Speech recognition using Support Vector Machines

In this article we applied Support Vector Machines to acoustic model of Speech Recognition System based on MFCC and LPC features for Azerbaijani DataSet. This DataSet has been used for speech recognition by Multilayer Artificial Neural Network and achieved some results. The main goal of this work is applying SVM techniques to the Azerbaijan Speech Recognition System. The variety of results of SVM with different Kernel functions is analyzed in the training process. It is shown that SVM with radial basis and polynomial kernels give better recognition results that Multilayer Artificial Neural Network.