Word topical mixture models for dynamic language model adaptation

Hsuan Sheng Chiu, Berlin Chen

研究成果: 書貢獻/報告類型會議貢獻

19 引文 斯高帕斯(Scopus)

摘要

This paper considers dynamic language model adaptation for Mandarin broadcast news recognition. A word topical mixture model (TMM) is proposed to explore the co-occurrence relationship between words, as well as the long-span latent topical information, for language model adaptation. The search history is modeled as a composite word TMM model for predicting the decoded word. The underlying characteristics and different kinds of model structures were extensively investigated, while the performance of word TMM was analyzed and verified by comparison with the conventional probabilistic latent semantic analysis-based language model (PLSALM) and trigger-based language model (TBLM) adaptation approaches. The large vocabulary continuous speech recognition (LVCSR) experiments were conducted on the Mandarin broadcast news collected in Taiwan. Very promising results in perplexity as well as character error rate reductions were initially obtained.

原文英語
主出版物標題2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07
頁面IV169-IV172
DOIs
出版狀態已發佈 - 2007
事件2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07 - Honolulu, HI, 美国
持續時間: 2007 四月 152007 四月 20

出版系列

名字ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
4
ISSN(列印)1520-6149

其他

其他2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07
國家美国
城市Honolulu, HI
期間2007/04/152007/04/20

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

指紋 深入研究「Word topical mixture models for dynamic language model adaptation」主題。共同形成了獨特的指紋。

引用此