Title :
Real world blind separation of convolved speech signals
Author :
Kawamoto, M. ; Matsuoka, K. ; Ohnishi, N.
Author_Institution :
RIKEN, Inst. of Phys. & Chem. Res., Saitama, Japan
Abstract :
This paper deals with blind separation that can extract original signals from their mixtures observed in a normal room. Our method achieves blind separation by making the mixed signals not correlating with each other. The validity of the proposed method has been confirmed by a computer simulation and an experiment in an anechoic room. In this paper, we apply our method to an experiment that extracts two source signals from their mixtures observed in a normal room
Keywords :
acoustic convolution; learning (artificial intelligence); neural nets; signal detection; speech processing; anechoic room; blind separation; convolution; learning; mixed signals; neural nets; signal extraction; speech signals; Autocorrelation; Computer simulation; Control engineering; Microphones; Microwave integrated circuits; Multiple signal classification; Neural networks; Signal processing; Speech; Testing;
Conference_Titel :
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-5529-6
DOI :
10.1109/IJCNN.1999.831090
