抄録
In this paper, a new language model is proposed for speech recognition in conversational speech translation. In conversation, speech strongly depends on the previous utterance of the other participant. Applying this dependency in language modeling, we can reduce the speech recognition error rate. To this end, we propose the following new language model where the content of the previous utterance is expressed by an interlingual representation which is widely used in the spoken language translation research group C-star. The proposed method reduces word error rate by 6% (from 14.7% to 13.9%), confirming our expectations.
本文言語 | English |
---|---|
ホスト出版物のタイトル | 6th International Conference on Spoken Language Processing, ICSLP 2000 |
出版社 | International Speech Communication Association |
ISBN(電子版) | 7801501144, 9787801501141 |
出版ステータス | Published - 2000 |
外部発表 | はい |
イベント | 6th International Conference on Spoken Language Processing, ICSLP 2000 - Beijing, China 継続期間: 2000 10月 16 → 2000 10月 20 |
Other
Other | 6th International Conference on Spoken Language Processing, ICSLP 2000 |
---|---|
国/地域 | China |
City | Beijing |
Period | 00/10/16 → 00/10/20 |
ASJC Scopus subject areas
- 言語学および言語
- 言語および言語学