In this paper, we present an ecient calculation of the factored LM probabilities for speeding up the large vocabulary continuous speech recognition. We introduced a novel technique based on the independent calculation of the factored LM probability. The basic idea of the proposed method is that each factored LM probability is calculated on-demand for a new combination of a previous word hypothesis and a LM look-ahead tree node, instead of calculating all the factored LM probabilities over the tree at a time. The speaker-independent continuous speech recognition experiment was performed for 20 speakers on a 60k word newspaper dictation task. As a result, the proposed method achieved 25% improvement in speed.
Cite as: Yamamoto, H., Fukada, T., Komori, Y. (2000) Effective lexical tree search for large vocabulary continuous speech recognition. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 4, 322-325, doi: 10.21437/ICSLP.2000-815
@inproceedings{yamamoto00d_icslp,
author={Hiroki Yamamoto and Toshiaki Fukada and Yasuhiro Komori},
title={{Effective lexical tree search for large vocabulary continuous speech recognition}},
year=2000,
booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
pages={vol. 4, 322-325},
doi={10.21437/ICSLP.2000-815}
}