Adaptive subspace algorithm for blind separation of independent sources inconvolutive mixture

The advantage of the algorithm proposed in this correspondence is that it r educes a convolutive mixture to an instantaneous mixture by using only seco nd-order statistics (but more sensors than sources). Furthermore, the sourc es can be separated by using any algorithm applicable to an instantaneous m ixture. Otherwise, to ensure the convergence of our algorithm, we assume so me classical assumptions for blind separation of sources and some added sub space assumptions. Finally, the assumptions concerning the subspace model a nd their properties are emphasized in this correspondence.