Presentation 2020-12-14
Sound source separation method for use in live concerts
Ryotaro Yamada, Kota Takahashi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In live concerts, musical instrument sounds are mixed at vocal microphone, which makes it difficult to mix properly. To enable proper mixing, we separate vocal components from observed signal at vocal microphone in real time. In this paper, we propose an online AuxIVA that specializes in maintaining the vocal band as a sound source separation method for use in live concerts.In addition, the proposed method was evaluated by an objective evaluation experiment simulating the environment of a live concert and a subjective evaluation experiment using actual recording data in a live house. In the objective evaluation experiment, the proposed method obtained higher SDR, SIR and SAR than the conventional AuxIVA. In the subjective evaluation experiment, the proposed method received the highest evaluation in terms of overall quality.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Independent component analysis / Sparseness / Music Audio signal / Source separation / Real time
Paper # EA2020-47
Date of Issue 2020-12-07 (EA)

Conference Information
Committee EA
Conference Date 2020/12/14(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English) Engineering/Electro Acoustics, and Related Topics
Chair Kenichi Furuya(Oita Univ.)
Vice Chair Yoshinobu Kajikawa(Kansai Univ.) / Kentaro Matsui(NHK)
Secretary Yoshinobu Kajikawa(Univ. of Tokyo) / Kentaro Matsui(NTT)
Assistant Yukou Wakabayashi(Tokyo Metropolitan Univ.) / Tatsuya Komatsu(LINE)

Paper Information
Registration To Technical Committee on Engineering Acoustics
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Sound source separation method for use in live concerts
Sub Title (in English)
Keyword(1) Independent component analysis
Keyword(2) Sparseness
Keyword(3) Music Audio signal
Keyword(4) Source separation
Keyword(5) Real time
1st Author's Name Ryotaro Yamada
1st Author's Affiliation The University of Electro-Communications(UEC)
2nd Author's Name Kota Takahashi
2nd Author's Affiliation The University of Electro-Communications(UEC)
Date 2020-12-14
Paper # EA2020-47
Volume (vol) vol.120
Number (no) EA-296
Page pp.pp.7-12(EA),
#Pages 6
Date of Issue 2020-12-07 (EA)