一种基于RBF神经网络的语音去噪方法

A method of speech denoising based on RBF neural networks

对语音去噪方法进行研究,采用RBF(radial basis function)神经网络在频域上对有噪语音信号进行去噪处理。比较了RBF神经网络对语音信号在时域和频域处理的不同效果,并用MATLAB进行了仿真。仿真结果表明,所采用的RBF神经网络算法在频域上对有噪语音信号进行去噪处理,效果优于时域处理结果,而且对背景噪声具有良好的抑制效果。

A method of speech denoising has been presented. The noisy mixed speech signal has been processed by using the RBF （radial basis function） neural network in the frequency domain. Simulation experiments have been carried out to compare different processing results using RBF neural networks in both time domain and frequency domain. Experimental results show that the pro- posed processing algorithm based on neural networks for the noisy mixed speech signal in the frequency domain outperforms the denoisin~ method in time domain and can restrain effectively the backuround noise.