7感情の強度推定結果に基づく音響的特徴からの話者感情の推定手法

URI http://harp.lib.hiroshima-u.ac.jp/hiroshima-cu/metadata/12310
File
Title
7感情の強度推定結果に基づく音響的特徴からの話者感情の推定手法
Title Alternative
Speaker’s mental state estimation method using intensities of seven emotions calculated from acoustic features
Author
氏名 上村 譲史
ヨミ ウエムラ ジョウジ
別名 UEMURA Joji
氏名 新升 悠太
ヨミ シンマス ユウタ
別名 SHINMASU Yuta
氏名 目良 和也
ヨミ メラ カズヤ
別名 MERA Kazuya
氏名 黒澤 義明
ヨミ クロサワ ヨシアキ
別名 KUROSAWA Yoshiaki
氏名 竹澤 寿幸
ヨミ タケザワ トシユキ
別名 TAKEZAWA Toshiyuki
Abstract

Previous multi-class emotion classification method has two problems; it cannot deal with emotions except pre-defined emotions, and it cannot express situation when multiple emotions are arousing at the same time. In this paper, we apply hard and soft clustering methods into emotion classification. Hard clustering method gives information to re-classify emotion classes. Soft clustering method is valid to detect data which arouse multiple emotions. Seven types of emotion voice data (anger, anticipation, disgust, fear, joy, sadness, and surprise) are re-classified into eight clusters based on intensity values of the seven emotions calculated from acoustic features. The result of hard clustering suggested that some emotion data can be classified more finely. On the other hand, some data which have the features of multiple emotions could be found by soft clustering method.

Journal Title
人工知能学会全国大会論文集
Volume
30
Spage
1
Epage
3
Published Date
2016-06
Publisher
人工知能学会
Language
jpn
NIIType
Conference Paper
Text Version
出版社版
Relation URL
Note

4K4-3

Set
hiroshima-cu