<![CDATA[The proposed Compressive sensing method is a new alternative method, it is used to eliminate noise from the input signal, and the quality of the speech signal is enhanced with fewer samples, thus it is required for the reconstruction than needed in some of the methods like Nyquist sampling theorem. The basic idea is that the speech signals are sparse in nature, and most of the noise signals are non-sparse in nature, and Compressive Sensing(CS) eliminates the non-sparse components and it reconstructs only the sparse components of the input signal. Experimental results prove that the average segmental SNR (signal to noise ratio) and PESQ (perceptual evaluation of speech quality) scores are better in the compressed domain．]]>
Copyrights © 2017
