Utilisation des Modèles de Markov Cachés pour le Débruitage

Utilisation des Modèles de Markov Cachés pour le Débruitage

D. Matrouf J.L. Gauvain 

LIMSI-CNRS, B.P. 133, 91403 Orsay cedex, France

Corresponding Author Email: 
23 July 1999
30 June 2001
| Citation


1. Introduction
2. Le Processus de Débruitage
2. Le Processus de Débruitage
3. Estimation des Probabilités a Posteriori
4. La Combinaison Parallèle de Données
5. Résultats Expérimentaux
6. Conclusion

[1] S.F. Boll, “Suppression of Acoustic Noise in Speech Using Spectral Subtraction,” IEEE, pp. 113-120, 1979.

[2] M. Berouti, R. Schwartz, J. Makhoul, “Enhancement of Speech Corrupted by Acoustic Noise”, ICASSP-79, pp. 208-211. 

[3] Y. Ephraim, D. Malah, B.H. Juang, “On the Application of Hidden Markov Models for Enhancing Speech,” IEEE Transactions on Acoustics, Speech, and Signal Processing, Vol. 37. No. 12. December 1989. 

[4] M.J.F. Gales, S.J. Young, “Robust speech recognition in additive and convolutional noise using parallel model combination,” Computer Speech & Language, 9(4), pp. 289-307, 1995. 

[5] M.J.F. Gales, S.J. Young, “A fast and flexible implementation of parallel model combination,” ICASSP-95, pp. 133-136. 

[6] J.L. Gauvain, L. Lamel, G. Adda, D. Matrouf, “Developments in Continuous Speech Dictation using the 1995 ARPA NAB News Task”, ICASSP-96, pp. 73-76. 

[7] F. Martin, K. Shikano, Y. Minami, “Recognition of Noisy Speech by Composition of Hidden Markov Models,” Eurospeech'93,pp. 1031-1034. 

[8] D. Matrouf, J.L. Gauvain, “Model compensation for noises in test and training data,” ICASSP-97, pp. 831-834. 

[9] C. E. Mokbel, G. F. A. Chollet, “Automatic Word Recognition in Cars,” IEEE Transactions on Speech and Audio Processing, Vol. 3. No. 3. September 95. 

[10] L. Lamel, S. Rosset, S. Bennacef, H. BonneauMaynard, L. Devillers, J.L. Gauvain, “Development of Spoken Language Corpora for Travel Information,” Eurospeech'95, pp. 19611964. 

[11] C.J. Leggetter, P.C. Woodland, “Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models”, Computer Speech & Language, pp. 171-185, 1995. 

[12] B. T. Logan, A. J. Robinson, “Enhancement and Recognition of Noisy Speech within an AutoRegressive HMM Framework Using Noise Estimates from The Noisy Signal,” ICASSP-97, pp. 843-846.

[13] P. Lockwood, J. Boudy, M. Blanchet, “Non-linear Spectral Subtraction (NSS), and Hidden Markov Models for robust speech recognition in car noise environments,” ICASSP-92, pp. 265-268.

[14] J.S. Lim,A.V. Oppenheim, “All-pole modeling of degraded speech,” IEEE Trans. Acoust., Speech, Signal Process.,Vol. 26, pp. 197-210, June 1978. 

[15] A.B. Poritz, “Linear predictive hidden Markov models and the speech signal”, ICASSP-82, pp. 1291-1294. 

[16] B.H. Juang,“Maximum-Liklihood Estimation for Mixture Multivariate Stochastic Observations of Markov Chains”, AT&T Technical Journal, pp. 1235-1249, July-August 1985. 

[17] A.P. Varga, H.J.M Steeneken, M. Tomlinson, D. Jones, “The NOISEX-92 study on the effect of additive noise on automatic speech recognition,” In Technical Report, DRA Speech Research Unit, 1992.