Presentation | 2019-10-27 Word Recognition using word likelihood vector from speech-imagery EEG Satoka Hirata, Yurie Iribe, Kentaro Fukai, Kouichi Katsurada, Tsuneo Nitta, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Previous research suggests that humans manipulate the machine using their electroencephalogram called BCI (Brain Computer Interface). However, there are not existed effective methods for speech imagery recognition. In this report, we performed word recognition of 10 numbers using speech-imagery EEG signals that could be measured through a non-invasive technique to reduce user’s burden. After removing the noise contained in EEG signals, line spectra feature was extracted from the amplitude spectra obtained by LPA. Next, word likelihood vector was calculated based on line spectra feature. We carried out the word recognition experiment of 10 numbers using one or the other or both of line spectra and word likelihood vector to clear the effective features. As a result, it was clarified that the likelihood vector based method got the highest accuracy in all features. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Speech-imagery EEG / Word recognition / Likelihood vector |
Paper # | SP2019-29,WIT2019-28 |
Date of Issue | 2019-10-19 (SP, WIT) |
Conference Information | |
Committee | WIT / SP |
---|---|
Conference Date | 2019/10/26(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Daiichi Institute of Technology |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Daisuke Wakatsuki(Tsukuba Univ. of Tech.) / Hisashi Kawai(NICT) |
Vice Chair | Shinji Sakou(Nagoya Inst. of Tech.) / Akinobu Ri(Nagoya Inst. of Tech.) |
Secretary | Shinji Sakou(Saitama Industrial Tech. Center) / Akinobu Ri(Teikyo Univ.) |
Assistant | Manabi Miyagi(Tsukuba Univ. of Tech.) / Minako Hosono(AIST) / Aki Sugano(Nagoya Univ.) / Tomoki Koriyama(Tokyo Inst. of Tech.) / Yusuke Ijima(NTT) |
Paper Information | |
Registration To | Technical Committee on Well-being Information Technology / Technical Committee on Speech |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Word Recognition using word likelihood vector from speech-imagery EEG |
Sub Title (in English) | |
Keyword(1) | Speech-imagery EEG |
Keyword(2) | Word recognition |
Keyword(3) | Likelihood vector |
1st Author's Name | Satoka Hirata |
1st Author's Affiliation | Aichi Prefectual University(Aichi Prefectual Univ.) |
2nd Author's Name | Yurie Iribe |
2nd Author's Affiliation | Aichi Prefectual University(Aichi Prefectual Univ.) |
3rd Author's Name | Kentaro Fukai |
3rd Author's Affiliation | Tokyo University of Science(Tokyo Univ. of Science) |
4th Author's Name | Kouichi Katsurada |
4th Author's Affiliation | Tokyo University of Science(Tokyo Univ. of Science) |
5th Author's Name | Tsuneo Nitta |
5th Author's Affiliation | Waseda University/Toyohashi University of Technology(Waseda Univ./Toyohashi Univ. of Tech.) |
Date | 2019-10-27 |
Paper # | SP2019-29,WIT2019-28 |
Volume (vol) | vol.119 |
Number (no) | SP-250,WIT-251 |
Page | pp.pp.69-73(SP), pp.69-73(WIT), |
#Pages | 5 |
Date of Issue | 2019-10-19 (SP, WIT) |