基于四阶累积量和简化粒子群的盲分离算法

摘要

For problems of Instantaneous mixed blind signal separation, a new blind source separation algorithm based on fourth-order cumulant and simple particle swarm optimization was proposed. Fourth-order cumulant was used as objective function, then the simple particle swarm optimization was uesd to optimize it. Simulation results show that the algorithm can achieve the efficient blind source separation separation for conference speech blind signal separation. Compared with other algorithms, the proposed algorithm has faster convergence speed and higher separation accuracy.%针对线性混合盲信号分离问题，本文提出一种基于四阶累积量和简化粒子群优化的盲信号分离新算法。该算法采用信号的四阶累积量作为目标函数，运用简化粒子群优化算法对目标函数进行优化，最终实现对混合信号的盲分离。仿真结果表明，该算法能够有效实现对会议语音混合信号的盲分离，跟其他算法相比，具有更快收敛速度和分离精度。