Blind separation for speech signal is the original purpose of BSS problem, and becomes the research attention of signal processing in recent years. Separation of speeches has an important theoretical importance in voice communications, acoustic target detection, etc. Blind source separation is a well-established signal processing problem. The sources to be estimated present some diversity in order to be efficiently retrieved. Assuming the transmitted signals to be mutually independent in a linear multiple-input-multiple-output (MIMO) memory-less system, the transmitted signal is subjected to Additive white Gaussian noise. The received signals are, hence, corrupted by inter-user interference (IUI), and we can model them as the outputs of a linear multiple-input-multiple-output (MIMO) memory-less system. In this paper, we have surveyed different techniques of blind signal separation.