Development of speech and environmental sounds and background sound simultaneous recognition system for robot

2014 Fiscal Year Final Research Report

• Project/Area Number: 24700169
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Perception information processing/Intelligent robotics
• Research Institution: Osaka Sangyo University
• Principal Investigator: TAKAHASHI Toru 大阪産業大学, デザイン工学部, 准教授 (30419494)
• Project Period (FY): 2012-04-01 – 2015-03-31
• Keywords: 音声認識 / 環境音認識 / 背景音認識 / マイクロホンアレイ / ヒューマノイドロボット / ヒュマンコンピュータインタラクション / コミュニケーション / ロボット聴覚

Outline of Final Research Achievements

A system that can recognize speech and environmental sound and background sound into a robot with a microphone-array has been developed. It detects the directions of the sound sources, and then separated into each sound for directions. The subsystem is realized by the method of selecting the recognizer depending on whether speech or environmental sounds, after the separated sound is determined whether speech or non-speech. In addition, the remaining sound subtracting all the directional sounds is handled as the background sound. A background sound recognizer is also developed. Finally, the total system has been able to simultaneously recognize speech and environmental sound and background sound.

Free Research Field

音情報処理