Presentation | 2015-12-03 Analyzing the human-human dialog and examining to build WOZ system for estimating the user's willingness to talk Yuya Chiba, Akinori Ito, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | This study considered an interview-based dialog system that asks the user his/her profile actively. Such a dialog system is expected to be able to acquire further information if the user is willing to talk a provided topic; on the contrary, it would not obtain beneficial information if the user does not want to talk. Therefore, the system should select the question or topic considering the user's willingness. In this paper, we analyzed the acoustic information to discriminate the user's willingness, and verified that the speakers tend to make a speech which has large F0 and power range or large variance when their motivation is high. The analysis also shows the facial movements of the user increase in the dialog that the user is willing to talk. In addition, we conducted discrimination experiments by using multi-modal features with SVM, and obtained 80.4% of discrimination ratio under leave-one-out condition and 77.1% discrimination ratio under subject-open condition. Finally, we plan the Wizard of Oz system to collect the dialog between the human and the system. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | spoken dialog / multi-modal information / estimation of user's state |
Paper # | SP2015-83 |
Date of Issue | 2015-11-25 (SP) |
Conference Information | |
Committee | NLC / IPSJ-NL / SP / IPSJ-SLP |
---|---|
Conference Date | 2015/12/2(3days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Nagoya Inst of Tech. |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | The Second Natural Language Processing Symposium & The 17th Spoken Language Symposium |
Chair | Koichi Takeuchi(Okayama Univ.) / Kentaro Inui(Tohoku Univ.) / Kazunori Mano(Shibaura Inst. of Tech.) / Koichi Shinoda(東工大) |
Vice Chair | Hiroshi Kanayama(IBM) / Makoto Ichise(NTT DoCoMo) / / Norihide Kitaoka(Tokushima Univ.) |
Secretary | Hiroshi Kanayama(Univ. of Tokyo/Hottolink) / Makoto Ichise(Ryukoku Univ.) / (Osaka Univ.) / Norihide Kitaoka(Tohoku Univ.) / (Mixi Co. Ltd.) |
Assistant | Kazutaka Shimada(Kyushu Inst. of Tech.) / Ryuichiro Higashinaka(NTT) / / Takashi Nose(Tohoku Univ.) / Taichi Asami(NTT) |
Paper Information | |
Registration To | Technical Committee on Natural Language Understanding and Models of Communication / Special Interest Group on Natural Language / Technical Committee on Speech / Special Interest Group on Spoken Language Processing |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Analyzing the human-human dialog and examining to build WOZ system for estimating the user's willingness to talk |
Sub Title (in English) | |
Keyword(1) | spoken dialog |
Keyword(2) | multi-modal information |
Keyword(3) | estimation of user's state |
1st Author's Name | Yuya Chiba |
1st Author's Affiliation | Tohoku University(Tohoku Univ.) |
2nd Author's Name | Akinori Ito |
2nd Author's Affiliation | Tohoku University(Tohoku Univ.) |
Date | 2015-12-03 |
Paper # | SP2015-83 |
Volume (vol) | vol.115 |
Number (no) | SP-346 |
Page | pp.pp.117-122(SP), |
#Pages | 6 |
Date of Issue | 2015-11-25 (SP) |