Single-trial-EEG-based SSBCIJ system: generalization to continuous silent speech recognition
| Project/Area Number |
15K00276
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Human interface and interaction
|
|---|
| Research Institution | Kyushu Institute of Technology |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
井上 勝裕 九州工業大学, 大学院情報工学研究院, 教授 (00150516)
齊藤 剛史 九州工業大学, 大学院情報工学研究院, 准教授 (10379654)
|
|---|
| Project Period (FY) |
2015-04-01 – 2018-03-31
|
| Project Status |
Completed (Fiscal Year 2017)
|
| Budget Amount *help |
¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
Fiscal Year 2017: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2016: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2015: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
|
|---|
| Keywords | サイレントスピーチ / 脳波 / BCI / 連続音声認識 / 単語 / 文節 / 実時間性 / SSBCIJ / decoding / wireless / real-time / 母音・単語・音節 / self monitoring / RNN / Elman network / SSRS / 単一試行脳波 / 運動準備電位 / Kalman filter / HMM |
|---|
| Outline of Final Research Achievements |
Our previous study in scalp-recorded-EEG-based silent speech Brain-Computer Interface in Japapnese (SSBCIJ) had been limitted to decoding of silent vowels and two-hiragana characters. This research addressed itself to development algorithm that enables us to decode silent words and phrases of more than three moras, and to design of real-time SSBCIJ system for a patient with spinal muscular atrophy.
|
Report
(4 results)
Research Products
(28 results)
