Presentation | 2019-03-15 [Poster Presentation] Design and Evaluation of Ladder Denoising Autoencoder for Auditory Speech Feature Extraction of Overlapped Speech Separation Hiroshi Sekiguchi, Yoshiaki Narusue, Hiroyuki Morikawa, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Primates and mammalian distinguish overlapped speech sounds from one another by recognizing a single sound source whether temporal contour of auditory speech features in auditory neurons are similar.This is called as temporal synchronization detection and clustering function. The performance of this detection and clustering function depends on the former function that is auditory speech feature extraction. The feature extraction is needed to satisfy two requirements: 1) auditory speech features are mutually stochastic independent and 2) the feature extraction should allow various complicated sounds to be represented, which leads to non-linearity.This paper introduces non-linear sparse encoder decoder model as computational model, implements it with a ladder network, and finally evaluate that network behavior. We show that our trained network can output auditory speech features that are mutually stochastic independent. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Ladder Network / Speech Separation / Auditory Neuroscience / Auditory Speech Feature Extraction / stochastic independence |
Paper # | EA2018-155,SIP2018-161,SP2018-117 |
Date of Issue | 2019-03-07 (EA, SIP, SP) |
Conference Information | |
Committee | EA / SIP / SP |
---|---|
Conference Date | 2019/3/14(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | i+Land nagasaki (Nagasaki-shi) |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Engineering/Electro Acoustics, Signal Processing, Speech, and Related Topics |
Chair | Suehiro Shimauchi(Kanazawa Inst. of Tech.) / Shogo Muramatsu(Niigata Univ.) / Yoichi Yamashita(Ritsumeikan Univ.) |
Vice Chair | Kenichi Furuya(Oita Univ.) / Kanji Watanabe(Akita Pref. Univ.) / Naoyuki Aikawa(TUS) / Kazunori Hayashi(Osaka City Univ) / Akinobu Ri(Nagoya Inst. of Tech.) |
Secretary | Kenichi Furuya(Shizuoka Inst. of Science and Tech.) / Kanji Watanabe(NHK) / Naoyuki Aikawa(Takushoku Univ.) / Kazunori Hayashi(Hiroshima Univ.) / Akinobu Ri(Kyoto Univ.) |
Assistant | Keisuke Imoto(Ritsumeikan Univ.) / Daisuke Morikawa(Toyama Pref Univ.) / Katsumi Konishi(Hosei Univ.) / hyihsin(Takushoku Univ.) / Tomoki Koriyama(Tokyo Inst. of Tech.) / Satoshi Kobashikawa(NTT) |
Paper Information | |
Registration To | Technical Committee on Engineering Acoustics / Technical Committee on Signal Processing / Technical Committee on Speech |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | [Poster Presentation] Design and Evaluation of Ladder Denoising Autoencoder for Auditory Speech Feature Extraction of Overlapped Speech Separation |
Sub Title (in English) | |
Keyword(1) | Ladder Network |
Keyword(2) | Speech Separation |
Keyword(3) | Auditory Neuroscience |
Keyword(4) | Auditory Speech Feature Extraction |
Keyword(5) | stochastic independence |
1st Author's Name | Hiroshi Sekiguchi |
1st Author's Affiliation | The University of Tokyo(Univ. of Tokyo) |
2nd Author's Name | Yoshiaki Narusue |
2nd Author's Affiliation | The University of Tokyo(Univ. of Tokyo) |
3rd Author's Name | Hiroyuki Morikawa |
3rd Author's Affiliation | The University of Tokyo(Univ. of Tokyo) |
Date | 2019-03-15 |
Paper # | EA2018-155,SIP2018-161,SP2018-117 |
Volume (vol) | vol.118 |
Number (no) | EA-495,SIP-496,SP-497 |
Page | pp.pp.329-333(EA), pp.329-333(SIP), pp.329-333(SP), |
#Pages | 5 |
Date of Issue | 2019-03-07 (EA, SIP, SP) |