Speech Recognition using Wavelets and Improved SVM

Abstract

Speaker recognition (identification/verification) is the computing task of validating a user’s claimed identity using speaker specific information included in speech waves: that is, it enables access control of various services by voice. Discrete Wavelet Transform (DWT) based systems for speaker recognition have shown robust results for several years and are widely used in speaker recognition applications. This paper is based on text independent speaker recognition system that makes use of Discrete Wavelet Transform (DWT) as a feature extraction and kernel Support Vector Machine (SVM) approach as a classification tool for taking the decision through applying simplified-Class Support Vector Machine approach. The proposed SVM approach can convert local Euclidean distances between frame vectors to angles by projecting these d-dimensional vectors together, and get the minimum global distance from the non-linear aligned speech path in order to address audio classification, and hence, sound recognition.The DWT for each frame of the spoken word are taken as a tool for extracting the main feature as a data code vectors, next these data is normalized utilizing the normalized power algorithm that is used to reduce the number of feature vector coefficients then these data is scaled and tested with those stored of the training spoken words to achieve the speaker identification tasks, also the DWT gives fixed amount of data that can be utilized modesty by SVM. Finally, the proposed method is tested and trained upon a very large data base with results limited to ten speakers only (5 males and 5 females) with words of maximally 17 phenomena and its performance gives an accurate and stable results which rises the algorithm efficiency and reduce the execution time with 97% overall accuracy.