Wavelet transform for speech compression and denoising

Abstract

We are interested in this paper in speech compression using Discrete Cosine Transformation DCT and the discrete wavelet transform WT, then speech denoising using packet wavelet is discussed. The efficiency of the packet wavelets is presented to reduce the effect of noise in an acoustic signal. Several audio compression standards exist; these standards are established to develop tools to compress an audio signal while respecting the standards. Peak Signal to Noise Ratio (PSNR) and mean square error are used to evaluate the quality of the acoustic compression. Good results are obtained with Wavelet transform compared to DCT.