Improvement of function in Robot Audition based on Active Audition
| Project/Area Number |
21700195
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
Perception information processing/Intelligent robotics
|
|---|
| Research Institution | Kyoto University |
|---|
Principal Investigator |
TAKAHASHI Toru 京都大学, 情報学研究科, GCOE助教 (30419494)
|
|---|
| Project Period (FY) |
2009 – 2011
|
| Project Status |
Completed (Fiscal Year 2011)
|
| Budget Amount *help |
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2011: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2010: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2009: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
|
|---|
| Keywords | ロボット聴覚 / 音源定位 / 音源分離 / 分離音声認識 / 音源追跡 / 音声認識 / アクティブオーディション / ミッシングフィーチャ理論 / 同時発話認識 / 実環境下音声認識 / ヒューマノイドロボット / HRP-2 |
|---|
| Research Abstract |
The accuracy of sound source localization, tracking, separation, and separated speech recognition is improved for robot audition. These improvements enable that a robot recognizes speech while the robot is moving and is gesturing, such as active audition. Restriction on robot's motion is reduced for active audition. A robot can close to a target sound source to improve signal-to-noise ratio. A robot can move to the best place for making angle between multiple sound sources wider. The improved system preserves speech recognition accuracy from noise of robot motion, when a robot's body doesn' t locates between sound source and microphone.
|
Report
(4 results)
Research Products
(108 results)
