Presentation 2008-01-25
A Study on Sign Language Dialogue System based on Utterance Prediction
Yuuki Okamoto, Masafumi Nishida, Yasuo Horiuchi, Shingo Kuroiwa, Akira Ichikawa,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this study, we propose a dialogue system based on utterance prediction in order to support communications by sign language. Conventional methods of sign language recognition have performed a word recognition based on gesture components. However, the recognition accuracy decreases when the number of recognition candidates increases. We can predict next utterances according to the scene in an actual dialogue. The proposed method is able to decrease the recognition candidates by performing a sentence recognition using the utterance prediction. We conducted recognition experiments by assuming scenes in the hospital. As a result, a sentence recognition accuracy by the conventional method was 7.9% and the recognition accuracy of 83.8% was obtained by the proposed method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Sign language dialogue system / Sign language recognition / Gesture component / Utterance prediction
Paper # TL2007-76,SP2007-171,WIT2007-76
Date of Issue

Conference Information
Committee WIT
Conference Date 2008/1/18(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 Well-being Information Technology(WIT)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Study on Sign Language Dialogue System based on Utterance Prediction
Sub Title (in English)
Keyword(1) Sign language dialogue system
Keyword(2) Sign language recognition
Keyword(3) Gesture component
Keyword(4) Utterance prediction
1st Author's Name Yuuki Okamoto
1st Author's Affiliation Graduate School of Advanced Integration Science, Chiba University()
2nd Author's Name Masafumi Nishida
2nd Author's Affiliation Graduate School of Advanced Integration Science, Chiba University
3rd Author's Name Yasuo Horiuchi
3rd Author's Affiliation Graduate School of Advanced Integration Science, Chiba University
4th Author's Name Shingo Kuroiwa
4th Author's Affiliation Graduate School of Advanced Integration Science, Chiba University
5th Author's Name Akira Ichikawa
5th Author's Affiliation Chiba University
Date 2008-01-25
Paper # TL2007-76,SP2007-171,WIT2007-76
Volume (vol) vol.107
Number (no) 437
Page pp.pp.-
#Pages 6
Date of Issue