基于离散小波变换的自适应语音消噪方法

A New Method for Adaptive Speech Noise Canceling Based on Wavelet Transform

针对语音信号的宽带特性 ,基于离散小波变换提出一种自适应消噪方案 (DW TANC) ,该方案利用多分辨率分析理论 ,把信号和噪声分解于不同的频率范围中 ,使信号和噪声的频谱得到简化 ,从而减少了自适应滤波器的级数L ,使输入自相关矩阵阶数降低 ,从而改善了它的自适应时间和输出精度 ,增强了其抗干扰能力。

For denoising the wide band speech signal,this paper presents a new adaptive noise canceling method based on discrete wavelet transform(DWTANC) This method analyzes the signal and noise into different frequency range with multiresolution analysis(MRA),and makes the signal and noise simple in frequency range,so the adaptive filter's orders would be shorted,and its self correlative matrix's orders will also be shorted So it improves the performance of adaptive noise canceling system,shorts the adaptive time and enhances the signal noise ratio(SNR),at last,the computer simulation test validates the conclusion above