Presentation 2022-03-10
A Consideration on Estimation Accuracy Improvement of Unlearned Music Pieces in Music Listener's Emotion Estimation Using Bio-signals
Nanami Tanizawa, Mutsumi Suganuma, Wataru Kameyama,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We are conducting a research of music listener’s emotion estimation by using bio-signals in order to utilize it for music recommendation systems. In this paper, in order to improve emotion estimation accuracy of unlearned music pieces, we perform an analysis with more training data and an analysis considering emotion changes within a music piece. Then, we compare the results in these analyses to the results in our previous study. In addition, we examine the estimation using the music information of key, tempo, mode and loudness obtained from Spotify as well as using bio-signals. As a result, the increase in the amount of data and the consideration of emotion changes within a music piece don’t improve the estimation accuracy much, although the chance levels are exceeded. On the other hand, the highest accuracies are achieved when both the music information and the bio-signals are used. The results suggest that it may be possible to estimate music listener’s emotion even for unlearned music pieces.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Bio-signals / Music Listener / Emotion Estimation / Unlearned Music Pieces / Machine Learning
Paper # CQ2021-118
Date of Issue 2022-03-02 (CQ)

Conference Information
Committee CQ / IMQ / MVE / IE
Conference Date 2022/3/9(3days)
Place (in Japanese) (See Japanese page)
Place (in English) Online (Zoom)
Topics (in Japanese) (See Japanese page)
Topics (in English) Media of five senses, Multimedia, Media experience, Picture codinge, Image media quality, Network,quality and reliability, etc
Chair Jun Okamoto(NTT) / Kenya Uomori(Osaka Univ.) / Masayuki Ihara(RIKEN) / Kazuya Kodama(NII)
Vice Chair Takefumi Hiraguri(Nippon Inst. of Tech.) / Gou Hasegawa(Tohoku Univ.) / Mitsuru Maeda(Canon) / Kiyoshi Kiyokawa(NAIST) / Hiroyuki Bandoh(NTT) / Toshihiko Yamazaki(Univ. of Tokyo)
Secretary Takefumi Hiraguri(NTT) / Gou Hasegawa(Ritsumeikan Univ.) / Mitsuru Maeda(Nagoya Univ.) / Kiyoshi Kiyokawa(NTT) / Hiroyuki Bandoh(Oosaka Inst. of Tech.) / Toshihiko Yamazaki(NTT)
Assistant Yoshiaki Nishikawa(NEC) / Ryoichi Kataoka(KDDI Research) / Kimiko Kawashima(NTT) / Masato Tsukada(NEC) / Takashi Yamazoe(Seikei Univ.) / Naoya Isoyama(NAIST) / Takenori Hara(DNP) / Mitsuhiro Goto(NTT) / Shunsuke Iwamura(NHK) / Shinobu Kudo(NTT)

Paper Information
Registration To Technical Committee on Communication Quality / Technical Committee on Image Media Quality / Technical Committee on Media Experience and Virtual Environment / Technical Committee on Image Engineering
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Consideration on Estimation Accuracy Improvement of Unlearned Music Pieces in Music Listener's Emotion Estimation Using Bio-signals
Sub Title (in English)
Keyword(1) Bio-signals
Keyword(2) Music Listener
Keyword(3) Emotion Estimation
Keyword(4) Unlearned Music Pieces
Keyword(5) Machine Learning
1st Author's Name Nanami Tanizawa
1st Author's Affiliation Waseda University(Waseda Univ.)
2nd Author's Name Mutsumi Suganuma
2nd Author's Affiliation Waseda University(Waseda Univ.)
3rd Author's Name Wataru Kameyama
3rd Author's Affiliation Waseda University(Waseda Univ.)
Date 2022-03-10
Paper # CQ2021-118
Volume (vol) vol.121
Number (no) CQ-421
Page pp.pp.100-105(CQ),
#Pages 6
Date of Issue 2022-03-02 (CQ)