A Statistical Language Model for Conventional Speech Reflecting the Previous Utterance of the Other Participant

Hirofumi Yamamoto, Koichi Tanigaki, Yoshinori Sagisaka

Research output: Contribution to journalArticle

Abstract

This paper proposes the construction of a language model for speech recognition in speech translation. The proposed language model is intended to improve speech recognition performance by taking account of the previous utterance content of the counterpart speaker. The previous utterance content of the counterpart speaker is represented by the intermediate language which is generally used by C-star (Spoken Language Translation Research Group). The proposed model is based on a language model that is dependent on the intermediate language representation. An experiment concerning the conversation of hotel reservations shows that the rate of incorrect word recognition is reduced by approximately 5.4% (from 14.7% to 13.9%), and the usefulness of the proposed model is demonstrated.

Original languageEnglish
Pages (from-to)54-62
Number of pages9
JournalElectronics and Communications in Japan, Part II: Electronics (English translation of Denshi Tsushin Gakkai Ronbunshi)
Volume87
Issue number1
DOIs
Publication statusPublished - 2004 Jan 1

Keywords

  • Conversation
  • Intermediate language representation
  • N-gram
  • Statistical language model
  • Task adaptation

ASJC Scopus subject areas

  • Physics and Astronomy(all)
  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'A Statistical Language Model for Conventional Speech Reflecting the Previous Utterance of the Other Participant'. Together they form a unique fingerprint.

  • Cite this