Presentation 2019-07-18
[Poster Presentation] A study of source separation method for non-negative matrix factorization using machine learning
Satoru Jomae, Kenko Ota, Hideaki Yoshino,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We proposed a sound source separation method which consists of Non-negative matrix factorization and deep neural network. Although this method estimated musical instruments name of each amplitude spectrum using DNN, this method estimated the pitch of amplitude spectrum based on the correlation coefficient. Hence, in this paper, we improved the proposed method so that the proposed method estimates both musical instruments name and the pitch, simultaneously. In addition, we clarified the classification accuracy.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Non-negative Matrix Factorization / Deep Learning / Sound Source Separation
Paper # CQ2019-48
Date of Issue 2019-07-11 (CQ)

Conference Information
Committee CQ
Conference Date 2019/7/18(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Niigata Univ.
Topics (in Japanese) (See Japanese page)
Topics (in English) Assessment, Measurement and Control of QoE and QoS, etc.
Chair Hideyuki Shimonishi(NEC)
Vice Chair Jun Okamoto(NTT) / Takefumi Hiraguri(Nippon Inst. of Tech.)
Secretary Jun Okamoto(Nippon Inst. of Tech.) / Takefumi Hiraguri(Doshisha Univ.)
Assistant Chikara Sasaki(KDDI Research) / Yoshiaki Nishikawa(NEC) / Takuto Kimura(NTT)

Paper Information
Registration To Technical Committee on Communication Quality
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) [Poster Presentation] A study of source separation method for non-negative matrix factorization using machine learning
Sub Title (in English)
Keyword(1) Non-negative Matrix Factorization
Keyword(2) Deep Learning
Keyword(3) Sound Source Separation
1st Author's Name Satoru Jomae
1st Author's Affiliation Nippon Institute of Technology(NIT)
2nd Author's Name Kenko Ota
2nd Author's Affiliation Nippon Institute of Technology(NIT)
3rd Author's Name Hideaki Yoshino
3rd Author's Affiliation Nippon Institute of Technology(NIT)
Date 2019-07-18
Paper # CQ2019-48
Volume (vol) vol.119
Number (no) CQ-125
Page pp.pp.63-64(CQ),
#Pages 2
Date of Issue 2019-07-11 (CQ)