Maximum likelihood estimators and Cramer-Rao bounds in source separation

Abstract This presentation deals with blind source separation. Firstly, the model is recalled. Then, our approach based on the maximum-likelihood principle is developed. We show that the estimators are based on higher-order statistics (HOS). Then we prove the unbiasedness of the estimator and give the Cramer-Rao bounds. Simulation results illustrate the potentialities of this new algorithm of source separation.