Word relevance modeling for speech recognition

Kuan Yu Chen, Hao Chin Chang, Berlin Chen, Hsin Min Wang

研究成果: 書貢獻/報告類型會議論文篇章

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, discovering either lexical co-occurrence or topic cues, have been developed to mitigate this problem with varying degrees of success. Among them, a more recent thread of work is the relevance modeling approach, which has shown promise to capture the lexical co-occurrence relationship between the entire search history and an upcoming word. However, a potential downside to such an approach is the need of resorting to a retrieval procedure to obtain relevance information; this is usually complex and time-consuming for practical applications. In this paper, we propose a word relevance modeling framework, which introduces 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 yet systematic way to render the lexical, topical, and proximity relationships between the search history and the upcoming word. Experiments on large vocabulary continuous speech recognition demonstrate the performance merits of the methods instantiated from this framework when compared to several existing methods.

原文英語
主出版物標題13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012
頁面998-1001
頁數4
出版狀態已發佈 - 2012 十二月 1
事件13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012 - Portland, OR, 美国
持續時間: 2012 九月 92012 九月 13

出版系列

名字13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012
2

其他

其他13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012
國家/地區美国
城市Portland, OR
期間2012/09/092012/09/13

ASJC Scopus subject areas

  • 電腦網路與通信
  • 通訊

指紋

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

引用此