Title :
Blind separation of convolutive mixtures
Author :
Ehlers, F. ; Schuster, H.G.
Author_Institution :
Inst. fur Theor. Phys., Kiel Univ., Germany
Abstract :
In this paper we propose a two-step-algorithm for the blind separation of convolutive mixtures. We show that its application to automatic speech recognition in a noisy environment yields good results.
Keywords :
convolution; signal resolution; speech processing; speech recognition; automatic speech recognition; blind separation; convolutive mixtures; noisy environment; two-step-algorithm; Acoustic noise; Cost function; Eigenvalues and eigenfunctions; Finite impulse response filter; Frequency; Higher order statistics; Signal processing algorithms; Source separation; Speech recognition; Transfer functions;
Conference_Titel :
Circuits and Systems, 1997. Proceedings of the 40th Midwest Symposium on
Print_ISBN :
0-7803-3694-1
DOI :
10.1109/MWSCAS.1997.662306
