Presentation | 2018-07-26 Single channel noisy speech recognition based on combination of noisy speech and enhanced speech Masakiyo Fujimoto, Hisashi Kawai, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In many cases, single channel speech enhancement seriously deteriorates speech recognition accuracy due to the influence of speech distortion. In this paper, we propose a method of single channel noise robust speech recognition based on feature-level combination of noisy speech and enhanced speech. In addition, we also reveal that further improvements are obtained by using DNN-level (sub-network) combination and a gating mechanism which can explicitly select adequate speech signal. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | noise robust speech recognition / speech enhancement / single-channel input / feature / sub-network combination / gating mechanism |
Paper # | SP2018-19 |
Date of Issue | 2018-07-19 (SP) |
Conference Information | |
Committee | SP / IPSJ-SLP |
---|---|
Conference Date | 2018/7/26(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Sago-Royal-Hotel (Hamamatsu) |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Speech recognition and understanding, dialog system, etc. |
Chair | Yoichi Yamashita(Ritsumeikan Univ.) / Masafumi Nishimura(Shizuoka Univ.) |
Vice Chair | Akinobu Ri(Nagoya Inst. of Tech.) |
Secretary | Akinobu Ri(Kyoto Univ.) / (Meijo Univ.) |
Assistant | Tomoki Koriyama(Tokyo Inst. of Tech.) / Satoshi Kobashikawa(NTT) |
Paper Information | |
Registration To | Technical Committee on Speech / 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) | Single channel noisy speech recognition based on combination of noisy speech and enhanced speech |
Sub Title (in English) | |
Keyword(1) | noise robust speech recognition |
Keyword(2) | speech enhancement |
Keyword(3) | single-channel input |
Keyword(4) | feature / sub-network combination |
Keyword(5) | gating mechanism |
1st Author's Name | Masakiyo Fujimoto |
1st Author's Affiliation | National Institute of Information and Communications Technology(NICT) |
2nd Author's Name | Hisashi Kawai |
2nd Author's Affiliation | National Institute of Information and Communications Technology(NICT) |
Date | 2018-07-26 |
Paper # | SP2018-19 |
Volume (vol) | vol.118 |
Number (no) | SP-160 |
Page | pp.pp.15-20(SP), |
#Pages | 6 |
Date of Issue | 2018-07-19 (SP) |