Subspace method for blind separation of sources and for a convolutive mixture model
Résumé
For the convolutive mixture, a subspace method to separate the sources is proposed. It is showed that after using only the second order statistic but more sensors than sources, the convolutive mixture can be identified up to instantaneous mixture. Furthmore, the sources can be separated by any algorithm for instantaneous mixture (based in generally on the fourth order statistics).