Stochastic features for noise robust speech recognition
- 27 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2 (15206149) , 633-636
- https://doi.org/10.1109/icassp.1998.675344
Abstract
This paper describes a novel technique for noise robust speech recognition, which can incorporate the characteristics of noise distribution directly in features. The feature itself of each analysis frame has a stochastic form, which can represent the probability density function of the estimated speech component in the noisy speech. Using the sequence of the probability density functions of the estimated speech components and hidden Markov modelling of clean speech, the observation probability of the noisy speech is calculated. In the whole process of the technique, the explicit information on the SNR is not used. The technique is evaluated by large vocabulary isolated word recognition under car noise environment, and is found to have clearly outperformed nonlinear spectral subtraction (with between 13% and 44% reduction in recognition errors).Keywords
This publication has 9 references indexed in Scilit:
- Enhancement of speech corrupted by acoustic noisePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Hidden Markov model decomposition of speech and noisePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Speech enhancement by spectral magnitude estimation — A unifying approachSpeech Communication, 1996
- Speech recognition in noisy environments: A surveySpeech Communication, 1995
- Cepstral parameter compensation for HMM recognition in noiseSpeech Communication, 1993
- Experiments with a nonlinear spectral subtractor (NSS), Hidden Markov models and the projection, for robust speech recognition in carsSpeech Communication, 1992
- An improved approach to the hidden Markov model decomposition of speech and noisePublished by Institute of Electrical and Electronics Engineers (IEEE) ,1992
- Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentencesIEEE Transactions on Acoustics, Speech, and Signal Processing, 1980
- Suppression of acoustic noise in speech using spectral subtractionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1979