Statistical language model adaptation for Mandarin broadcast news transcription

Berlin Chen, Wen Hung Tsai, Jen Wei Kuo

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

4 Citations (Scopus)

Abstract

This paper investigates statistical language model adaptation for Mandarin broadcast news transcription. A topical mixture model was proposed to explore the long-span latent topical information for dynamic language model adaptation. The underlying characteristics and various kinds of model complexities were extensively investigated, while their performance was verified by comparison with the conventional MAP-based adaptation approaches, which are devoted to extracting the short-span n-gram information. The speech recognition experiments were conducted on the broadcast news collected in Taiwan. Very promising results in both perplexity and word error rate reductions were initially obtained.

Original languageEnglish
Title of host publication2004 International Symposium on Chinese Spoken Language Processing - Proceedings
Pages313-316
Number of pages4
Publication statusPublished - 2004 Dec 1
Event2004 International Symposium on Chinese Spoken Language Processing - Hong Kong, China, Hong Kong
Duration: 2004 Dec 152004 Dec 18

Publication series

Name2004 International Symposium on Chinese Spoken Language Processing - Proceedings

Other

Other2004 International Symposium on Chinese Spoken Language Processing
CountryHong Kong
CityHong Kong, China
Period04/12/1504/12/18

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint Dive into the research topics of 'Statistical language model adaptation for Mandarin broadcast news transcription'. Together they form a unique fingerprint.

  • Cite this

    Chen, B., Tsai, W. H., & Kuo, J. W. (2004). Statistical language model adaptation for Mandarin broadcast news transcription. In 2004 International Symposium on Chinese Spoken Language Processing - Proceedings (pp. 313-316). [L7.3] (2004 International Symposium on Chinese Spoken Language Processing - Proceedings).