盲信号分离(BSS)是指在对彼此独立的源信号混合过程及各源信号本身均未知的情况下，从混合信号中分离出这些源信号的方法。BSS可以用来从多个麦克风混合语音信号中提炼出单个语音信号。本文简要阐述LMS、RLS算法，并通过仿真实验来分析比较这两类方法的性能，并利用此方法对一实际的语音信号进行分离。-Blind Signal Separation (BSS) is defined as independent of each other mixed-signal process and the source of the signal itself are unknown circumstances, from the mixed-signal to isolate the source of these signals. BSS can be used from multiple microphones mixed voice signal to extract a single speech signal. This paper briefly described LMS, RLS algorithm, and through simulation experiments to analyze the comparative performance of these two types of methods and take advantage of this method on a real speech signal separation.