Speech Denoising Based On Wavelet Transform

Speech signal is the most convenient and shortcut way of intercommunion. However,in the course of the intercommunion,speech signal is disturbed and polluted inevitably by surroundings and transmission mediums. As a result,we are unable to catch on the meanings of speech signal. In the past,we used to analyze speech signal and filter the noise by short-time Fourier transform in the frequent domain. However,this method is not effective to the white noise. Wavelet transform is a very popular method in the processing of digital signal nowadays. This thesis deals with the quality and the realization of arithmetic as well as the application in speech signal denoising mainly and put forward three methods of speech signal denoising based on wavelet transform .The results of experiments show that we can get satisfying effects by these methods.