| Presentation | 2017-12-22 A Sound Source Separation Method for Multiple Person Speech Recognition using Wavelet Analysis Based on Sound Source Position Obtained by Depth Sensor Nobuhiro Uehara, Kazuo Ikeshiro, Hiroki Imamura, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Recently, voice information guidance systems are used for only one person in operating at a city hall. To realize operating for multiple people simultaneously, we propose a sound source separation method using wavelet analysis based on positions of user obtained by depth sensor. Through the results of evaluation experiments, we found the proposed method was equal to or greater than that of a conventional method in recognition accuracy. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Speech Recognition / Sound Source Separation / Noise Reduction / Depth Image / Sparse Modeling |
| Paper # | SP2017-63 |
| Date of Issue | 2017-12-14 (SP) |
| Conference Information | |
| Committee | NLC / IPSJ-NL / SP / IPSJ-SLP |
|---|---|
| Conference Date | 2017/12/20(3days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Waseda Univ. Green Computing Systems Research Organization |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | The 4th Natural Language Processing Symposium & The 19th Spoken Language Symposium |
| Chair | Hiroshi Kanayama(IBM) / Kentaro Inui(Tohoku Univ.) / Yoichi Yamashita(Ritsumeikan Univ.) / Nobuaki Minematsu(Univ. Tokyo) |
| Vice Chair | Takeshi Sakaki(Hottolink) / Kazutaka Shimada(Kyushu Inst. of Tech.) / / Hiroki Mori(Utsunomiya Univ.) |
| Secretary | Takeshi Sakaki(Ryukoku Univ.) / Kazutaka Shimada(NTT) / (Osaka Univ.) / Hiroki Mori(Tokyo Inst. of Tech.) / (Mixi Co. Ltd.) |
| Assistant | Mitsuo Yoshida(Toyohashi Univ. of Tech.) / Takeshi Kobayakawa(NICT) / / Kei Hashimoto(Nagoya Inst. of Tech.) / Satoshi Kobashikawa(NTT) |
| Paper Information | |
| Registration To | Technical Committee on Natural Language Understanding and Models of Communication / Special Interest Group on Natural Language / 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) | A Sound Source Separation Method for Multiple Person Speech Recognition using Wavelet Analysis Based on Sound Source Position Obtained by Depth Sensor |
| Sub Title (in English) | |
| Keyword(1) | Speech Recognition |
| Keyword(2) | Sound Source Separation |
| Keyword(3) | Noise Reduction |
| Keyword(4) | Depth Image |
| Keyword(5) | Sparse Modeling |
| 1st Author's Name | Nobuhiro Uehara |
| 1st Author's Affiliation | Soka University(Soka Univ.) |
| 2nd Author's Name | Kazuo Ikeshiro |
| 2nd Author's Affiliation | Soka University(Soka Univ.) |
| 3rd Author's Name | Hiroki Imamura |
| 3rd Author's Affiliation | Soka University(Soka Univ.) |
| Date | 2017-12-22 |
| Paper # | SP2017-63 |
| Volume (vol) | vol.117 |
| Number (no) | SP-368 |
| Page | pp.pp.79-83(SP), |
| #Pages | 5 |
| Date of Issue | 2017-12-14 (SP) |