International Journal of Electronics Engineering Research. ISSN 0975-6450 Volume 9, Number 3 (2017) pp. 377-390 © Research India Publications http://www.ripublication.com A comparative Performance Analysis of LPC and MFCC for Noise Estimation in Speech Recognition Task Syed Sibtain Khalid 1 Asst. professor, Department of Computer Science & Engineering, Jamia Hamdard, New Delhi-62 Safdar Tanweer 2 Asst. professor, Department of Computer Science & Engineering, Jamia Hamdard, New Delhi-62 Dr. Abdul Mobin 3 Adjunct Professor, Department Of Computer Science & Engineering, Jamia Hamdard, New Delhi-62 Dr. Afshar Alam 4 Department Of Computer Science & Engineering, Jamia Hamdard, New Delhi-62 Abstract From the days of adam and eve Speech plays an important means in communication system, its recognition is truly a challenging task. Generally noise is an unwanted interface in any form of communication system. This paper deals with the estimation of noise that are present at the front end of original speech Signal, for estimation of noise we have calculated the coefficient of LPC (Linear Predictive Coding) and MFCC (Mel Frequency Cepstral Coefficient). To minimize the complexity of processing only three classes of noise are considered, ten samples from each classes are taken for computational work. Accurate deviation results are pin pointed for similar kind of noises in both LPC and MFCC. Finally percentage deviation is calculated. Resultant vector shows MFCC outperform LPC in terms of percentage deviation for estimation of noise that will be the key thrust of this paper. MATLAB 7.11 is used to carry out all the experimental work. Keyword: Noise samples, LPC, MFCC, Deviation