Model-Based Techniques For Noise Robust Speech Recognition

DMCA

Model-Based Techniques For Noise Robust Speech Recognition (1995)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Mark John , Mark J. F. Gales , Caius College

BibTeX

@MISC{John95model-basedtechniques,
    author = {Mark John and Mark J. F. Gales and Caius College},
    title = {Model-Based Techniques For Noise Robust Speech Recognition},
    year = {1995}
}

OpenURL

Abstract

observed in terms of both a distance measure, the average Kullback-Leibler number on a feature vector component level, and the effect on word accuracy. For best performance in noise-corrupted environments, it is necessary to compensate all these parameters. Various methods for compensating the HMMs are described. These may be split into two classes. The first, non-iterative PMC, assumes that the frame/state component alignment associated with the speech models and the clean speech data is unaltered by the addition of noise. This implies that the corrupted-speech distributions are approximately Gaussian, which is known to be false. However, this assumption allows rapid adaptation of the model parameters. The second class of PMC is iterative PMC, where only the frame/state alignment is assumed unaltered. By allowing the component alignment within a state to vary, it is possible to better model the corrupted-speech distribution. One implementation is described, Data-driven Parallel Model

Keyphrases

noise robust speech recognition model-based technique corrupted-speech distribution distance measure various method component alignment speech model word accuracy clean speech data model parameter frame state alignment iterative pmc rapid adaptation non-iterative pmc frame state component alignment feature vector component level data-driven parallel model second class noise-corrupted environment average kullback-leibler number

DMCA