Position information for language modeling in speech recognition

Hsuan Sheng Chiu*, Guan Yu Chen, Chun Jen Lee, Berlin Chen

*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

4 引文 斯高帕斯(Scopus)

摘要

This paper considers word position information for language modeling. For organized documents, such as technical papers or news reports, the composition and the word usage of articles of the same style are usually similar. Therefore, the documents can be separated into partitions consisting of identical rhetoric or topic styles by the literary structures, e.g., introductory remarks, related studies or events, elucidations of methodology or affairs, conclusions of the articles, and references, or footnotes of reporters. In this paper, we explore word position information and then propose two position-dependent language models for speech recognition. The structures and characteristics of these position-dependent language models were extensively investigated, while its performance was analyzed and verified by comparing it with the existing n-gram, mixture- and topic-based language models. The large vocabulary continuous speech recognition (LVCSR) experiments were conducted on the broadcast news transcription task. The preliminary results seem to indicate that the proposed position-dependent models are comparable to the mixture- and topic-based models.

原文英語
主出版物標題Proceedings - 2008 6th International Symposium on Chinese Spoken Language Processing, ISCSLP 2008
頁面101-104
頁數4
DOIs
出版狀態已發佈 - 2008 十二月 1
事件2008 6th International Symposium on Chinese Spoken Language Processing, ISCSLP 2008 - Kunming, 中国
持續時間: 2008 十二月 162008 十二月 19

出版系列

名字Proceedings - 2008 6th International Symposium on Chinese Spoken Language Processing, ISCSLP 2008

其他

其他2008 6th International Symposium on Chinese Spoken Language Processing, ISCSLP 2008
國家/地區中国
城市Kunming
期間2008/12/162008/12/19

ASJC Scopus subject areas

  • 電腦科學應用
  • 資訊系統
  • 軟體

指紋

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

引用此