Blind voice separation refers to retrieve a set of independent sources combined by an unknown destructive system. The proposed separation procedure is based on processing of the observed sources without having any information about the combinational model or statistics of the source signals. Also, the number of combined sources is usually predefined and it is difficult to estimate based on the combined sources. In this paper, a new algorithm is introduced to resolve these issues using empirical mode decomposition technique as a pre-processing step. The proposed method can determine precisely the number of mixed voice signals based on the energy and kurtosis criteria of the captured intrinsic mode functions. Also, the separation procedure employs a grey wolf optimization algorithm with a new cost function in the optimization procedure. The experimental results show that the proposed separation algorithm performs prominently better than the earlier methods in this context. Moreover, the simulation results in the presence of white noise emphasize the proper performance of the presented method and the prominent role of the presented cost function especially when the number of sources is high.
