Presentation 2010-08-28
Estimating affective states in a spoken dialog by using speech parameters
Gaoyahan G, Yuko Ohno, Yoshihiko Hayashi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We have been investigating characteristics of empathic states expressed in spontaneous utterances by analyzing speech data annotated with attitude and emotion categories. Basing on these investigations, this paper examines a method to estimate empathic states from speech utterances. The idea is to use the annotated data as training data for a machine learning algorithm (SVM) to construct relevant classifiers. These classifiers are arranged in such a way to reflect our definition of empathic states. The experimental results suggest: (1) there exist dependencies between attitude and emotion; (2) the estimation can be improved if augmented with the categories for the preceding utterance. This paper further discusses details of the initial experimental resutls and proposes a research agenda for the future study.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) empathic state / speech parameters / machine learning / spontaneous dialogue
Paper # HCS2010-33
Date of Issue

Conference Information
Committee HCS
Conference Date 2010/8/20(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 Human Communication Science (HCS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Estimating affective states in a spoken dialog by using speech parameters
Sub Title (in English)
Keyword(1) empathic state
Keyword(2) speech parameters
Keyword(3) machine learning
Keyword(4) spontaneous dialogue
1st Author's Name Gaoyahan G
1st Author's Affiliation Graduate School of Medicine, Osaka University()
2nd Author's Name Yuko Ohno
2nd Author's Affiliation Graduate School of Medicine, Osaka University
3rd Author's Name Yoshihiko Hayashi
3rd Author's Affiliation Graduate School of Language and Culture, Osaka University
Date 2010-08-28
Paper # HCS2010-33
Volume (vol) vol.110
Number (no) 185
Page pp.pp.-
#Pages 6
Date of Issue