Novel Approach in Speaker Identification using SVM and GMM

Conventional speaker Identification systems use Gaussian mixture models (GMM) and support vector machines (SVM) to model a speaker's voice based on the speaker's acoustic characteristics. Whereas GMNI needs more data to perform adequately and is computationally inexpensive, SVM on the other hand can do well with less data and is computationally expensive. This paper proposes a novel approach that combines the power of generative Gaussian mixture models (GMM) and discriminative support vector machines (SVM). Due to its excellent expandability, GMM have been used to extract a small quantity of typical feature vectors from large numbers of speech data for SVM classifier. A hybrid system is described and experimentally evaluated on a text-independent speaker identification task. The results prove that the combination is beneficial in terms of performance and practical in terms of computation.