Presentation 2022-06-17
ブラインド音声抽出のためのランク制約付き空間共分散行列推定法における雑音欠落ランク空間基底選択に関する一考察
Koki Nishida, Norihiro Takamune, Daichi Kitamura, Hiroshi Saruwatari,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Rank-constrained spatial covariance matrix estimation (RCSCME) is a method for blind speech extraction. In RCSCME, we derive a more appropriate complementation method compared with the conventional complementation method from the consideration for the process that the spatial covariance matrix (SCM) of noise becomes rank-deficient. Then, we show the property of the common part of the conventional and proposed complementation methods. Furthermore, it is shown that the SCM of noise is included in the common part with ideal preprocessing of RCSCME. To confirm this experimentally, we propose RCSCME based on the new complementation method corresponding to the process of rank dificiency, and conduct several experiments to show that the SCM of noise is estimated in the region close to the common part and it is useful to constrain the SCM of noise to the common part.
Keyword(in Japanese) (See Japanese page)
Keyword(in English)
Paper # SP2022-6
Date of Issue 2022-06-10 (SP)

Conference Information
Committee SP / IPSJ-MUS / IPSJ-SLP
Conference Date 2022/6/17(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Tomoki Toda(Nagoya Univ.)
Vice Chair
Secretary (NTT) / (Univ. of Electro-Comm.)
Assistant Ryo Aihara(Mitsubishi Electric) / Daisuke Saito(Univ. of Tokyo)

Paper Information
Registration To Technical Committee on Speech / Special Interest Group on Music and Computer / Special Interest Group on Spoken Language Processing
Language JPN-ONLY
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English)
Sub Title (in English)
Keyword(1)
Keyword(2)
Keyword(3)
Keyword(4)
1st Author's Name Koki Nishida
1st Author's Affiliation The University Of Tokyo(The Univ. of Tokyo)
2nd Author's Name Norihiro Takamune
2nd Author's Affiliation The University Of Tokyo(The Univ. of Tokyo)
3rd Author's Name Daichi Kitamura
3rd Author's Affiliation National Institute of Technology, Kagawa Collage(NIT Kagawa)
4th Author's Name Hiroshi Saruwatari
4th Author's Affiliation The University Of Tokyo(The Univ. of Tokyo)
Date 2022-06-17
Paper # SP2022-6
Volume (vol) vol.122
Number (no) SP-81
Page pp.pp.18-23(SP),
#Pages 6
Date of Issue 2022-06-10 (SP)