An algorithm of voice activity detection based on noise estimation

In the condition of low signal to noise ratio(SNR) and complex noise model,the performance of the voice activity detection(VAD) algorithms always becomes poor.This paper presents a new VAD algorithm based on noise estimation.Through the adaptive noise estimation,the accurate SNR threshold is decided.Then,after applying whitening filter to short time spectra the spectral entropy can be used to VAD algorithm in complex noise model.The experimental results show that the proposed algorithm gets better performance than G.729B and AMR VAD algorithms in the condition of low SNR and complex noise model.