Study on Human-Machine Communication and Learning through Content-Awareness
| Project/Area Number |
26280059
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Partial Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Perceptual information processing
|
|---|
| Research Institution | Kobe University |
|---|
Principal Investigator |
ARIKI Yasuo 神戸大学, 都市安全研究センター, 名誉教授 (10135519)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
滝口 哲也 神戸大学, 都市安全研究センター, 准教授 (40397815)
榎並 直子 神戸大学, 自然科学系先端融合研究環重点研究部, 助教 (80628925)
|
|---|
| Project Period (FY) |
2014-04-01 – 2017-03-31
|
| Project Status |
Completed (Fiscal Year 2016)
|
| Budget Amount *help |
¥14,040,000 (Direct Cost: ¥10,800,000、Indirect Cost: ¥3,240,000)
Fiscal Year 2016: ¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
Fiscal Year 2015: ¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
Fiscal Year 2014: ¥4,940,000 (Direct Cost: ¥3,800,000、Indirect Cost: ¥1,140,000)
|
|---|
| Keywords | 音声認識 / 物体認識 / コミュニケーション / アウェアネス / 機能認識 / 学習 / 未知物体 / 音声対話 / リカーレントニューラルネットワーク / 意図認識 / 特定物体認識 / 一般物体認識 |
|---|
| Outline of Final Research Achievements |
We studied on a smooth communication method with computers under the assumption that human and computers can communicate each other through the common recognition that is called content awareness in this study. To realize the content awareness, the following five points were carried out and the associated research results were obtained;
(1)Objects and state recognition with high accuracy, (2)Utilization of object recognition in speech communication, (3)Unknown object recognition and learning, (4)Functional recognition of unknown object, (5)Speech communication with common knowledge about objects.
|
Report
(4 results)
Research Products
(32 results)
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
[Presentation] 物体特定のための顕著性2014
Author(s)
小篠裕子, 榎並直子, 有木康雄
Organizer
電子情報通信学会
Place of Presentation
幕張メッセ国際会議場 (千葉県・千葉市）
Year and Date
2014-10-09 – 2014-10-10
Related Report
-
-
-
-
