Effective pseudo-relevance feedback for language modeling in speech recognition

Berlin Chen, Yi Wen Chen, Kuan Yu Chen, Ea Ee Jan

研究成果: 書貢獻/報告類型會議論文篇章

摘要

A part and parcel of any automatic speech recognition (ASR) system is language modeling (LM), which helps to constrain the acoustic analysis, guide the search through multiple candidate word strings, and quantify the acceptability of the final output hypothesis given an input utterance. Despite the fact that the n-gram model remains the predominant one, a number of novel and ingenious LM methods have been developed to complement or be used in place of the n-gram model. A more recent line of research is to leverage information cues gleaned from pseudo-relevance feedback (PRF) to derive an utterance-regularized language model for complementing the n-gram model. This paper presents a continuation of this general line of research and its main contribution is two-fold. First, we explore an alternative and more efficient formulation to construct such an utterance-regularized language model for ASR. Second, the utilities of various utterance-regularized language models are analyzed and compared extensively. Empirical experiments on a large vocabulary continuous speech recognition (LVCSR) task demonstrate that our proposed language models can offer substantial improvements over the baseline n-gram system, and achieve performance competitive to, or better than, some state-of-the-art language models.

原文英語
主出版物標題2013 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2013 - Proceedings
頁面13-18
頁數6
DOIs
出版狀態已發佈 - 2013 十二月 1
事件2013 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2013 - Olomouc, 捷克共和国
持續時間: 2013 十二月 82013 十二月 13

出版系列

名字2013 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2013 - Proceedings

其他

其他2013 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2013
國家/地區捷克共和国
城市Olomouc
期間2013/12/082013/12/13

ASJC Scopus subject areas

  • 言語和聽力

指紋

深入研究「Effective pseudo-relevance feedback for language modeling in speech recognition」主題。共同形成了獨特的指紋。

引用此