Presentation 2013-09-24
Speech Classification Using Brain Activity Signals
Atsushi NISHIMOTO, Natsue YOSHIMURA, Koji JIMURA, Hiroyuki KAMBARA, Duk SHIN, Takashi HANAKAWA, Yasuharu KOIKE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recently, Brain-Computer Interfaces (BCI) are used for handicapped individuals such as patients that have difficulty in communicating. In this study, we explored the possibilities of non-invasive BCIs for speech identification. Based on electroencephalogram (EEG) and functional magnetic resonance imaging (fMRI), EEG cortical current signals were estimated using Variational Bayesian Multimodal Encephalo Graphy (VBMEG) method. The results of experiments with Japanese vowels /a/ and /i/ showed that classification accuracies might be increased when using anatomical-based functional region of interests (ROIs).
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Brain-computer Interface / EEG / fMRI / vowel
Paper # MBE2013-43,NC2013-29
Date of Issue

Conference Information
Committee NC
Conference Date 2013/9/17(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Speech Classification Using Brain Activity Signals
Sub Title (in English)
Keyword(1) Brain-computer Interface
Keyword(2) EEG
Keyword(3) fMRI
Keyword(4) vowel
1st Author's Name Atsushi NISHIMOTO
1st Author's Affiliation Tokyo Institute of Technology:National Center of Neurology and Psychiatry()
2nd Author's Name Natsue YOSHIMURA
2nd Author's Affiliation Tokyo Institute of Technology:National Center of Neurology and Psychiatry
3rd Author's Name Koji JIMURA
3rd Author's Affiliation Tokyo Institute of Technology:National Center of Neurology and Psychiatry:CREST, Japan Science and Technology Agency
4th Author's Name Hiroyuki KAMBARA
4th Author's Affiliation Tokyo Institute of Technology:CREST, Japan Science and Technology Agency
5th Author's Name Duk SHIN
5th Author's Affiliation Tokyo Institute of Technology:CREST, Japan Science and Technology Agency
6th Author's Name Takashi HANAKAWA
6th Author's Affiliation National Center of Neurology and Psychiatry:PRESTO, Japan Science and Technology Agency
7th Author's Name Yasuharu KOIKE
7th Author's Affiliation Tokyo Institute of Technology:CREST, Japan Science and Technology Agency
Date 2013-09-24
Paper # MBE2013-43,NC2013-29
Volume (vol) vol.113
Number (no) 223
Page pp.pp.-
#Pages 6
Date of Issue