Blind Source Separation by Entropy Rate Minimization

Back to Publications


Blind Source Separation by Entropy Rate Minimization, Gérman Gómez-Herrero, Kalle Rutanen, Karen Egiazarian, Signal Processing Letters, IEEE, Volume 17, Issue 2, pp. 153-156, 2010.

Official paper


An algorithm for the blind separation of mutually independent and/or temporally correlated sources is presented in this letter. The algorithm is closely related to the maximum likelihood approach based on entropy rate minimization but uses a simpler contrast function that can be accurately and efficiently estimated using nearest-neighbor distances. The advantages of the new algorithm are highlighted using simulations and real electroencephalographic data.