Presentation 2020-12-01
[Tutorial Lecture] A Theory for Controlling Musical Noise Based on Higher-Order Statistics
Ryoichi Miyazaki, Takuya Fujimura,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Although nonlinear speech enhancement methods can significantly eliminate background noise, it is known to generate musical noise. Musical noise is an artificial noise that is aurally very disagreeable and does not exist in nature. In this paper, we present a case study of the derivation of internal parameters that suppress the occurrence of musical noise by statistical and theoretical analysis. The {it musical-noise-free theorem}, which does not generate any musical noise, is also described. In addition, we report on deep learning-based musical noise elimination.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Musical noise / speech enhancement / higher-order statistics / deep learning
Paper # SIS2020-30
Date of Issue 2020-11-24 (SIS)

Conference Information
Committee SIS
Conference Date 2020/12/1(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English) Smart Personal Systems, etc.
Chair Noriaki Suetake(Yamaguchi Univ.)
Vice Chair Tomoaki Kimura(Kanagawa Inst. of Tech.) / Naoto Sasaoka(Tottori Univ.)
Secretary Tomoaki Kimura(Kindai Univ.) / Naoto Sasaoka(National Inst. of Tech., Ube College)
Assistant Yukihiro Bandoh(NTT) / Soh Yoshida(Kansai Univ.)

Paper Information
Registration To Technical Committee on Smart Info-Media Systems
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) [Tutorial Lecture] A Theory for Controlling Musical Noise Based on Higher-Order Statistics
Sub Title (in English)
Keyword(1) Musical noise
Keyword(2) speech enhancement
Keyword(3) higher-order statistics
Keyword(4) deep learning
1st Author's Name Ryoichi Miyazaki
1st Author's Affiliation National Institute of Technology, Tokuyama College(NITTC)
2nd Author's Name Takuya Fujimura
2nd Author's Affiliation National Institute of Technology, Tokuyama College(NITTC)
Date 2020-12-01
Paper # SIS2020-30
Volume (vol) vol.120
Number (no) SIS-269
Page pp.pp.18-23(SIS),
#Pages 6
Date of Issue 2020-11-24 (SIS)