Model-based feature enhancement with uncertainty decoding for noise robust ASR

Speech Communication

Volumn 48, Issue 11, 2006, Pages 1502-1514

  Stouten, Veronique ^a   Van hamme, Hugo ^a   Wambacq, Patrick ^a  

^a UNIVERSITY OF LEUVEN   (Belgium)

Author keywords

Additive noise; Convolutional noise; Model based feature enhancement; Noise robust speech recognition; Uncertainty decoding

Indexed keywords

ACOUSTIC NOISE; DECODING; FEATURE EXTRACTION; LEARNING SYSTEMS; MAXIMUM LIKELIHOOD ESTIMATION; PROBABILITY; PROBABILITY DENSITY FUNCTION; ROBUSTNESS (CONTROL SYSTEMS);

ADDITIVE NOISE; CONVOLUTIONAL NOISE; MODEL-BASED FEATURE ENHANCEMENT (MBFE); NOISE ROBUST SPEECH RECOGNITION; UNCERTAINTY DECODING;

SPEECH RECOGNITION;

EID: 33750376174     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.specom.2005.12.006     Document Type: Article

References (28)

1. Arrowood, J., Clements, M., 2002. Using observation uncertainty in HMM decoding. In: Proc. ICSLP, Denver, Colorado, pp. 1561-1564.
2. Attias, H., Deng, L., Acero, A., Platt, J., 2001. A new method for speech denoising and robust speech recognition using probabilistic models for clean speech and for noise. In: Proc. EUROSPEECH, Aalborg, Denmark, pp. 1903-1906.
3. Benitez, M., Segura, J., dela Torre, A., Ramirez, J., Rubio, A., 2004. Including uncertainty of speech observations in robust speech recognition. In: Proc. ICSLP, Jeju Island, Korea, pp. 137-140.
4. Bernard, A., Gong, Y., Cui, X., 2004. Can back-ends be more robust than font-ends? Investigation over the Aurora-2 database. In: Proc. ICASSP, Montreal, Canada, pp. 1025-1028.
5. Cooke M., Green P., Josifovski L., and Vizinho A. Robust automatic speech recognition with missing and unreliable acoustic data. Speech Comm. 34 3 (2001) 267-285
6. Dempster A.P., Laird N.M., and Rubin D.B. Maximum likelihood from incomplete data via the EM-algorithm. J. Roy. Statist. Soc. B 39 (1977) 1-38
7. Demuynck K., Duchateau J., Van Compernolle D., and Wambacq P. An efficient search space representation for large vocabulary continuous speech recognition. Speech Comm. 30 1 (2000) 37-53
8. Deng, L., Droppo, J., Acero, A., 2002. Exploiting variances in robust feature extraction based on a parametric model of speech distortion. In: Proc. ICSLP, Denver, Colorado, pp. 2449-2452.
9. Droppo, J., Deng, L., Acero, A., 2001. Evaluation of the SPLICE algorithm on the Aurora2 database. In: Proc. EUROSPEECH, Aalborg, Denmark, pp. 217-220.
10. Duchateau J., Demuynck K., and Van Compernolle D. Fast and accurate acoustic modelling with semi-continuous HMMs. Speech Comm. 24 1 (1998) 5-17
11. Duchateau, J., Demuynck, K., Van Compernolle, D., Wambacq, P., 2001. Class definition in discriminant feature analysis. In: Proc. EUROSPEECH, Vol. III, Aalborg, Denmark, pp. 1621-1624.
12. Ephraim, Y., 1990. A minimum mean square error approach for speech enhancement. In: Proc. ICASSP, New Mexico, USA, pp. 829-832.
13. Ephraim Y., and Malah D. Speech enhancement using a minimum mean-square error short-time spectral amplitude estimator. IEEE Trans. ASSP 32 6 (1984) 1109-1121
14. ETSI ES 202 050 v1.1.1, 2002. Speech processing, transmission and quality aspects (STQ); distributed speech recognition; advanced front-end feature extraction algorithm; compression algorithm.
15. Gales, M., 1995. Model-based techniques for noise robust speech recognition. Ph.D. thesis, University of Cambridge.
16. Gong Y. Speech recognition in noisy environments: a survey. Speech Comm. 16 3 (1995) 261-291
17. Holmes, J., Holmes, W., Garner, P., 1997. Using formant frequencies in speech recognition. In: Proc. EUROSPEECH, Rhodes, Greece, pp. 2083-2086.
18. HTK homepage: .
19. Kristjansson, T., Frey, B., 2002. Accounting for uncertainty in observations: a new paradigm for robust automatic speech recognition. In: Proc. ICASSP, Orlando, Florida, pp. 61-64.
20. Kristjansson, T., Frey, B., Deng, L., 2001. Joint estimation of noise and channel distortion in a generalized EM framework. In: Proc. ASRU, Madonna di Campiglio, Italy.
21. Macho, D., Mauuary, L., Noé, B., Cheng, Y., Ealey, D., Jouvet, D., Kelleher, H., Pearce, D., Saadoun, F., 2002. Evaluation of a noise-robust DSR front-end on Aurora databases. In: Proc. ICSLP, Denver, Colorado, USA, pp. 17-20.
22. Sameti H., Sheikhzadeh H., Deng L., and Brennan R. HMM-based strategies for enhancement of speech signals embedded in non-stationary noise. IEEE Trans. SAP 6 5 (1998) 445-455
23. Stouten, V., Van hamme, H., Demuynck, K., Wambacq, P., 2003. Robust speech recognition using model-based feature enhancement. In: Proc. EUROSPEECH, Geneva, Switzerland, pp. 17-20.
24. Stouten, V., Van hamme, H., Wambacq, P., 2004a. Accounting for the uncertainty of speech estimates in the context of model-based feature enhancement. In: Proc. ICSLP, Vol. I, Jeju Island, Korea, pp. 105-108.
25. Stouten, V., Van hamme, H., Wambacq, P., 2004b. Joint removal of additive and convolutional noise with model-based feature enhancement. In: Proc. ICASSP, Vol. I, Montreal, Canada, pp. 949-952.
26. Van Compernolle, D., 1987. Increased noise immunity in large vocabulary speech recognition with the aid of spectral subtraction. In: Proc. International Conference on Acoustics, Speech and Signal Processing, Dallas, TX, USA, pp. 1143-1146.
27. Varga, A., Moore, R., 1990. Hidden Markov model decomposition of speech and noise. In: Proc. ICASSP, Albuquerque, USA, pp. 845-848.
28. Yamaguchi, Y., Takahashi, S., Sagayama, S., 1997. Fast adaptation of acoustic models to environmental noise using Jacobian adaptation algorithm. In: Proc. EUROSPEECH, Rhodes, Greece, pp. 2051-2054.