An embedded knowledge integration for hybrid language modeling

Shuwu Zhang, Hirofumi Yamamoto, Yoshinori Sagisaka

研究成果: Conference contribution

抄録

This paper describes an embedded architecture to couple utilizable language knowledge and innovative language models, as well as modeling approaches, for intensive language modeling in speech recognition. In this embedded mechanism, three innovative language modeling approaches at different levels, ie., composite N-gram, dis tance-related unit association maximum entropy (DU-AME), and linkgram, have different functions to extend the definitions of basic language units, favorably improve the underlying model instead of conventional N-grams and provide effective combination with longer history syntactic lnk dependency knowledge, respectively. In this threelevel hybrid language modeling, each lower level modeling serves the higher level modeling(s). The results in each level are well utized or embedded in the higher level(s). These models can be trained level by level Accordingly, some prospective language constraints can finally be embedded in a wellorganized hybrid model. Experimental data based on the embedded modeling show that the hybrid model reduces WER 14.5% compared with the conventional word-based bigram model As a result, it can be expected to improve the conventional statistical language modelng.

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 162000 10月 20

出版物シリーズ

名前6th International Conference on Spoken Language Processing, ICSLP 2000

Other

Other6th International Conference on Spoken Language Processing, ICSLP 2000
国/地域China
CityBeijing
Period00/10/1600/10/20

ASJC Scopus subject areas

  • 言語学および言語
  • 言語および言語学

フィンガープリント

「An embedded knowledge integration for hybrid language modeling」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル