Presentation 2019-10-26
Emotional speech classification using DNN and RF stacking
Nayuta Tanaami, Minoru Hayashi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Conventionally, support vector machine (SVM) has been used for emotional speech classification. Recently, however, research on classification using deep neural network (DNN) has also been conducted. In many cases, they performed only by one DNN, but it is known that accuracy improvement can be expected by performing ensemble learning using a plurality of classifiers in a classification problem. Therefore, in this study, stacking, one of ensemble learning, performed using DNN and random forest (RF) and compared with SVM and DNN. The result of this study indicate that stacking DNN and RF was 10.42% higher than SVM and 3.71% higher than DNN.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Emotional Speech / Deep neural network / Random Forest
Paper # HCS2019-42
Date of Issue 2019-10-19 (HCS)

Conference Information
Committee HCS
Conference Date 2019/10/26(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Nihon Univ.
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Masafumi Matsuda(NTT)
Vice Chair Tomoo Inoue(Univ. of Tsukuba) / Yugo Hayashi(Ritsumeikan Univ.)
Secretary Tomoo Inoue(Kanazawa Inst. of Tech.) / Yugo Hayashi(Osaka Electro-Comm. Univ.)
Assistant Tomoko Kanda(Osaka Inst. of Tech.) / Kazuki Takashima(Tohoku Univ.) / Ken Fujiwara(Osaka Univ. of Economic) / Kazunori Terada(Gifu Univ.) / Atsushi Kimura(Nihon Univ.) / HUANG HUNGHSUAN(Riken)

Paper Information
Registration To Technical Committee on Human Communication Science
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Emotional speech classification using DNN and RF stacking
Sub Title (in English)
Keyword(1) Emotional Speech
Keyword(2) Deep neural network
Keyword(3) Random Forest
1st Author's Name Nayuta Tanaami
1st Author's Affiliation Meisei University(Meisei Univ.)
2nd Author's Name Minoru Hayashi
2nd Author's Affiliation Meisei University(Meisei Univ.)
Date 2019-10-26
Paper # HCS2019-42
Volume (vol) vol.119
Number (no) HCS-252
Page pp.pp.11-15(HCS),
#Pages 5
Date of Issue 2019-10-19 (HCS)