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)
|
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.
|