| Project/Area Number |
15K01459
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Rehabilitation science/Welfare engineering
|
|---|
| Research Institution | Waseda University (2017-2018)
Kagawa University (2015-2016) |
|---|
Principal Investigator |
|
|---|
| Research Collaborator |
Thanh Vo Nhu University of Science and Technology
|
|---|
| Project Period (FY) |
2015-04-01 – 2019-03-31
|
| Project Status |
Completed (Fiscal Year 2018)
|
| Budget Amount *help |
¥4,810,000 (Direct Cost: ¥3,700,000、Indirect Cost: ¥1,110,000)
Fiscal Year 2017: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2016: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Fiscal Year 2015: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
|
|---|
| Keywords | 知能ロボット / ソフトロボット / 人工知能 / 音声生成 / 聴覚フィードバック / 脳内ネットワーク / 音声認識 / 発声障害 / 機械学習 |
|---|
| Outline of Final Research Achievements |
We have developed a talking robot, which is a mechanical vocalization system by modeling the human vocal articulatory system. The robot is constructed with mechanical parts that are made by referring to human vocal organs biologically and functionally. In this project, newly redesigned organs were developed for extending the speaking capability.
In human speech, the timing function is important for determining its duration, stress and rhythm. The cerebellum plays a key role in the coordination, precision and timing of motor responses. We have developed a robotic brain, which generates human-like vocal sounds using a simplified cerebellum-like neural network model as the timing function. The brain model was designed using the System Generator software, and implemented in a hardware co-simulated with a FPGA. We verified that the learning capability of the cerebellar-like neural network was applicable to speaking for generating a human-like utterance with prosodic features.
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究は、人間の音声生成機構を全て機械的に再現した発話ロボットを構築するばかりでなく、音声の自律獲得に拘わる脳機能を再現した学習機構を実装し、音声から口内の発話動作を獲得して音声生成を行うシステムを実現した。これにより、人間の様に学習によって発話動作及び音声を獲得することが出来る機械機構を再現でき、更に人間の構音動作との比較から、発話障害の訓練装置の実現に貢献できる。
人間は、聴覚フィードバックによって各発話器官を統合的に制御して、安定した発話をおこなう手法を、後天的に獲得している。人間の音声学習機構との比較、解析を行っていくことにより、脳における情報の認知・生成メカニズムの解明につながる。
|
