This paper discusses a blind separation algorithm of non-stationary convolved sounds mixtures.

讨论一种非平稳卷积混合声音信号盲分离算法。

Stability and convergence of the model are proven by means of the weak convergence theorem of generalized function and the convolved integration theory.

由广义函数弱收敛定理和卷积理论，证明所提出的非局部连续模型具备收敛性和稳定性。

In feature extraction, the performance of the Laplacian of Guassian operators is improved by enhancing the resultant convolved image and calibrating with region-growing algorithm.

在特征提取阶段，我们提出通过对卷积图进行增强和用区域增长方法进行辅助校正的方法来改善轮廓提取的效果。

Simulations show that the algorithm can get high separation performance for both non-stationary temporary and convolved mixing signals.

仿真结果表明算法分离精度高，分离过程平稳，在任意混合情况下均能获得良好的分离性能。

Usually an inverse filter is designed and convolved with the signal, the objective being to nullify an objectionable effect of an earlier filter action.

通常是设计一个逆滤波器，然后与信号进行褶积，目的是使以前的滤波器对信号的影响变为零。