Speaker Classification Using Support Vector Machine and Wavelets

In this paper, a novel speaker classification method is presented. This method makes use of wavelets and support vector machines (SVMs) to classify speech data. When a speech data is given, wavelets are first applied to extract acoustical features such as subband power and pitch information. Then the proposed method uses a SVM over these acoustical features and additional parameters, such as frequency cepstral coefficients, to accomplish multi-speaker classification. A public audio database, Aurora, is used to evaluate the performances of the proposed method against other similar schemes. Experimental results show that the segmentation of a given speech can exactly segment sentences of one male and female speaker. And the segmental accuracy in multi-speaker conditions can achieve 90.32% and 83.43% for 2 males 2 females and 4 males 4 females speaking, respectively