改进的减谱法在语音增强中的应用

Application of Improved Spectral Subtraction Method to Speech Enhancement

为消除语音信号中噪声,改善语音质量,本文提出一种改进的减谱法。首先根据每帧的功率谱动态调整谱减系数,然后通过维纳滤波法把各种噪声变换为类似白噪声的噪声,最后用原减谱法把该噪声去除。实验证明,该方法有较好的去噪效果。

In order to remove noise from a speech and improve the speech quality,this paper presents an improved spectral subtraction method.The method first dynamically adjusts spectral subtraction coefficient according to the power spectrum of each speech frame,then transforms all kinds of noises to the noises similar to white noise by Weiner filter,and finally removes the noises by the traditional spectral subtraction method.Experimental results demonstrate that the proposed method is much effective on removing noise.