Presentation 2000/3/16
Study on Learning Method of Word Space Produced from Information Integration of Telop Appearing Sections and Speech Dictation
Seiichi Takao, Junichi Funamoto, Yasuo Ariki, Jun Ogata,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) It is necessary for conventional topic segmentation techniques to adapt itself by using large amount of training data to news data changing everyday. But this is really impossible, because time difference and topic distribution difference between training data and test data occurs. To solve these problems, we propose the learning method of word space based on integrating the information of telop appearing sections with speech dictation in this paper. Its effectiveness was shown by carrying out topic segmentation based on the word space method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) integration / topic segmentation / telop appearing section / LVCSR / word space
Paper # NLC99-76,PRMU99-259
Date of Issue

Conference Information
Committee PRMU
Conference Date 2000/3/16(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 Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Study on Learning Method of Word Space Produced from Information Integration of Telop Appearing Sections and Speech Dictation
Sub Title (in English)
Keyword(1) integration
Keyword(2) topic segmentation
Keyword(3) telop appearing section
Keyword(4) LVCSR
Keyword(5) word space
1st Author's Name Seiichi Takao
1st Author's Affiliation Faculty of Science and Technology, Ryukoku University()
2nd Author's Name Junichi Funamoto
2nd Author's Affiliation Faculty of Science and Technology, Ryukoku University
3rd Author's Name Yasuo Ariki
3rd Author's Affiliation Faculty of Science and Technology, Ryukoku University
4th Author's Name Jun Ogata
4th Author's Affiliation Faculty of Science and Technology, Ryukoku University
Date 2000/3/16
Paper # NLC99-76,PRMU99-259
Volume (vol) vol.99
Number (no) 709
Page pp.pp.-
#Pages 6
Date of Issue