A study of variable-parameter gaussian mixture hidden markov modeling for noisy speech recognition

IEEE Transactions on Audio, Speech and Language Processing

Volumn 15, Issue 4, 2007, Pages 1366-1376

  Cui, Xiaodong ^a,b   Gong, Yifan ^c  

^a UNIVERSITY OF CALIFORNIA   (United States)

^b IBM T J WATSON RESEARCH CENTER   (United States)

^c MICROSOFT   (United States)

Author keywords

Hidden Markov model; Noise robust speech recognition; Polynomial regression; Variable parameter

Indexed keywords

ACOUSTIC MODELS; CLEAN SPEECH; DEPENDENT VARIABLES; EMISSION PARAMETERS; EXPECTATION MAXI- MIZATION; GAUSSIAN MIXTURES; HIDDEN MARKOV MODELING; MAXIMUM-LIKELIHOOD ESTIMATIONS; NOISE ROBUST SPEECH RECOGNITION; NOISY ENVIRONMENTS; NOISY SPEECH RECOGNITION; POLYNOMIAL FUNCTIONS; POLYNOMIAL REGRESSION; RECOGNITION PERFORMANCE; RECOGNITION TIME; SPEECH DISTRIBUTIONS; SPEECH EVENTS; SPEECH SIGNALS; VARIABLE PARAMETER;

HIDDEN MARKOV MODELS; MAXIMUM LIKELIHOOD ESTIMATION; MIXTURES; OBJECT RECOGNITION; POLYNOMIAL APPROXIMATION; SPEECH ANALYSIS; SPEECH PROCESSING; TRELLIS CODES;

SPEECH RECOGNITION;

EID: 51849099743     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2006.889791     Document Type: Article

References (29)

1. 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.
2. Y. Gong, "Speech recognition in noisy environments: A survey," Speech Commun., vol. 16, pp. 261-291, 1995.
3. D. V. Compernolle, "Noise adaptation in a hidden Markov model speech recognition system," Comput. Speech Lang., vol. 3, no. 2, pp. 151-168, 1989.
4. C.-H. Lee, C.-H. Lin, and B.-H. Juang, "A study on speaker adaptation of the parameters of continuous density hidden Markov models," IEEE Trans. Signal Process., vol. 39, no. 4, pp. 806-814, Apr. 1991.
5. L. Neumeyer, A. Sankar, and V. Digalakis, "A comparative study of speaker adaptation techniques," in Proc. Eur. Conf. Speech Commun. Technol., 1995, pp. 1127-1130.
6. M. Gales, "Model-based techniques for noise robust speech recognition," Ph.D dissertation, Univ. Cambridge, Cambridge, U.K., 1995.
7. M. Gales and S. Young, "A fast and flexible implementation of parallel model combination," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., 1995, pp. 133-136.
8. Y. Chung, "A data-driven model parameter compensation method for noise-robust speech recognition," IEICE Trans. Inf. Syst., vol. E88-D, no. 3, pp. 432-434, 2005.
9. V. Stouten, H. V. Hamme, K. Demuynck, and P. Wambacq, "Robust speech recognition using model-based feature enhancement," in Proc. Eur. Conf. Speech Commun. Technol., 2003, pp. 17-20.
10. G. Saon, J. Huerta, and E.-E. Jan, "Robust digit recognition in noisy environments: the IBM Aurora 2 system," in Proc. Eur. Conf. Speech Commun. Technol., 2001, pp. 629-632.
11. M. Afify, H. Jiang, F. K. , C.-H. Lee, Q. Li, O. Siohan, F. Soong, and A. Surendran, "Evaluating the Aurora connected digit recognition task: A Bell Labs approach," in Proc. Eur. Conf. Speech Commun. Technol., 2001, pp. 633-636.
12. Q. Zhu, M. Iseli, X. Cui, and A. Alwan, "Noise robust feature extraction for ASR using the Aurora 2 database," in Proc. Eur. Conf. Speech Commun. Technol., 2001, pp. 341-344.
13. M. B. Islam, H. Matsumoto, and K. Yamamoto, "Evaluation of Mel-Wiener filter for Mel-LPC based speech recognition," in Proc. Int. Conf. Speech Comput., 2005, pp. 531-534.
14. M. Gales, ""nice" model-based compensation schemes for robust speech recognition," in Proc. ESCA-NATO Workshop Robust Speech Recognition for Unknown Commun. Channels, 1997, pp. 55-64.
15. C.-H. Lee, "On feature and model compensation approach to robust speech recognition," in Proc. ESCA-NATO Workshop Robust Speech Recognition for Unknown Commun. Channels, 1997, pp. 45-54.
16. S. Morii, T. Morii, and M. Hoshimi, "Noise robustness in speaker independent speech recognition," in Proc. Int. Conf. Spoken Lang. Process., 1990, pp. 1145-1148.
17. S. Furui, "Toward robust, speech recognition under adverse conditions," in ESCA Workshop Proc. Speech Process. Adverse Conditions, 1992, pp. 31-41.
18. S. Vaseghi, B. Milner, and J. Humphries, "Noisy speech recognition using cepstral-time features and spectral-time filters," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., 1994, pp. 65-68.
19. C. Mokbel and G. Chollet, "Speech recognition in adverse environments: speech enhancement and spectral transformations," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., 1991, pp. 925-928.
20. S. Das, R. Bakis, A. Nadas, B. Nahamoo, and M. Picheny, "Influence of background noise and microphone on the performance of the IBM TANGORA speech recognition system," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., 1993, pp. 71-74.
21. R. Lippmann, E. Martin, and D. Paul, "Multi-style training for robust isolated-word speech recognition," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., 1987, pp. 705-708.
22. M. Blanchet, J. Boudy, and P. Lockwood, "Environment adaptation for speech recognition in noise," in Proc. EUSIPCO, 1992, pp. 391-394.
23. Y. C. et al., "A robust front-end algorithm for distributed speech recognition," in Proc. Eur. Conf. Speech Commun. Technol., 2001.
24. X. Cui and Y. Gong, "Variable parameter Gaussian mixture hidden Markov modeling for speech recognition," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., 2003, vol. 1, pp. 12-15.
25. T. Kitamura, S. Ando, and E. Hayahara, "Speaker-independent spoken digit recognition in noisy environments using dynamic spectral features and neural networks," in Proc. Int. Conf. Spoken Lang. Process., 1992, pp. 699-702.
26. Y. Gong, "Noise-dependent Gaussian mixture classifiers for robust rejection decision," IEEE Trans. Speech Audio Process., vol. 10, no. 2, pp. 57-64, Feb. 2002.
27. -, "Noise-dependent open-set, speaker recognition using noise-dependent Gaussian mixture classifier," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., 2002.
28. A. Dempster, N. Laird, and D. Rubin, "Maximum likelihood from incomplete data via the EM algorithm," J. R. Statist. Soc., vol. 39, no. 1, pp. 1-38, 1977.
29. R. Martin, "An efficient algorithm to estimate instantanous SNR of speech signals," in Proc. Eur. Conf. Speech Commun. Technol., 1993, pp. 1093-1096.