Presentation 2020-01-24
[Short Paper] CNN-based Music Emotion and Theme Recognition Featuring Shallow Architecture
Shengzhou Yi, Xueting Wang, Toshihiko Yamasaki,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose several convolutional neural networks to recognize emotions and themes conveyed by the audio tracks. We applied these models on audio data from Jamendo. As a result, we find that a relatively shallow VGG-style neural network achieves better performance.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Music emotion recognitionMusic theme recognitionCNN
Paper # MVE2019-32
Date of Issue 2020-01-16 (MVE)

Conference Information
Committee MVE / IPSJ-CVIM
Conference Date 2020/1/23(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Kenji Mase(Nagoya Univ.)
Vice Chair Masayuki Ihara(NTT)
Secretary Masayuki Ihara(Nagoya Univ.) / (NTT)
Assistant Satoshi Nishiguchi(Oosaka Inst. of Tech.) / Masanori Yokoyama(NTT) / Shogo Fukushima(Univ. of ToKyo)

Paper Information
Registration To Technical Committee on Media Experience and Virtual Environment / Special Interest Group on Computer Vision and Image Media
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) [Short Paper] CNN-based Music Emotion and Theme Recognition Featuring Shallow Architecture
Sub Title (in English)
Keyword(1) Music emotion recognitionMusic theme recognitionCNN
1st Author's Name Shengzhou Yi
1st Author's Affiliation The University of Tokyo(UTokyo)
2nd Author's Name Xueting Wang
2nd Author's Affiliation The University of Tokyo(UTokyo)
3rd Author's Name Toshihiko Yamasaki
3rd Author's Affiliation The University of Tokyo(UTokyo)
Date 2020-01-24
Paper # MVE2019-32
Volume (vol) vol.119
Number (no) MVE-386
Page pp.pp.99-100(MVE),
#Pages 2
Date of Issue 2020-01-16 (MVE)