Minimum word error based discriminative training of language models

Jen Wei Kuo*, Berlin Chen

*此作品的通信作者

研究成果: 會議貢獻類型會議論文同行評審

12 引文 斯高帕斯(Scopus)

摘要

This paper considers discriminative training of language models for large vocabulary continuous speech recognition. The minimum word error (MWE) criterion was explored to make use of the word confusion information as well as the local lexical constraints inherent in the acoustic training corpus, in conjunction with those constraints obtained from the background text corpus, for properly guiding the speech recognizer to separate the correct hypothesis from the competing ones. The underlying characteristics of the MWE-based approach were extensively investigated, and its performance was verified by comparison with the conventional maximum likelihood (ML) approaches as well. The speech recognition experiments were performed on the broadcast news collected in Taiwan.

原文英語
頁面1277-1280
頁數4
出版狀態已發佈 - 2005 十二月 1
事件9th European Conference on Speech Communication and Technology - Lisbon, 葡萄牙
持續時間: 2005 九月 42005 九月 8

其他

其他9th European Conference on Speech Communication and Technology
國家/地區葡萄牙
城市Lisbon
期間2005/09/042005/09/08

ASJC Scopus subject areas

  • 工程 (全部)

指紋

深入研究「Minimum word error based discriminative training of language models」主題。共同形成了獨特的指紋。

引用此