Can back-ends be more robust than front-ends? Investigation over the Aurora-2 database

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 1, Issue , 2004, Pages

  Bernard, Alexis ^a   Gong, Yifan ^a   Cui, Xiaodong ^b  

^a TEXAS INSTRUMENTS   (United States)

^b UNIVERSITY OF CALIFORNIA   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

EXPECTATION-MAXIMIZATION (EM); HIDDEN MARKOV MODELS (HMM); SPEECH ACOUSTIC MODELS; VITERBI DECODING;

CONVOLUTION; DATA ACQUISITION; DATABASE SYSTEMS; MARKOV PROCESSES; MATHEMATICAL MODELS; NOISE ABATEMENT; PROBABILITY; SIGNAL TO NOISE RATIO; VECTORS;

SPEECH RECOGNITION;

EID: 4544310318     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (14)

1. Y. Gong, "Speech recognition in noisy environments: A survey," Speech Communication, vol.16, no. 3, pp. 261-291, April 1995.
2. M. Lieb and A. Fischer, "Experiments with the Philips continuous ASR system on the AURORA noisy digits database," in Proceedings of European Conference on Speech Communication and Technology, 2001.
3. D. Macho, L. Mauuary, B. Noe, Y. M. Cheng, D. Ealey, D. Jouvet, H. Kelleher, D. Pearce, and F. Saadoun, "Evaluation of a noise-robust DSR front-end on AURORA databases," in Proc. Int. Conf. on Spoken Language Processing, Colorado, USA, September 2002, pp. 17-20.
4. M. Afify, Y. Gong, and J.-P. Haton, "A general joint additive and convolutive bias compensation approach applied to noisy lombard speech recognition," IEEE Trans. on Speech and Audio Processing, vol.6, no. 6, pp. 524-538, November 1998.
5. J. L. Gauvain, L. Lamel, M. Adda-Decker, and D. Matrouf, "Developments in continuous speech dictation using the ARPA NAB news task," in Proc. of IEEE Int. Conf. on Acoustics, Speech and Signal Processing, Detroit, 1996, pp. 73-76.
6. Y. Minami and S. Furui, "A maximum likelihood procedure for a universal adaptation method based on HMM composition," in Proc. of IEEE Int. Conf. on Acoustics, Speech and Signal Processing, Detroit, 1995, pp. 129-132.
7. M. J. F. Gales, Model-Based Techniques for Noise Robust Speech Recognition, Ph.D. thesis, Cambridge University, U.K., 1995.
8. Y. Gong, "A robust continuous speech recognition system for mobile information devices (invited paper)," in Proc. of International Workshop on Hands-Free Speech Communication, Kyoto, Japan, April 2001.
9. Y. Gong, "Model-space compensation of microphone and noise for speaker-independent speech recognition," in Proc. of IEEE Int. Conf. on Acoustics, Speech and Signal Processing, Hong Kong, April 2003.
10. S. Sagayama, Y. Yamaguchi, and S. Takahashi, "Jacobian adaptation of noisy speech models," in Proceedings of IEEE Automatic Speech Recognition Workshop, Santa Barbara, CA, USA, DEC 1997, pp. 396-403, IEEE Signal Processing Society.
11. N. S. Kim, "Statistical linear approximation for environment compensation," IEEE Signal Processing Letters, vol.5, no. 1, pp. 8-10, Jan. 1998.
12. M. J. F. Gales and S. Young, "An improved approach to the hidden Markov model decomposition of speech and noise," in Proc. of IEEE Int. Conf. on Acoustics, Speech and Signal Processing, U.S.A., April 1992, vol.I, pp. 233-236.
13. A. P. Dempster, N. M. Laird, and D. B. Rubin, "Maximum likelihood from incomplete data via the EM algorithm," Journal of the Royal Statistical Society, vol.39, no. 1, pp. 1-38, 1977.
14. Y. Gong, "A method of joint compensation of additive and convolutive distortions for speaker-independent speech recognition," IEEE Trans. on Speech and Audio Processing, (submitted for publication) 2002.