Vowel Phoneme Classification Using SMO Algorithm for Training Support Vector Machines

Support vector machines (SVM) is a powerful new generation learning algorithm based on recent advances in statistical learning theory. Based on the principle of Structure Risk Minimization, Support Vector Machines have advantage than other classifier. SVM deliver state-of-the-art performance in real-word applications such as text categorization, hand-written character recognition, image classification, biosequence analysis, etc. In this paper, we describe the use of the sequential minimal optimization (SMO) algorithm to classify vowel phoneme of the TIMIT corpus. To evaluate this classifier, we compare SVM result with neural network classifier of Gas, Zarader, Chavy and Chetouani.