Relevance language modeling for speech recognition

Kuan Yu Chen, Berlin Chen

研究成果: 書貢獻/報告類型會議貢獻

9 引文 斯高帕斯(Scopus)

摘要

Language models for speech recognition tend to be brittle across domains, since their performance is vulnerable to changes in the genre or topic of the text on which they are trained. A number of adaptation methods, exploring either lexical co-occurrence or topic cues, have been developed to mitigate this problem with varying degrees of success. In this paper, we study a novel use of relevance information for dynamic language model adaptation in speech recognition. It not only inherits the merits of several existing techniques but also provides a flexible but systematic way to render the lexical and topical relationships between a search history and an upcoming word. Empirical results on large vocabulary continuous speech recognition show that the methods deduced from our framework represent promising alternatives to the other existing language model adaptation methods compared in this paper.

原文英語
主出版物標題2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings
頁面5568-5571
頁數4
DOIs
出版狀態已發佈 - 2011 八月 18
事件36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Prague, 捷克共和国
持續時間: 2011 五月 222011 五月 27

出版系列

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

其他

其他36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011
國家捷克共和国
城市Prague
期間11/5/2211/5/27

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

指紋 深入研究「Relevance language modeling for speech recognition」主題。共同形成了獨特的指紋。

引用此