In this paper we develop a method of representing the speech waveform in terms of a set of abstract, linguistic distinctions in order to derive a set of discriminative features for use in a speech recognizer. By combining the distinctive feature representation with our original waveform representation we are able to achieve a reduction in word error rate of 33 percent on an automatic speech recognition task.
Cite as: Eide, E. (2001) Distinctive features for use in an automatic speech recognition system. Proc. 7th European Conference on Speech Communication and Technology (Eurospeech 2001), 1613-1616, doi: 10.21437/Eurospeech.2001-195
@inproceedings{eide01_eurospeech,
author={Ellen Eide},
title={{Distinctive features for use in an automatic speech recognition system}},
year=2001,
booktitle={Proc. 7th European Conference on Speech Communication and Technology (Eurospeech 2001)},
pages={1613--1616},
doi={10.21437/Eurospeech.2001-195}
}