Speech recognition of a named entity

Tatsuhiko Tomita*, Yoshiyuki Okimoto, Hirofumi Yamamoto, Yoshinori Sagisaka

*この研究の対応する著者

研究成果: Conference contribution

3 被引用数 (Scopus)

抄録

A hierarchical language model is newly applied to identify a named entity consisting of multiple word sequences for continuous speech recognition. By redesigning an out-of-vocabulary model of a single word using phonotactic constraints for a named entity, a hierarchical model is composed harmoniously with conventional word and word-class N-grams. Continuous speech recognition experiments aiming at movie-title identification showed the effectiveness of this modeling in the task of inquiries on these titles. These results ensure that the proposed hierarchical language modeling architecture is applicable to multiple word successions for speech recognition to cope with unregistered expressions and enables the mix use of different statistics harmoniously.

本文言語English
ホスト出版物のタイトル2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05 - Proceedings - Image and Multidimensional Signal Processing Multimedia Signal Processing
出版社Institute of Electrical and Electronics Engineers Inc.
ページI1057-I1060
ISBN(印刷版)0780388747, 9780780388741
DOI
出版ステータスPublished - 2005 1 1
イベント2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05 - Philadelphia, PA, United States
継続期間: 2005 3 182005 3 23

出版物シリーズ

名前ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
I
ISSN(印刷版)1520-6149

Conference

Conference2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05
国/地域United States
CityPhiladelphia, PA
Period05/3/1805/3/23

ASJC Scopus subject areas

  • ソフトウェア
  • 信号処理
  • 電子工学および電気工学

フィンガープリント

「Speech recognition of a named entity」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