Date: October 21, 2005

Time: 3:00 p.m.

Location: GCATT Room 325

Speaker(s): Ryo Mukai (NTT Communications Science Labs)

Title: Blind Source Separation and DOA Estimation Using Small 3-D Microphone Array
Ryo Mukai, Hiroshi Sawada, Shoko Araki, Shoji Makino

Abstract:
We present a prototype system for blind source separation (BSS) of many speech signals. There have been many studies on BSS in a reverberant environment, however most of them have assumed only two or three source signals. Our system uses 8 microphones located at the vertexes of a 4cm cube and has the ability to separate signals distributed in three-dimensional space. The mixed signals observed by the microphone array are processed by Independent Component Analysis (ICA) in the frequency domain and separated into a given number of signals (up to 4 in real-time mode, and up to 8 in batch mode). The system estimates direction of arrival (DOA) of the source signals as a by-product of the separation process. We carried out experiments in an ordinary office and obtained more than 20 dB of SIR improvement. We will perform a demonstration of real-time separation.

Bio:
Ryo Mukai received the B.S. and the M.S. degrees in information science from the University of Tokyo, Japan, in 1990 and 1992, respectively. He joined NTT in 1992. From 1992 to 2000, he was engaged in research and development of processor architecture for network service systems and distributed network systems. Since 2000, he has been with NTT Communication Science Laboratories, where he is engaged in research of blind source separation. His current research interests include digital signal processing and its applications. He is a senior member of the IEEE, a member of ACM, the Acoustical Society of Japan (ASJ), IEICE, and the IPSJ.

Date:	October 21, 2005
Time:	3:00 p.m.
Location:	GCATT Room 325
Speaker(s):	Ryo Mukai (NTT Communications Science Labs)
Title:	Blind Source Separation and DOA Estimation Using Small 3-D Microphone Array Ryo Mukai, Hiroshi Sawada, Shoko Araki, Shoji Makino
Abstract:	We present a prototype system for blind source separation (BSS) of many speech signals. There have been many studies on BSS in a reverberant environment, however most of them have assumed only two or three source signals. Our system uses 8 microphones located at the vertexes of a 4cm cube and has the ability to separate signals distributed in three-dimensional space. The mixed signals observed by the microphone array are processed by Independent Component Analysis (ICA) in the frequency domain and separated into a given number of signals (up to 4 in real-time mode, and up to 8 in batch mode). The system estimates direction of arrival (DOA) of the source signals as a by-product of the separation process. We carried out experiments in an ordinary office and obtained more than 20 dB of SIR improvement. We will perform a demonstration of real-time separation.
Bio:	Ryo Mukai received the B.S. and the M.S. degrees in information science from the University of Tokyo, Japan, in 1990 and 1992, respectively. He joined NTT in 1992. From 1992 to 2000, he was engaged in research and development of processor architecture for network service systems and distributed network systems. Since 2000, he has been with NTT Communication Science Laboratories, where he is engaged in research of blind source separation. His current research interests include digital signal processing and its applications. He is a senior member of the IEEE, a member of ACM, the Acoustical Society of Japan (ASJ), IEICE, and the IPSJ.