On the basis of traditional BSS (Blind Source Separation) algorithm, a BSS algorithm based on the improved genetic algorithm is proposed in this paper. The improved genetic algorithm can effectively restrain the optimization into a local minimum, prevent the vibrating, speed up the convergence rate of the weights, and is suitable for nonlinear aliasing situation.The experimental results show that the BSS algorithm combined with the genetic algorithm can get a good separation effect for processing of multiple overlapping speech signals.%在传统盲源分离算法的基础上，提出了一种基于改进遗传算法的盲源分离算法。改进遗传算法可有效地抑制寻优陷入局部最小，防止了震荡，加快了权值的收敛速度，适用于非线性混叠情况。实验结果表明，将遗传算法和盲源分离相结合对于多路混叠语音信号具有较好的分离效果。
展开▼
