Integration of Event Related Brain Potentials into Speech Recognition Framework
| Project/Area Number |
26870371
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Cognitive science
Perceptual information processing
|
|---|
| Research Institution | Nara Institute of Science and Technology |
|---|
Principal Investigator |
SAKRIANI SAKTI 奈良先端科学技術大学院大学, 情報科学研究科, 助教 (00395005)
|
|---|
| Project Period (FY) |
2014-04-01 – 2017-03-31
|
| Project Status |
Completed (Fiscal Year 2016)
|
| Budget Amount *help |
¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
Fiscal Year 2015: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Fiscal Year 2014: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
|
|---|
| Keywords | 音声情報処理 / 脳認知科学 / 音声認識 / 事象関連電位 / 脳波 |
|---|
| Outline of Final Research Achievements |
Most of ASR systems exist today are still tuned by minimizing word error rate, in which all errors from any words like functional words or fillers are treated in a uniform manner. In fact, the impact of all errors is not the same, but how big and differences are the impact are still unknown. To align with human perception, in this research I propose to utilize the event-related brain potential (ERP) studies into ASR framework, in which the human cognitive process during language comprehension is directly analysis and the possibilities to incorporate within ASR framework are investigated. We were successfully perform the ERP experiments given the ASR results, and we can confirmed that a difference occurs in the EEG/ERP signal when perceiving the communication failure factor. Furthermore, we can learn also how to incorporate different knowledge in ASR framework. We also have opportunities to collaborate with some research institutes from Indonesia, Vietnam, and France.
|
Report
(4 results)
Research Products
(48 results)
-
-
-
-
-
[Journal Article] Gated Recurrent Neural Tensor Network2016
Author(s)
Andros Tjandra, Sakriani Sakti, Ruli Manurung, Mirna Adriani, Satoshi Nakamura
-
Journal Title
Proceedings of The 2016 International Joint Conference on Neural Networks (IJCNN 2016)
Volume: Vol. 1
Pages: 448-456
DOI
Related Report
Peer Reviewed / Int'l Joint Research / Acknowledgement Compliant
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
[Journal Article] 単語視認時の脳波信号を用いた未知語知覚検出2014
Author(s)
Takafumi Sasakura, Sakti Sakriani, Neubig Graham, Tomoki Toda, Satoshi Nakamura
-
Journal Title
SIG-SLUD-B402
Volume: Vol. 1
Pages: 57-62
NAID
Related Report
Acknowledgement Compliant
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
