期刊名称：International Journal of Electronics, Communication and Soft Computing Science and Engineering
印刷版ISSN：2277-9477
出版年度：2015
卷号：4
期号：Special 1
出版社：IJECSCSE
摘要：With technological advancement telephonic and electronic transactions have increased manifold. Digit recognition plays an important role in such commu nication. It is also useful in security applications. This paper proposes to implement and compare some popular algorithms used for is olated digit recognition. Two feature extraction techniques namely linear predictive cepstral coefficients (LPCC) and mel frequency cepstral coefficients (MFCC) are implemented for a speaker dependent recognition system. The results obtained for these algorithms are perused and conclusions are drawn
关键词：Digit Recognition; Linear Predictive Cepstral Coefficients; Frequency Cepstral Coefficients; Euclidean distance
