Automatic speech recognition (ASR) has been extensively studied during the past few decades, and some systems are already daily used in several domains. Most of present systems are based on statistical modeling, both at the acoustic and linguistic levels, not only. Speech recognition in adverse conditions has recently received increased attention since noise resistance has become one of the major bottlenecks for practical use of speech recognizers. After briefly recalling the basic principles of statistical approaches to ASR, we present the models that are presently investigated for increasing recognition performance.
Cite as: Haton, J.-P. (2004) Automatic speech recognition: past, present, and future. Proc. 9th Conference on Speech and Computer (SPECOM 2004), 3-7
@inproceedings{haton04_specom,
author={Jean-Paul Haton},
title={{Automatic speech recognition: past, present, and future}},
year=2004,
booktitle={Proc. 9th Conference on Speech and Computer (SPECOM 2004)},
pages={3--7}
}