JAIST Repository >
b. 情報科学研究科・情報科学系 >
b11. 会議発表論文・発表資料等 >
b11-1. 会議発表論文・発表資料 >

このアイテムの引用には次の識別子を使用してください: http://hdl.handle.net/10119/17068

タイトル: Improving Valence Prediction in Dimensional Speech Emotion Recognition Using Linguistic Information
著者: Atmaja, Bagus Tris
Akagi, Masato
キーワード: valence prediction
linguistic feature
speech emotion recognition
dimensional emotion
affective computing
発行日: 2020-11-06
出版者: Institute of Electrical and Electronics Engineers (IEEE)
誌名: 2020 23rd Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)
開始ページ: 166
終了ページ: 171
DOI: 10.1109/O-COCOSDA50338.2020.9295032
抄録: In dimensional emotion recognition, a model called valence, arousal, and dominance is widely used. The current research in dimensional speech emotion recognition has shown a problem that the performance of valence prediction is lower than arousal and dominance. This paper presents an approach to tackle this problem: improving the low score of valence prediction by utilizing linguistic information. Our approach fuses acoustic features with linguistic features, which is a conversion from words to vectors. The results doubled the performance of valence prediction on both single-task learning single-output (predicting valence only) and multitask learning multi-output (predicting valence, arousal, and dominance). Using a proper combination of acoustic and linguistic features not only improved valence prediction, but also improved arousal and dominance predictions in multitask learning.
Rights: This is the author's version of the work. Copyright (C) 2020 IEEE. 2020 23rd Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA), 2020, pp.166-171. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
URI: http://hdl.handle.net/10119/17068
資料タイプ: author
出現コレクション:b11-1. 会議発表論文・発表資料 (Conference Papers)

このアイテムのファイル:

ファイル 記述 サイズ形式
3360.pdf172KbAdobe PDF見る/開く

当システムに保管されているアイテムはすべて著作権により保護されています。

 


お問い合わせ先 : 北陸先端科学技術大学院大学 研究推進課図書館情報係