Joint diagonalization of complex spatial-wavelet matrices for blind sources separation of non stationary sources

This communication concerns the problem of blind sources separation (BSS) of non stationary sources in the instantaneous mixture case. We consider an approach based on joint-diagonalization of some hermitian matrices constructed by a family of spatial complex cross-wavelet transform. We show that mixing matrix can be estimated by using some algebraic properties of considered matrices. Computer simulations are provided to demonstrate the effectiveness of the proposed method, which is compared with other approach based on the joint-diagonalization.