum classification error training algorithm," in Proc. NNSP, 1995, pp. 67-76.
28. M. Rahim and C.-H. Lee, "Simultaneous feature and HMM design using string-based minimum classification error training criterion," in Proc. ICSLP, 1996, pp. 1820-1823.
29. M. Rahim, B.-H. Juang, W. Chou, and E. Buhrke, "Signal conditioning techniques for robust speech recognition," IEEE Signal Process. Lett., vol. 3, no. 4, pp. 107-109, Apr. 1996.
30. A. Sankar and C.-H. Lee, "A maximum-likelihood approach to stochastic matching for robust speech recognition," IEEE Trans. Speech Audio Process., vol. 4, no. 3, pp. 190-202, May 1996.
31. R. Singh, R. M. Stern, and B. Raj, "Signal and feature compensation methods for robust speech recognition," in Noise Reduction Speech Applications, G. M. Davis, Ed. Boca Raton, FL: CRC, 2002, pp. 219-244.
32. R. M. Stern, A. Acero, F.-H. Liu, and Y. Ohshima, "Signal processing for robust speech recognition," in Automatic Speech and Speaker Recognition: Advanced Topics, C.-H. Lee, F. Soong, and K. K. Paliwal, Eds. Norwell, MA: Kluwer, 1996, pp. 351-378.
33. A. Torre, A. M. Peinado, A. J. Rubio, V. E. Sanchez, and J. E. Diaz, "An application of minimum classification error to feature space transformations for speech recognition," Speech Commun., vol. 20, pp. 273-290, 1996.
34. S. Tsakalidis, V. Doumpiotis, and W. Byrne, "Discriminative linear transforms for feature normalization and speaker adaptation in HMM estimation," in Proc. ICSLP, 2002, pp. 2585-2588.
35. L. Wang and P. C. Woodland, "Discriminative adaptive training using the MPE criterion," in Proc. ASRU, 2003, pp. 279-284.
36. J. Wu and Q. Huo, "An environment compensated minimum classification error training approach and its evaluation on Aurora2 database," in Proc. ICSLP, Denver, CO, 2002, pp. I-453-I-456.
37. -, "Several HKU approaches for robust speech recognition and their evaluation on Aurora connected digit recognition tasks," in Proc. Eurospeech, Geneva, Switzerland, 2003, pp. 21-24.
38. J. Wu, Q. Huo, and D.-L. Zhu, "An environment compensated maximum likelihood training approach based on stochastic vector mapping," in Proc. ICASSP, Philadelphia, PA, 2005, pp. I-429-I-432.
39. J.-X. Wu, Z. Qi, C. Chan, and J. Li, "Speaker normalization by input space optimization for continuous density hidden Markov models," in 1994 Int. Symp. Speech, Image Process. Neural Netw., Hong Kong, China, Apr. 1994, pp. 682-685.
40. S. Young et al., The HTK Book (for HTK V3.0) July 2000.