An HMM/N-gram-based linguistic processing approach for Mandarin spoken document retrieval

Berlin Chen, Hsin Min Wang, Lin Shan Lee

研究成果: 書貢獻/報告類型會議論文篇章

9 引文 斯高帕斯(Scopus)

摘要

In this paper an HMM/N-gram-based linguistic processing approach for Mandarin spoken document retrieval is presented. The underlying characteristics and different structures of this approach were extensively investigated. The retrieval capabilities were verified by tests with indexing features of word-And syllable(subword)-levels and comparison with the conventional vector space model approach. To further improve the discrimination capabilities of the HMMs, both the expectation-maximization (EM) and minimum classification error (MCE) training algorithms were introduced in training. The information fusion of indexing features of word-And syllable-levels was also investigated. The spoken document retrieval experiments were performed on the Topic Detection and Tracking Corpora (TDT-2 and TDT-3). Very encouraging retrieval performance was obtained.

原文英語
主出版物標題EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology
編輯Borge Lindberg, Henrik Benner, Paul Dalsgaard, Zheng-Hua Tan
發行者International Speech Communication Association
頁面1045-1048
頁數4
ISBN(電子)8790834100, 9788790834104
出版狀態已發佈 - 2001 一月 1
事件7th European Conference on Speech Communication and Technology - Scandinavia, EUROSPEECH 2001 - Aalborg, 丹麦
持續時間: 2001 九月 32001 九月 7

出版系列

名字EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology

其他

其他7th European Conference on Speech Communication and Technology - Scandinavia, EUROSPEECH 2001
國家/地區丹麦
城市Aalborg
期間2001/09/032001/09/07

ASJC Scopus subject areas

  • 通訊
  • 語言和語言學
  • 電腦科學應用
  • 軟體

指紋

深入研究「An HMM/N-gram-based linguistic processing approach for Mandarin spoken document retrieval」主題。共同形成了獨特的指紋。

引用此