自适应神经网络模糊小波语音消噪算法

针对有色噪声,采用自适应神经网络模糊系统模糊(Auto Neural Fuzzy Inference System,ANFIS)逼近有色噪声,利用自适应神经模糊推理系统ANFIS对噪声的非线性动态特性进行建模,提出了语音自适应神经网络模糊小波消噪算法,建立并训练了消噪系统。对被有色噪声污染的测量信号经模糊消噪后,根据信号和噪声的小波系数在不同分解尺度上的传递性,进行中值滤波和小波重构,得到了干净的语音。对算法进行了仿真实验,结果表明,消噪效果明显。

Algorithm for ANFIS and wavelet denoising of speech signal

An ANFIS and wavelet denoising algorithm is proposed for additive colored noise. Modeling the nonlinear dynamic characteristic of noise by ANFIS and fuzzy approximating colored noise, the Auto Neural Fuzzy Inference System （ANFIS） and wavelet denoising system of speech signal is set up and trained. According to the different wavelet coefficients＇ transmission properties of edge signals and noises under the different scales of the wavelet transform, the median filter is designed. Colored noise can be successfully removed by using subtraction in the original speech signal. Experimental results show that the algorithm is effective.