Presentation | 2021-03-03 [Poster Presentation] Noise-robust time-domain speech separation with basis signals for noise Kohei Ozamoto, Koji Iwano, Kuniaki Uto, Koichi Shinoda, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Recently, speech separation using deep learning has been extensively studied. TasNet, a time-domain method that directly inputs waveforms, converts speech into features by convolution, performs separation, and reconstructs waveform by convolution on separated features. The convolutional filter is called basis signals and is trained to improve separation accuracy between speakers. The separation performance of this method is greatly degraded when the speech contains noise. Therefore, we propose TasNet with noise basis signals (TasNet-NB), a method to improve separation performance by adding noise basis signals to speaker's basis signals. We evaluate the method on WHAM! dataset and show that it improves SI-SDRi from 13.7 to 14.6. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Speech separation / single channel / time-domain / deep learning |
Paper # | EA2020-70,SIP2020-101,SP2020-35 |
Date of Issue | 2021-02-24 (EA, SIP, SP) |
Conference Information | |
Committee | EA / US / SP / SIP / IPSJ-SLP |
---|---|
Conference Date | 2021/3/3(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Online |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Speech, Engineering/Electro Acoustics, Signal Processing, Ultrasonics, and Related Topics |
Chair | Kenichi Furuya(Oita Univ.) / Hikaru Miura(Nihon Univ.) / Hisashi Kawai(NICT) / Kazunori Hayashi(Kyoto Univ.) / 北岡 教英(豊橋技科大) |
Vice Chair | Yoshinobu Kajikawa(Kansai Univ.) / Kentaro Matsui(NHK) / Jun Kondo(Shizuoka Univ.) / Yoshikazu Koike(Shibaura Inst. of Tech.) / / Yukihiro Bandou(NTT) / Toshihisa Tanaka(Tokyo Univ. Agri.&Tech.) |
Secretary | Yoshinobu Kajikawa(Univ. of Tokyo) / Kentaro Matsui(NTT) / Jun Kondo(Doshisha Univ.) / Yoshikazu Koike(Tohoku Univ.) / (Univ. of Tokyo) / Yukihiro Bandou(Waseda Univ.) / Toshihisa Tanaka(Hosei Univ.) / (Waseda Univ.) |
Assistant | Yukou Wakabayashi(Tokyo Metropolitan Univ.) / Tatsuya Komatsu(LINE) / Shinnosuke Hirata(Tokyo Inst. of Tech.) / Yusuke Ijima(NTT) / Yuichi Tanaka(Tokyo Univ. Agri.&Tech.) |
Paper Information | |
Registration To | Technical Committee on Engineering Acoustics / Technical Committee on Ultrasonics / Technical Committee on Speech / Technical Committee on Signal Processing / Special Interest Group on Spoken Language Processing |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | [Poster Presentation] Noise-robust time-domain speech separation with basis signals for noise |
Sub Title (in English) | |
Keyword(1) | Speech separation |
Keyword(2) | single channel |
Keyword(3) | time-domain |
Keyword(4) | deep learning |
1st Author's Name | Kohei Ozamoto |
1st Author's Affiliation | Tokyo Institute of Technology(Tokyo Tech) |
2nd Author's Name | Koji Iwano |
2nd Author's Affiliation | Tokyo City University(TCU) |
3rd Author's Name | Kuniaki Uto |
3rd Author's Affiliation | Tokyo Institute of Technology(Tokyo Tech) |
4th Author's Name | Koichi Shinoda |
4th Author's Affiliation | Tokyo Institute of Technology(Tokyo Tech) |
Date | 2021-03-03 |
Paper # | EA2020-70,SIP2020-101,SP2020-35 |
Volume (vol) | vol.120 |
Number (no) | EA-397,SIP-398,SP-399 |
Page | pp.pp.63-67(EA), pp.63-67(SIP), pp.63-67(SP), |
#Pages | 5 |
Date of Issue | 2021-02-24 (EA, SIP, SP) |