实验结果表明该算法对非冲击噪声效果良好。

lx_main为主程序，NS_lxwz为噪声估计模块，lxG_wz为增益估计模块，noise_sound为测试用含噪语音。

算法原理参见本人的文章《一种引入延迟的语音增强算法》。-Experimental results show that the algorithm for non-impulsive noise effect is good. lx_main the main program, NS_lxwz for the noise estimation module, lxG_wz for the gain estimation module, noise_sound to test the noisy speech. Algorithm theory see my article " delay the introduction of a speech enhancement algorithm."