Improving performance of spectral subtraction in speech recognition using a model for additive noise

IEEE Transactions on Speech and Audio Processing

Volumn 6, Issue 6, 1998, Pages 579-582

  Yoma, Nestor Becerra ^a,b   McInnes, Fergus R ^a   Jack, Mervyn A ^a  

^a UNIVERSITY OF CAMPINAS   (Brazil)

^b UNIVERSITY OF EDINBURGH   (United Kingdom)

Author keywords

Additive noise; Cepstral mean normalization; Convolutional noise; Spectral subtraction; Speech recognition; Weighted matching algorithms

Indexed keywords

ALGORITHMS; CONVOLUTION; MARKOV PROCESSES; MATHEMATICAL MODELS; SIGNAL TO NOISE RATIO; SPURIOUS SIGNAL NOISE;

ADDITIVE NOISE; CEPSTRAL MEAN NORMALIZATION; CONVOLUTIONAL NOISE; SPECTRAL SUBTRACTION; WEIGHTED MATCHING ALGORITHMS;

SPEECH RECOGNITION;

EID: 0032205798     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/89.725325     Document Type: Article

References (6)

1. N. B. Yoma, F. R. Mclnnes, and M. A. Jack,"Weighted matching algorithms and reliability in noise cancelling by spectral subtraction," in Proc. ICASSP, 1997, pp. 1171-1174.
2. H. Kobatake and Y. Matsunoo,"Degraded word recognition based on segmental signal-to-noise ratio weighting," in Proc. ICASSP, 1994, vol. I, pp. 425-428.
3. A. Varga, H. J. M. Steeneken, M. Tomlinson, and D. Jones,"The Noisex-92 study on the effect of additive noise in automatic speech recognition," Tech. Rep., DRA Speech Res. Unit, Malvern, Worcestershire, U.K., 1992.
4. D. Van Compernolle,"Noise adaptation in a hidden Markov model speech recognition system," Comput. Speech Lang., vol. 3, pp. 151-167, 1989.
5. M. F Gales,"Model-based techniques for noise robust speech recognition," Ph.D. dissertation, Dept. Eng., Cambridge Univ., U.K., Sept. 1995.
6. T. Claes and D. Van Compernolle,"SNR-normalization for robust speech recognition," in Proc. ICASSP, 1996, pp. 331-334.