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
Externally publishedYes
Event2010 IEEE Workshop on Spoken Language Technology, SLT 2010 - Berkeley, CA, United States
Duration: 2010 Dec 122010 Dec 15

Other

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

Fingerprint

Language Model
Speech Recognition
Language
Acoustics

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] https://doi.org/10.1109/SLT.2010.5700882

Application of topic tracking model to language model adaptation and meeting analysis. / Watanabe, Shinji; Iwata, Tomoharu; Hori, Takaaki; Sako, Atsushi; Ariki, Yasuo.

2010 IEEE Workshop on Spoken Language Technology, SLT 2010 - Proceedings. 2010. p. 378-383 5700882.

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

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., 5700882, pp. 378-383, 2010 IEEE Workshop on Spoken Language Technology, SLT 2010, Berkeley, CA, United States, 10/12/12. https://doi.org/10.1109/SLT.2010.5700882
Watanabe S, Iwata T, Hori T, Sako A, Ariki Y. Application of topic tracking model to language model adaptation and meeting analysis. In 2010 IEEE Workshop on Spoken Language Technology, SLT 2010 - Proceedings. 2010. p. 378-383. 5700882 https://doi.org/10.1109/SLT.2010.5700882
Watanabe, Shinji ; Iwata, Tomoharu ; Hori, Takaaki ; Sako, Atsushi ; Ariki, Yasuo. / Application of topic tracking model to language model adaptation and meeting analysis. 2010 IEEE Workshop on Spoken Language Technology, SLT 2010 - Proceedings. 2010. pp. 378-383
@inproceedings{ab6e2ddb47a5483283a0aef8a654c1b3,
title = "Application of topic tracking model to language model adaptation and meeting analysis",
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.",
keywords = "Language model adaptation, Latent topic model, Meeting analyzer, On-line algorithm, Topic tracking",
author = "Shinji Watanabe and Tomoharu Iwata and Takaaki Hori and Atsushi Sako and Yasuo Ariki",
year = "2010",
doi = "10.1109/SLT.2010.5700882",
language = "English",
isbn = "9781424479030",
pages = "378--383",
booktitle = "2010 IEEE Workshop on Spoken Language Technology, SLT 2010 - Proceedings",

}

TY - GEN

T1 - Application of topic tracking model to language model adaptation and meeting analysis

AU - Watanabe, Shinji

AU - Iwata, Tomoharu

AU - Hori, Takaaki

AU - Sako, Atsushi

AU - Ariki, Yasuo

PY - 2010

Y1 - 2010

N2 - 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.

AB - 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.

KW - Language model adaptation

KW - Latent topic model

KW - Meeting analyzer

KW - On-line algorithm

KW - Topic tracking

UR - http://www.scopus.com/inward/record.url?scp=79951790582&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79951790582&partnerID=8YFLogxK

U2 - 10.1109/SLT.2010.5700882

DO - 10.1109/SLT.2010.5700882

M3 - Conference contribution

SN - 9781424479030

SP - 378

EP - 383

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

ER -