International Journal of Emerging Engineering Research and Technology Volume 2, Issue 2, May 2014, PP 91-95 ©IJEERT www.ijeert.org 91 Implementation of Speech Compression Using Linear Predictive Coding (LPC) with Tms320c6713dsk and Comparison with Other Platforms Uday Mithapelli , Suraj P. Patil Dept. of E & Tc, KJEI’s Trinity College of Engineering & Research, Pune, India Abstract: In recent multimedia system, people consider speed, power, and size very important. People want the process to have very high performance and high quality, while consume only small amount of power. Beside the development on better algorithm, special hardware design techniques can also help in increasing performance. This project mainly focuses on the linear predictive coding algorithm on speech. The algorithm is analyzed and implemented on DSP processor TMS320C6713 . The implementation is done using Code Composer Studio(CCS) for which we also have a chance to evaluate the effectiveness of the software in implementing the encoder from a hardware level perspective. This LPC coding is having wide application in wireless communication and also used for accurate estimation of Speech Properties. Keywords: Linear Predictive Coding(LPC), DSP processor TMS320C6713,Code Composer Studio(CCS 3.1),Segmental Signal To Noise Ratio (SEGSNR) and Power Signal To Noise Ratio (PSNR )MATLAB platform. 1. INTRODUCTION Linear Predictive Coding (LPC) is one of the methods of compression that models the process of speech production. Specifically, LPC models this process as a linear sum of earlier samples using a digital filter inputting an excitement signal. An alternate explanation is that linear prediction filters attempt to predict future values of the input signal based on past signals. LPC “...models speech as an autoregressive process, and sends the parameters of the process as opposed to sending the speech itself” . It was first proposed as a method for encoding human speech by the United States Department of Defense in federal standard 1015, published in 1984. Another name for federal standard 1015 is LPC-10 which is the method of Linear predictive coding that will be described in this paper.[1] Speech coding or compression is usually conducted with the use of voice coders or vocoders. There are two types of voice coders: waveform-following coders and model-base coders. Waveform following coders will exactly reproduce the original speech signal if no quantization errors occur. Model-based coders will never exactly reproduce the original speech signal, regardless of the presence of quantization errors, because they use a parametric model of speech production which involves encoding and transmitting the parameters not the signal. LPC vocoders are considered model-based coders which means that LPC coding is lossy even if no quantization errors occur. Speech coder that is developed analyzed using both subjective and objective analysis. Subjective analysis will consist of listening to the encoded speech signal and making a judgment on its quality. The quality of played back signal will solely depends on opinion of listener. Objective analysis will be introduce to technical access the speech quality and to minimize human bias.[4] The Objective Analysis will be performed by computing between the original and coded speech signal . Also speed of operating platform in terms of second is also analyzed. 2. KEY FEATURES AND BASIC OPERATION OF 6713 PROCESSOR This project is implemented on TMS3206713 DSK kit. A Texas Instruments TMS 320C6713 DSP operates at 225 MHz It has 16 Mbytes of synchronous DRAM and512 Kbytes of non-volatile flash memory (256 Kbytes usable in default configuration). Digital signal Processing is one of the most powerful technologies that will shape science and engineering in the twenty first century.