Neural network based audio signal denoising

Abstract

In this paper, a novel filter is proposed by applying back propagation neural network (BPNN) ensemble where the noisy signal and the reference one are the same in a learning process. This neural network (NN) ensemble filter not only well reduces additive and multiplicative white noise inside signals, but also preserves signals' characteristics. It is proved that the reduction of noise using NN ensemble filter is better than the improved e nonlinear filter and single NN filter while signal to noise ratio is low. The performance of the NN ensemble filter is demonstrated in the audio signals processing.