Sequential Estimation with Optimal Forgetting for Robust Speech Recognition

IEEE Transactions on Speech and Audio Processing

Volumn 12, Issue 1, 2004, Pages 19-26

  Afify, Mohamed ^a   Siohan, Olivier ^b  

^a Cairo University   (Egypt)

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

Author keywords

Noise compensation; Robust speech recognition; Speech recognition; Stochastic approximation

Indexed keywords

ALGORITHMS; DATABASE SYSTEMS; MAXIMUM LIKELIHOOD ESTIMATION; NONLINEAR EQUATIONS; OPTIMIZATION; ROBUSTNESS (CONTROL SYSTEMS); SPURIOUS SIGNAL NOISE;

NOISE COMPENSATION; SEQUENTIAL ALGORITHM;

SPEECH RECOGNITION;

EID: 0742324997     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/TSA.2003.819954     Document Type: Article

References (27)

1. Y. Gong, "Speech recognition in noisy environments: A survey," Speech Commun., vol. 16, pp. 261-291, Apr. 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. H. Lee and Q. Huo, "On adaptive decision rules and decision parameter adaptation for automatic speech recognition," Proc. IEEE, vol. 88, no. 88, pp. 1241-1269, Aug. 2000.
4. T. Matsouka and C. H. Lee, "A study of on-line bayesian adaptation for HMM-based speech recognition," in Proc. Eurospeech'93, Berlin, Germany, Sept. 1993, pp. 815-818.
5. Q. Huo and C. H. Lee, "On-line adaptive learning of the continuous density hidden Markov model based on approximate recursive bayes estimate, " IEEE Trans. Speech Audio Processing, vol. 5, pp. 161-172, Mar. 1997.
6. _, "On-line adaptive learning of the correlated continuous density hidden Markov model for speech recognition," IEEE Trans. Speech Audio Processing, vol. 6, pp. 386-397, July 1998.
7. Y. Gotoh and H. F. Silverman, "Incrmental ML estimation of HMM parameters for efficient training," in Proc. ICASSP'96, Apr. 1996, pp. 585-588.
8. V. Digalakis, "Online adaptation of hidden Markov models using incremental estimation algorithms," IEEE Trans. Speech Audio Processing, vol. 7, pp. 253-261, May 1999.
9. G. Zavaliagkos, R. Schwartz, and J. Makhoul, "Batch, incremental, and instantaneous adaptation techniques for speech recognition," in Proc. ICASSP'95, May 1995, pp. 696-699.
10. C. J. Leggetter and P. C. Woodland, "Flexible speaker adaptation using maximum-likelihood linear regression," in Proc. ARPA Workshop on Spoken Language Technology, Jan. 1995, pp. 110-115.
11. P. J. Moreno, B. Raj, and R. M. Stern, "A vector Taylor series approach for environment-independent speech recognition," in Proc. ICASSP, Atlanta, GA, May 1996, pp. 733-736.
12. N. S. Kim, "Statistical linear approximation for environment compensation," IEEE Signal Processing Lett., vol. 5, pp. 8-10, Jan. 1998.
13. _, "Nonstationary environment compensation based on sequential estimation," IEEE Signal Processing Lett., vol. 5, pp. 57-59, Mar. 1998.
14. M. Afify, "Sequential bias compensation for robust speech recognition," in Proc. EUROSPEECH, Budapest, Hungary, Sept. 1999.
15. M. Rahim and B. H. Juang, "Signal bias removal by maximum likelihood estimation for robust telephone speech recognition," IEEE Trans. Speech Audio Processing, vol. 4, Jan. 1996.
16. C. Mokbel, "MUSE: MUlti-path stochastic equalization: A theoretical framework to combine equalization and stochastic modeling," in Proc. ESCA Workshop on Robust Speech Recognition, Pont-a-Mousson, France, 1997, pp. 211-214.
17. L. Delphin-Poulat, C. Mokbel, and J. Idier, "Frame-synchronous stochastic matching based on Kullback-Leibler information," in Proc. ICASSP, Seattle, WA, Apr. 1998.
18. A. Sankar and C. H. Lee, "A maximum likelihood approach to stochastic matching for robust speech recognition," IEEE Trans. Speech Audio Processing, vol. 4, pp. 190-202, May 1996.
19. A. Benveniste, M. Metivier, and P. Priouret, Adaptive Algorithms and Stochastic Approximation. New York: Springer-Verlag, 1990.
20. V. Krishnamurthy and J. B. Moore, "On line estimation of hidden Markov model parameters based on the Kullback Leibler information measure, " IEEE Trans. Signal Processing, vol. 41, pp. 2557-2573, Aug. 1993.
21. E. Weinstein, M. Feder, and A. V. Oppenheim, "Sequential algorithms for parameter estimation based on Kullback Leibler information measure," IEEE Trans. Signal Processing, vol. 38, pp. 1652-1654, Sept. 1990.
22. M. J. F. Gales and S. J. Young, "Cepstral parameter compensation for HMM recognition in noise," Speech Commun., vol. 12, pp. 231-239, 1993.
23. D. M. Titterington, "Recursive parameter estimation using incomplete data," J. R. Statist. Soc. B, vol. 46, pp. 257-267, 1984.
24. H. J. Kushner and J. Yang, "Analysis of adaptive step-size SA algorithms for parameter tracking," IEEE Trans. Automat. Contr., vol. 40, pp. 1403-1410, Aug. 1995.
25. W. Reichl and W. Chou, "A unified approach to incorporating general features in decision tree based acoustic modeling," in Proc. ICASSP99, Phoenix, AZ, Mar. 1999.
26. Q. Zhou and W. Chou, "An approach to continuous speech recognition based on layered self-adjusting decoding graph," in Proc. ICASSP97, Munich, Germany, Apr. 1997.
27. M. Afify et al., "Evaluating the aurora connected digit recognition task - A bell labs approach," in Proc. EUROSPEECH, Sept. 2001, pp. 633-637.