Presentation 1999/6/18
A Study on English-Japanese Mutual Retrieval for Broadcast News Articles
Jun Ogata, Seiichi Takao, Keiko Hasegawa, Yasuo Ariki,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose on English-Japanese mutual retrieval system toward cross-language information retrieval. This system consists of two parts, one is a speech recognition part where news speech articles are automatically dictated and the other is a retrieval part where news articles are retrieved using the dictation result produced at the speech recognition part. In speech recognition part, we carried out large vocabulary continuous speech recognition using word N-gram language model. We retrieved news articles based on the similarity between them. The similarity is computed by topic vectors of news articles based on the word frequency word importance.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) LVCSR / article retrieval / word importance
Paper # SP99-34
Date of Issue

Conference Information
Committee SP
Conference Date 1999/6/18(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Speech (SP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Study on English-Japanese Mutual Retrieval for Broadcast News Articles
Sub Title (in English)
Keyword(1) LVCSR
Keyword(2) article retrieval
Keyword(3) word importance
1st Author's Name Jun Ogata
1st Author's Affiliation Faculty of Science and Technology, Ryukoku University()
2nd Author's Name Seiichi Takao
2nd Author's Affiliation Faculty of Science and Technology, Ryukoku University
3rd Author's Name Keiko Hasegawa
3rd Author's Affiliation Faculty of Science and Technology, Ryukoku University
4th Author's Name Yasuo Ariki
4th Author's Affiliation Faculty of Science and Technology, Ryukoku University
Date 1999/6/18
Paper # SP99-34
Volume (vol) vol.99
Number (no) 121
Page pp.pp.-
#Pages 8
Date of Issue