This paper shows that a domain-dependent language model and states-kipped HMMs can achieve improvements in word recognition accuracy on a broadcast sports news transcription task. Although a domain-dependent language model is much better than a general model in terms of word error rate, the smaller training corpus for a special topic relative to the general news corpus leads to problems especially in higher-order n-gram probability estimation. In this paper, we tried a linear interpolation technique to smooth out unreliable higher-order n-gram probabilities using more reliable lower-order n-gram probabilities. We also applied a language model adaptation technique by using news manuscripts on sports topics. For acoustic modeling, we added two state-skipping paths to three-state HMMs to deal with phonemes of duration less than three frames. Overall, we reduced the word error rate from 15.1% to 5.8%, and achieved sufficient performance to realize real-time subtitling services.
Cite as: Matsui, A., Segi, H., Kobayashi, A., Imai, T., Ando, A. (2001) Speech recognition of broadcast sports news. Proc. 7th European Conference on Speech Communication and Technology (Eurospeech 2001), 709-712, doi: 10.21437/Eurospeech.2001-214
@inproceedings{matsui01_eurospeech,
author={Atsushi Matsui and Hiroyuki Segi and Akio Kobayashi and Toru Imai and Akio Ando},
title={{Speech recognition of broadcast sports news}},
year=2001,
booktitle={Proc. 7th European Conference on Speech Communication and Technology (Eurospeech 2001)},
pages={709--712},
doi={10.21437/Eurospeech.2001-214}
}