A link between cepstral shrinking and the weighted product rule in audio-visual speech recognition
Conference Paper, Proceedings of 7th International Conference on Spoken Language Processing (ICSLP '02), pp. 1961 - 1964, September, 2002
Abstract
The weighted product rule has been shown empirically to be of great benefit in audio-visual speech recognition (AVSR), for isolated word recognition tasks. A firm theoretical basis for the selection of effective weights is of considerable interest to the audio-visual speech processing community. In this paper a clear link is established between the selection of effective weightings and the approximately isotropic shrinkage that the distribution of acoustic cepstral features undergo in the presence of additive noise. An elucidation of the theoretical relationship between the cepstral shrinkage and the variance of the HMM audio log-likelihoods is then explored.
BibTeX
@conference{Lucey-2002-121089,author = {S. Lucey and S. Sridharan and V. Chandran},
title = {A link between cepstral shrinking and the weighted product rule in audio-visual speech recognition},
booktitle = {Proceedings of 7th International Conference on Spoken Language Processing (ICSLP '02)},
year = {2002},
month = {September},
pages = {1961 - 1964},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.