In this paper we present a novel method for Blind Speech Separation of convolutive speech signals of moving speakers in highly reverberant rooms. The separation network used is a hybrid neural network, which performs separation of convolutive speech mixtures in the time domain, without any prior knowledge of the propagation media, based on the Maximum Likelihood Estimation (MLE) principle. The proposed method improves significantly (more than 13% in all adverse mixing situations) the performance of a phoneme-based continuous speech recognition system and therefore can be used as a front-end to separate simultaneous speech of speakers who are moving in reverberant rooms.