Technical Program

Paper Detail

Paper:	SAM-P1.8
Session:	Source Localization and Tracking
Time:	Tuesday, May 16, 10:30 - 12:30
Presentation:	Poster
Topic:	Sensor Array and Multichannel Signal Processing: Source localization, separation, classification, and tracking
Title:	ROBUST TRACKING OF MULTIPLE SOUND SOURCES BY SPATIAL INTEGRATION OF ROOM AND ROBOT MICROPHONE ARRAYS
Authors:	Kazuhiro Nakadai, Honda Research Institute Japan Co., Ltd., Japan; Hirofumi Nakajima, Nittobo Acoustic Engineering Co., Ltd., Japan; Masamitsu Murase, Satoshi Kaijiri, Kyoto University, Japan; Kentaro Yamada, Takahiro Nakamura, Yuji Hasagawa, Honda Research Institute Japan Co., Ltd., Japan; Hiroshi G. Okuno, Kyoto University, Japan; Hiroshi Tsujino, Honda Research Institute Japan Co., Ltd., Japan
Abstract:	Sound tracking is an important function for a robot, because the robot should recognize where a sound event is from. This paper addresses sound tracking by integrating a room and a robot microphone array. The room microphone array consists of 64 microphones attached to the walls. It provides 2D localization based on weighted delay-and-sum beamforming. The robot microphone array consists of eight microphones installed on a robot head, and localizes sound sources in azimuth. The localization results are integrated to track sound sources by using a particle filter for multiple sound sources. The results show that particle filter based integration reduces localization errors and provides robust 2D sound tracking.