A NEW APPROACH OF SPEECH COMPRESSION BY USING DWT & DCT RATISH KUMAR 1 & HEMANT AMHIA 2 1 Department of Electrical Engineering, Jabalpur Engineering College, Jabalpur, Madhya Pradesh, India 2 Professor, Jabalpur Engineering College, Jabalpur, Madhya Pradesh, India ABSTRACT With the growth of multimedia technology over past decades, the demand for digital information increase dramatically. The enormous demand poses difficulties in handling speech compression. Speech compression is a mature technology with many applications. To overcome this problem is to compress the information by removing redundancies present in it. Lossy compression scheme that is often used to compress information such as speech signals. This paper presents a method of transformation for the compression of speech signal. In this paper a new lossy algorithm to compress speech signal using discrete wavelet transform (DWT) and then again compressed by discrete cosine transform (DCT) then decompressed it by discrete cosine transform afterward decompressed by discrete wavelet transform to retrieve the original signal in compressed form. To measure the performance of speech signal on the basis of signal to noise ratio (SNR) and mean square error (MSE) by using different filter of wavelet families. KEYWORDS: DWT, DCT, Speech Compression & Decompression, PSNR, MSE INTRODUCTION Speech is a very basic way for humans to convey information to one another. With a bandwidth of 400Hz to 4kHz, speech can carry information with different colour of emotion of a human voice. Now a day’s people are able to hear someone’s voice from anywhere in the world-as if the person would be in the same location and they are talking in face to face. Speech can be defined such as the response of the vocal tract to one or more excitation signals. Compression of signals is based on removing the redundancy between neighbouring samples and/or between the adjacent cycles. In data compression, it is desired to represent data by as small as possible number of coefficient within an acceptable loss of visual quality. Compression techniques can be classified into one of two main categories: lossy and lossless. Compression methods can be classified into three functional categories: Direct Methods: The samples of the signal are directly handled to provide compression. In transformation method the signal is transformed into frequency domain. In transform method we use Discrete wavelet transform and Discrete cosine transform. Transformation techniques don’t compress the signal, they provide information they provide information about the signal and using various encoding technique compression of signal. BEST: International Journal of Management, Information Technology and Engineering (BEST: IJMITE) ISSN 2348-0513 Vol. 2, Issue 8, Aug 2014, 9-14 © BEST Journals