一种新的瞬时混迭信号盲分离的自适应方法

An Adaptive Algorithm for Blind Separation of Instantaneous Mixing Signals

本文利用源信号的统计独立特性，推导出一种瞬时混迭信号分离的自适应方法。这种方法将预白化和正交化合二为一，仅利用观测数据迭代更新分离阵参数。计算机仿真实验结果表明，该方法是有效的，可以较精确分离线性混迭的信号。

Using statistics independent feature of source signals, this paper proposed a self-adaptive algorithm for separation of instantaneous mixing signals. The proposed algorithm combines pre- whiten and orthogonization, and uses only observation data. The computer simulations show that the proposed algorithm can well restore source signals from their mixtures.