In this paper, we present the results that our n-gram based word string language model, combined with speaker and noise adaptation of the acoustic model, improves recognition performance of noisy broadcast news speech. The focus was brought into a remedy against recognition errors of short words. The word string language models based on POS and n-gram fre- quency reduced deletion errors by 17%, insertion errors by 20%, and substitution errors by 3% in Japanese TV broadcast news speech recognition.
Cite as: Takagi, K., Oguro, R., Ozeki, K. (2000) Effects of word string language models on noisy broadcast news speech recognition. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 1, 154-157
@inproceedings{takagi00_icslp,
author={Kazuyuki Takagi and Rei Oguro and Kazuhiko Ozeki},
title={{Effects of word string language models on noisy broadcast news speech recognition}},
year=2000,
booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
pages={vol. 1, 154-157}
}