等变自适应盲信号分离方法的研究

Study on Equivalent Adaptive Blind Source Separation

盲信号处理(BSP)是近年来现代信号处理领域研究的主要方向之一，而盲信号分离(BSS)则又是盲信号处理中最重要的一部分。本文首先给出了盲信号分离中传统的瞬时混合模型、时延混合模型和卷积混合模型，其次介绍了一种等变自适应盲分离算法，最后给出了相应的仿真和结论。

Blind Signal Processing (BSP) is one of the main aspects which has been studied in the field of modern signal processing in recent years, and Blind Source Separation (BSS) is the most important part of BSP. First, this paper shows the hackneyed instantaneous mixture model, time-delay mixture model and convolutive mixture model in BSS. Then it discusses two BSS algorithms, Equivalent Adaptive Separation via Independence and Fast Fixed-Point Algorithm based on maximization of non-gaussianity. At last, it presents the corresponding experiments and conclusion.