This paper describes an efficient search algorithm for a high speed and high accuracy LVCSR system. A conventionally used lexical tree search is an efficient method, but has a problem in incorporating the language probability. To solve this problem, we propose in this paper a newefficient search algorithm incorporating the language model structure. In our developed LVCSR, 2-pass search algorithm is adopted to produce a word graph as an intermediate expression. The experimental results on the 20,000-word Japanese dictation task showed that the proposed method can reduce approximately half of the processing time without increasing any errors.
Cite as: Ogata, J., Ariki, Y. (2000) An efficient lexical tree search for large vocabulary continuous speech recognition. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 2, 967-970
@inproceedings{ogata00_icslp,
author={Jun Ogata and Yasuo Ariki},
title={{An efficient lexical tree search for large vocabulary continuous speech recognition}},
year=2000,
booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
pages={vol. 2, 967-970}
}