Outdoor sound collection for auditory scene analysis in a daily life and its applications

2017 Fiscal Year Final Research Report

• Project/Area Number: 15K00255
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Perceptual information processing
• 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): 2015-04-01 – 2018-03-31
• Keywords: 音環境理解 / ロボット聴覚 / 音源定位 / 音源分離 / 音声強調 / 環境音

Outline of Final Research Achievements

Sound signal processing to understand daily life sounds is investigated in this project.　 Sound source localization, sound source separation, and sound source emphasis methods are developed. Since many kinds of sounds are radiated in daily environment, it is hard to optimize recoding level in advance. I investigated how difficult for optimizing the level with conventional recording devices. And I also investigated the task of detecting the sound source direction and the speech signal enhancement method in the environment where the music flows in the background. In the everyday sound environment, since the number of sound sources in the environment cannot be known in advance, the sound source separation task in environments where there are sound sources more than the number of microphones, especially the target signal emphasis method specialized for speech and its parameter learning method Was developed.

Free Research Field

音声信号処理，ロボット聴覚