Auditory scene analysis and hidden Markov model recognition of speech in noise
- 19 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1 (15206149) , 401-404
- https://doi.org/10.1109/icassp.1995.479606
Abstract
We describe a novel paradigm for automatic speech recognition in noisy environments in which an initial stage of auditory scene analysis separates out the evidence for the speech to be recognised from the evidence for other sounds. In general, this evidence will be incomplete, since intruding sound sources will dominate some spectro-temporal regions. We generalise continuous-density hidden Markov model recognition to this 'occluded speech' case. The technique is based on estimating the probability that a Gaussian mixture density distribution for an auditory firing rate map will generate an observation such that the separated components are at their observed values and the remaining components are not greater than their values in the acoustic mixture. Experiments on isolated digit recognition in noise demonstrate the potential of the new approach to yield performance comparable to that of listeners.Keywords
This publication has 6 references indexed in Scilit:
- Computational auditory scene analysisComputer Speech & Language, 1994
- Computational auditory scene analysis: Exploiting principles of perceived continuitySpeech Communication, 1993
- Auditory Scene AnalysisPublished by MIT Press ,1990
- Simulation of auditory–neural transduction: Further studiesThe Journal of the Acoustical Society of America, 1988
- A neural cocktail-party processorBiological Cybernetics, 1986
- Perceptual Restoration of Missing Speech SoundsScience, 1970