Search

This paper discusses a suggested approach for new kind of Speech Signal Compression Algorithm based on KL transform (Karhunen-Loève transform) which normally used with digital image. Speech signal (which is single sequence) rearranged in form of two dimension square matrix to be suitable for KL transformation. Then to be compressed using different no. of eigen values and eigenvectors. Measuring the performance of applied KL transformation (by evaluating the PSNR and SNR factors) with different numbers of eigen values and vectors studied. High rate of compression with high SNR, PSNR got with so closed speech signal to the original one measured using correlation factor which gives values near to 1. In addition to short time needed for compression operation.

Voice compression is one of the important subject today specially in field of communication and application so in this paper, speech compression was adopted based on hybrid technique between wavelet and Huffman code. Wavelet in single dimension can reduce the signal size to half of the original in each level, then using Huffman code to store output the file. Hybrid between the above two techniques give high rate of compression ratio, and closed returned signal from the original one, because of the coding technique from the lossless classification but the idea of sample down was achieved with the wavelet which produce little loss in the retrieved data, while the effected of the wavelet is positive effect due to the reduction of the high frequencies, which effect as noise in most application[specially in speech],in addition to that it give high redundancy in the component of the speech signal [in low-low components]. The practical application of the proposed algorithm give (30%) compression ratio plus stability when the file size growth up. SNR&MSE show that retrieved speech quality is good.