This paper describes methods developed to improve the performance of a preselection algorithm in a large vocabulary isolated word recognizer. First we investigate ways for optimizing the phonetic representations of the words in the lexicon (the base forms of which are obtained from a grapheme-to-phoneme converter) in such a way that the inherent limitations of the front-end are taken into account and where possible are remedied. Then an attempt is made to improve the quality of the symbol strings produced by the acoustic front-end. keywords: Isolated-Word-Recognition preselection lexicon
Cite as: Drexler, H., Roddeman, R., Boves, L., Strik, H. (1991) Optimizing lexical fast search in a large vocabulary isolated word speech recognition system. Proc. 2nd European Conference on Speech Communication and Technology (Eurospeech 1991), 1401-1404, doi: 10.21437/Eurospeech.1991-320
@inproceedings{drexler91_eurospeech,
author={H. Drexler and R. Roddeman and Louis Boves and Helmer Strik},
title={{Optimizing lexical fast search in a large vocabulary isolated word speech recognition system}},
year=1991,
booktitle={Proc. 2nd European Conference on Speech Communication and Technology (Eurospeech 1991)},
pages={1401--1404},
doi={10.21437/Eurospeech.1991-320}
}