Title :
Direction of arrival estimation for multiple source signals using independent component analysis
Author :
Sawada, Hiroshi ; Mukai, Ryo ; Makino, Shoji
Author_Institution :
NTT Commun. Sci. Labs., NTT Corp., Kyoto, Japan
Abstract :
This paper presents a new method for estimating the directions of source signals. We assume a situation in which multiple source signals are mixed in a reverberant condition and observed at several sensors. The new method is based on independent component analysis, which separates mixed signals into original source signals. It can be applied where the number of sources is equal to the number of sensors, whereas the conventional methods based on subspace analysis, such as the MUSIC algorithm, are applicable where there are fewer sources than sensors. Even in cases where the MUSIC algorithm can be applied, the new method is better at estimating the directions of sources if they are closely placed.
Keywords :
array signal processing; direction-of-arrival estimation; independent component analysis; sensors; signal classification; array signal processing; direction of arrival estimation; independent component analysis; multiple source signals; reverberant condition; sensors; Algorithm design and analysis; Array signal processing; Direction of arrival estimation; Frequency; Independent component analysis; Laboratories; Multiple signal classification; Sensor arrays; Signal processing algorithms; Source separation;
Conference_Titel :
Signal Processing and Its Applications, 2003. Proceedings. Seventh International Symposium on
Print_ISBN :
0-7803-7946-2
DOI :
10.1109/ISSPA.2003.1224901