A robust blind source separation algorithm based on generalized variance

To solve the problem of blind source separation, a robust algorithm based on generalized variance is presented by exploiting the different temporal structure of uncorrelated source signals. In contrast to higher order cumulant techniques, this algorithm is based on second order statistical characteristic of observation signals, can blindly separate super-Gaussian and sub-Gaussian signals successfully at the same time without adjusting the contrast function, and the computation burden of it is relatively light. Simulation results confirm that the algorithm is efficient and feasible.