DMCA
Robust Speech Recognition Using Articulatory Information (1999)
Cached
Download Links
BibTeX
@MISC{Der99robustspeech,
author = {Der Technischen Fakultät Der and Universität Bielefeld and Katrin Kirchhoff and Bielefeld Juni},
title = {Robust Speech Recognition Using Articulatory Information},
year = {1999}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Current automatic speech recognition systems make use of a single source of information about their input, viz. a preprocessed form of the acoustic speech signal, which encodes the timefrequency distribution of signal energy. The goal of this thesis is to investigate the benefits of integrating articulatory information into state-of-the art speech recognizers, either as a genuine alternative to standard acoustic representations, or as an additional source of information. Articulatory information is represented in terms of abstract articulatory classes or "features", which are extracted from the speech signal by means of statistical classifiers. A higher-level classifier then combines the scores for these features and maps them to standard subword unit probabilities. The main motivation for this approach is to improve the robustness of speech recognition systems in adverse acoustic environments, such as background noise. Typically, recognition systems show a sharp decline of performance...
Keyphrases
articulatory information higher-level classifier recognition system genuine alternative abstract articulatory class current automatic speech recognition system signal energy additional source acoustic representation subword unit probability sharp decline single source timefrequency distribution adverse acoustic environment statistical classifier preprocessed form speech recognition system main motivation speech signal background noise state-of-the art speech recognizers acoustic speech signal
