Discriminative language modeling for speech recognition with relevance information

Berlin Chen*, Jia Wen Liu

*此作品的通信作者

研究成果: 書貢獻/報告類型會議論文篇章

5 引文 斯高帕斯(Scopus)

摘要

Discriminative language modeling (DLM) attempts to improve speech recognition performance by reranking the recognition hypotheses output from a baseline system. Most of the existing DLM methods assume that the reranking task can be treated as a linear discrimination problem and all testing utterances share the same parameter vector for reranking of hypotheses. However, the latter assumption sometimes results in a trained DLM model with weak generalizability and unsatisfactory performance. In view of this problem, we hence propose a relevance-based DLM (RDLM) framework that can efficiently infer the DLM model parameters of each testing utterance on-the-fly for better recognition performance. The structures and characteristics of the RDLM framework are extensively investigated, while the performance is thoroughly analyzed and verified by comparison with the existing DLM methods.

原文英語
主出版物標題Electronic Proceedings of the 2011 IEEE International Conference on Multimedia and Expo, ICME 2011
DOIs
出版狀態已發佈 - 2011 十一月 7
事件2011 12th IEEE International Conference on Multimedia and Expo, ICME 2011 - Barcelona, 西班牙
持續時間: 2011 七月 112011 七月 15

出版系列

名字Proceedings - IEEE International Conference on Multimedia and Expo
ISSN(列印)1945-7871
ISSN(電子)1945-788X

其他

其他2011 12th IEEE International Conference on Multimedia and Expo, ICME 2011
國家/地區西班牙
城市Barcelona
期間2011/07/112011/07/15

ASJC Scopus subject areas

  • 電腦網路與通信
  • 電腦科學應用

指紋

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

引用此