On-line Gaussian mixture modeling in the log-power domain for signal-to-noise ratio estimation and speech enhancement

Speech Communication

Volumn 48, Issue 11, 2006, Pages 1515-1527

  Dat, Tran Huy ^a   Takeda, Kazuya ^b   Itakura, Fumitada ^c  

^a INSTITUTE FOR INFOCOMM RESEARCH   (Singapore)

^b NAGOYA UNIVERSITY   (Japan)

^c MEIJO UNIVERSITY   (Japan)

Author keywords

Cumulative distribution function equalization; Gaussian mixture modeling; Log normal distributions; Segmental SNR; Speech enhancement

Indexed keywords

ESTIMATION; FUNCTION EVALUATION; MATHEMATICAL MODELS; SPEECH ANALYSIS; SPEECH RECOGNITION; STATISTICAL METHODS;

CUMULATIVE DISTRIBUTION FUNCTION EQUALIZATION; GAUSSIAN MIXTURE MODELING; LOG-NORMAL DISTRIBUTIONS; SEGMENTAL SNR; SPEECH ENHANCEMENT;

SIGNAL TO NOISE RATIO;

EID: 33750380834     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.specom.2006.06.009     Document Type: Article

References (21)

1. Acero A. Acoustical and Environmental Robustness in Automatic Speech Recognition (1993), Kluwer Academic Publishers
2. Aulay Mc., and Malpass M. Speech enhancement using a soft-decision noise suppression filter. IEEE Trans. ASSP 28 2 (1980) 137-145
3. Burshtein D., and Gannot S. Speech enhancement using a mixture-maximum model. IEEE Trans. ASSP 10 6 (2002) 341-351
4. Cohen I. Noise spectrum estimation in adverse environments. IEEE Trans. ASSP 20 (2002)
5. Dasgusta, S., 1995. Learning Gaussian mixtures. In: Proceedings of IEEE ICASSP.
6. Dempster A., Laird N., and Rubin D. Maximum-likelihood from incomplete data via the EM algorithm. J. Roy. Stat. Soc. Ser. B 39 (1977)
7. Ephraim Y., and Malah D. Speech enhancement using a minimum mean-square error short-time spectral amplitude estimator. IEEE Trans. ASSP ASSP-32 (1984) 1109-1121
8. ETSI standard document, 2000. ETSI ES201 108 v1.1.2, 2000-04.
9. Hastie T., Tibshinari R., and Friedman J. The Elements of Statistical Learning (2001), Springer
10. Hirsch, H., Ehrlicher, C., 1999. Noise estimation techniques for robust speech recognition. In: Proceedings of IEEE RMSRAC.
11. Hirsch, H., Pearce, D., 2000. The AURORA experimental framework for the performance evaluation of speech recognition systems under noisy conditions. In: Proceedings of ISCA ITRW ASR.
12. Itou K. JNAS: Japanese speech corpus for large vocabulary continuous speech recognition research. J. Acoust. Soc. Jpn. (E) 20 3 (1999) 199-206
13. Korthauer, A., 1999. Robust estimation of the SNR of noisy speech for the quality evaluation of speech databases. In: Proceedings of IEEE RMSRAC.
14. Martin R. Noise power spectral estimation based on optimal smoothing and minimum statistics. IEEE Trans. ASSP 9 5 (2001) 504-512
15. Nakamura, S., 2003. Data collection and evaluation of AURORA-2 Japanese corpus. In: Proceedings of IEEE ASRU 2003, pp. 619-632.
16. NIST Speech Quality Assurance (SPQA) Package. Available from: .
17. Reynolds D., and Rose R. Robust text-independent speaker identification using gaussian mixture speaker models. IEEE Trans. ASSP 3 1 (1995) 72-83
18. Stahl, V., Fischer, A., Bippus, R., 2000. Quantile based noise estimation for spectral subtraction and wiener filtering. In: Proceedings of ICSLP.
19. The HTK Book, 1995. Version 2.2, Entropic.
20. Van Compernolle D. Noise adaptation in a hidden Markov model speech recognition system. Comput. Speech Language 13 1 (1989) 151-167
21. Zolfaghari, P., Robinson, T., 1996. Formant analysis using mixtures of Gaussian. In: Proceedings of IEEE ICSLP.