Structured language model for class identification of out-of-vocabulary words arising from multiple word-classes

Shigehiko Onishi, Hirofumi Yamamoto, Yoshinori Sagisaka

研究成果: Conference contribution

抄録

A structured language model (STLM) is proposed to cope with out-of-vocabulary (OOV) words coming from multiple wond-classes. tie STLM aims at independently modeling the classes without interference and identifying the class of words arising from multiple word-classes. The STLM consists of the conventional word-class N-gram and the sets of the independent-Trained class-specific sub-wond N-grams. We made an experimental language model by using STLM for the two similar proper-noun classes and performed the speech recognition experiments. The results show that any OOV word of the one class is never misrecognized as that of the other class. The results show that the STLM could integrate the multiple different statistical language models with no interference.

本文言語English
ホスト出版物のタイトルEUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology
編集者Borge Lindberg, Henrik Benner, Paul Dalsgaard, Zheng-Hua Tan
出版社International Speech Communication Association
ページ693-696
ページ数4
ISBN(電子版)8790834100, 9788790834104
出版ステータスPublished - 2001 1月 1
外部発表はい
イベント7th European Conference on Speech Communication and Technology - Scandinavia, EUROSPEECH 2001 - Aalborg, Denmark
継続期間: 2001 9月 32001 9月 7

出版物シリーズ

名前EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology

Other

Other7th European Conference on Speech Communication and Technology - Scandinavia, EUROSPEECH 2001
国/地域Denmark
CityAalborg
Period01/9/301/9/7

ASJC Scopus subject areas

  • 通信
  • 言語学および言語
  • コンピュータ サイエンスの応用
  • ソフトウェア

フィンガープリント

「Structured language model for class identification of out-of-vocabulary words arising from multiple word-classes」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