Presentation | 2012-02-09 Estimation of a User's Internal State before the First Input Utterance Using HMM with Non-verbal Information Yuya CHIBA, Masashi ITO, Akinori ITO, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | This paper describes a method for estimating the internal state of the user of a spoken dialog system before his input utterance. In the practical use of dialogue-based system, the user often perplexed with the prompt. An ordinary system provides more detailed information to the user taking time to input, but these helps are meddlesome for the user considering the answer to the prompt. To make appropriate response, the spoken dialogue system have to be able to consider the user's internal state before user's input. The conventional researches on user modeling have focused on the linguistic information of the utterance. One problem of these approaches is that it cannot estimate the user's states until the end of the user's first utterance. Therefor, our study focused on the user's non-verbal output such as fillers, silence or head-moving until the occurrence of user's input utterance. This paper describes the method of the user modeling by HMM. We conducted the examination discrimination, and obtained the accuracy of 79.6%. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | spoken dialogue / user modeling / speech processing / image processing |
Paper # | PRMU2011-187,SP2011-102 |
Date of Issue |
Conference Information | |
Committee | SP |
---|---|
Conference Date | 2012/2/2(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) | Estimation of a User's Internal State before the First Input Utterance Using HMM with Non-verbal Information |
Sub Title (in English) | |
Keyword(1) | spoken dialogue |
Keyword(2) | user modeling |
Keyword(3) | speech processing |
Keyword(4) | image processing |
1st Author's Name | Yuya CHIBA |
1st Author's Affiliation | Graduate School of Engineering, Tohoku University() |
2nd Author's Name | Masashi ITO |
2nd Author's Affiliation | Department of Electronics and Intelligent System, Tohoku Institute of Technology |
3rd Author's Name | Akinori ITO |
3rd Author's Affiliation | Graduate School of Engineering, Tohoku University |
Date | 2012-02-09 |
Paper # | PRMU2011-187,SP2011-102 |
Volume (vol) | vol.111 |
Number (no) | 431 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |