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 Transactions on Speech and Audio Processing

Volumn 12, Issue 2, 2004, Pages 133-143

  Deng, Li ^a   Droppo, Jasha ^a   Acero, Alex ^a  

^a MICROSOFT RESEARCH   (United States)

Author keywords

Noise estimate; Noise robust ASR; Phase sensitive acoustic environment model; Sequential algorithm; Speech feature enhancement

Indexed keywords

ACOUSTIC DISTORTION; ACOUSTIC NOISE; ALGORITHMS; LINEAR SYSTEMS; MATHEMATICAL MODELS; PROBABILITY;

NOISE ESTIMATE; NOISE-ROBUST ASR; PHASE-SENSITIVE ACOUSTIC ENVIRONMENTAL MODEL; SEQUENTIAL ALGORITHM; SPEECH FEATURE ENHANCEMENT;

SPEECH RECOGNITION;

EID: 2142756950     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/TSA.2003.820201     Document Type: Article

References (25)

1. A. Acero, Acoustic and Environmental Robustness in Automatic Speech Recognition. Norwell, MA: Kluwer, 1993.
2. A. Acero, L. Deng, T. Kristjansson, and J. Zhang, "HMM adaptation using vector Taylor series for noisy speech recognition," in Proc. ICSLP, vol. 3, 2000, pp. 869-872.
3. M. Afify and O. Siohan, "Sequential noise estimation with optimal forgetting for robust speech recognition," in Proc. ICASSP, vol. 1, 2001, pp. 229-232.
4. A. Dempster, N. Laird, and D. Rubin, "Maximum likelihood from incomplete data via the EM algorithm," J. R. Statist. Soc., vol. B-39, pp. 1-38, 1977.
5. L. Deng, A. Acero, M. Plumpe, and X. D. Huang, "Large-vocabulary speech recognition under adverse acoustic environments," in Proc. ICSLP, vol. 3, 2000, pp. 806-809.
6. L. Deng, A. Acero, L. Jiang, J. Drpppo, and X. D. Huang, "High-performance robust speech recognition using stereo training data," in Proc. ICASSP, vol. 1, 2001, pp. 301-304.
7. L. Deng, J. Droppo, and A. Acero, "A Bayesian approach to speech feature enhancement using the dynamic cepstral prior," in Proc. ICASSP, vol. 1, May 2002, pp. 829-832.
8. _, "Recursive noise estimation using iterative stochastic approximation for stereo-based robust speech recognition," in Proc. Automatic Speech Recognition and Understanding, Trento, Italy, Dec. 2001.
9. _, "Recursive estimation of nonstationary noise using iterative stochastic approximation for robust speech recognition," IEEE Trans. Speech Audio Processing, vol. 11, pp. 568-580, Nov. 2003.
10. L. Deng and J. Ma, "Spontaneous speech recognition using a statistical coarticulatory model for the hidden vocal-tract-resonance dynamics," J. Acoust. Soc. Amer., vol. 108, no. 6, pp. 3036-3048, Dec. 2000.
11. J. Droppo, L. Deng, and A. Acero, "Evaluation of the SPLICE algorithm on the Aurora2 database," in Proc. Eurospeech, vol. 1, Sept. 2001, pp. 217-220.
12. Y. Ephraim, "Speech enhancement using a minimum mean-square error log-spectral amplitude estimator," IEEE Trans. Acoust., Speech, Signal Processing, vol. 33, pp. 443-445, 1985.
13. _, "Statistical-model-based speech enhancement systems," Proc. IEEE, vol. 80, pp. 1526-1555, Oct. 1992.
14. B. Frey, L. Deng, A. Acero, and T. Kristjansson, "ALGONQUIN: Iterating Laplace's method to remove multiple types of acoustic distortion for robust speech recognition," in Proc. Eurospeech, vol. 2, Sept. 2001, pp. 901-904.
15. H. Hirsch and D. Pearce, "The AURORA experimental framework for the performance evaluations of speech recognition systems under noisy conditions," in Proc. ISCA ITRW ASR2000 on Automatic Speech Recognition: Challenges for the Next Millennium, Paris, France, Sept 2000.
16. N. S. Kim, "Nonstationary environment compensation based on sequential estimation," IEEE Signal Processing Lett., vol. 5, pp. 57-60, 1998.
17. Speech Enhancement, J. S. Lim, Ed., Prentice-Hall, London, U.K., 1983.
18. P. Lockwood and J. Boudy, "Experiments with a nonlinear spectral subtraction (NSS), hidden Markov models and the projection for robust speech recognition in cars," Speech Commun., vol. 11, pp. 215-228, 1992.
19. J. Mendel, Lessons in Estimation Theory for Signal Processing, Communications and Control. Englewood Cliffs, NJ: Prentice-Hall, 1995.
20. P. Moreno, B. Raj, and R. Stern, "A vector Taylor series approach for environment-independent speech recognition," in Proc. ICASSP, vol. 2, 1996, pp. 733-736.
21. ESE2 Special Sessions on Noise Robust Recognition, Proc. Eurospeech, D. Pearce, Ed., Aalborg, Denmark, Sept. 2001.
22. J. Segura, A. Torre, M. Benitez, and A. Peinado, "Model-based compensation of the additive noise for continuous speech recognition: Experiments using the AURORA2 database and tasks," in Proc. Eurospeech, Aalborg, Denmark, Sept. 2001.
23. D. M. Titterington, "Recursive parameter estimation using incomplete data," J. R. Statist. Soc. B, vol. 46, pp. 257-267, 1984.
24. Speech Commun., vol. 34, O. Viikki, Ed., 2001.
25. Q. Zhu and A. Alwan, "The effect of additive noise on speech amplitude spectra: A quantitative analysis," IEEE Signal Processing Lett., vol. 9, pp. 275-277, Sept. 2002.