Dynamic language model adaptation using latent topical information and automatic transcripts

Berlin Chen*

*Corresponding author for this work

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

3 Citations (Scopus)

Abstract

This paper considers dynamic language model adaptation for Mandarin broadcast news recognition. Both contemporary newswire texts and in-domain automatic transcripts were exploited in language model adaptation. A topical mixture model was presented to dynamically explore the long-span latent topical information for language model adaptation. The underlying characteristics and different kinds of model structures were extensively investigated, while their performance was analyzed and verified by comparison with the conventional MAP-based adaptation approaches, which are devoted to extracting the short-span ra-gram information. The fusion of global topical and local contextual information was investigated as well. The speech recognition experiments were conducted on the broadcast news collected in Taiwan. Very promising results in perplexity as well as character error rate reductions were initially obtained.

Original languageEnglish
Title of host publicationIEEE International Conference on Multimedia and Expo, ICME 2005
Pages97-100
Number of pages4
DOIs
Publication statusPublished - 2005
EventIEEE International Conference on Multimedia and Expo, ICME 2005 - Amsterdam, Netherlands
Duration: 2005 Jul 62005 Jul 8

Publication series

NameIEEE International Conference on Multimedia and Expo, ICME 2005
Volume2005

Other

OtherIEEE International Conference on Multimedia and Expo, ICME 2005
Country/TerritoryNetherlands
CityAmsterdam
Period2005/07/062005/07/08

ASJC Scopus subject areas

  • General Engineering

Fingerprint

Dive into the research topics of 'Dynamic language model adaptation using latent topical information and automatic transcripts'. Together they form a unique fingerprint.

Cite this