Application of topic tracking model to language model adaptation and meeting analysis

Shinji Watanabe, Tomoharu Iwata, Takaaki Hori, Atsushi Sako, Yasuo Ariki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In a real environment, acoustic and language features often vary depending on the speakers, speaking styles and topic changes. This paper focuses on changes in the language environment, and applies a topic tracking model to language model adaptation for speech recognition and topic word extraction for meeting analysis. The topic tracking model can adaptively track changes in topics based on current text information and previously estimated topic models in an online manner. The effectiveness of the proposed method is shown experimentally by the improvement in speech recognition performance achieved with the Corpus of Spontaneous Japanese and by providing appropriate topic information in an automatic meeting analyzer.

Original languageEnglish
Title of host publication2010 IEEE Workshop on Spoken Language Technology, SLT 2010 - Proceedings
Pages378-383
Number of pages6
DOIs
Publication statusPublished - 2010 Dec 1
Event2010 IEEE Workshop on Spoken Language Technology, SLT 2010 - Berkeley, CA, United States
Duration: 2010 Dec 122010 Dec 15

Publication series

Name2010 IEEE Workshop on Spoken Language Technology, SLT 2010 - Proceedings

Other

Other2010 IEEE Workshop on Spoken Language Technology, SLT 2010
CountryUnited States
CityBerkeley, CA
Period10/12/1210/12/15

    Fingerprint

Keywords

  • Language model adaptation
  • Latent topic model
  • Meeting analyzer
  • On-line algorithm
  • Topic tracking

ASJC Scopus subject areas

  • Language and Linguistics

Cite this

Watanabe, S., Iwata, T., Hori, T., Sako, A., & Ariki, Y. (2010). Application of topic tracking model to language model adaptation and meeting analysis. In 2010 IEEE Workshop on Spoken Language Technology, SLT 2010 - Proceedings (pp. 378-383). [5700882] (2010 IEEE Workshop on Spoken Language Technology, SLT 2010 - Proceedings). https://doi.org/10.1109/SLT.2010.5700882