Presenting a New Text-Independent Speaker Verification System Based on Multi Model GMM

Speaker verification is the process of accepting or rejecting claimed identity interms of its sound features. A speaker verification system can be used for numeroussecurity systems, including bank account accessing, getting to security points,criminology and etc. When a speaker verification system wants to check the identityof individuals remotely, it confronts problems such as noise effect on speech signaland also identity falsification with speech synthesis. In this system, we haveproposed a new speaker verification system based on Multi Model GMM, called SVMMGMM,in which all speakers are divided into seven different age groups, andthen an isolated GMM model for each group is created; instead of one model for allspeakers. In order to evaluate, the proposed method has been compared with severalspeaker verification systems based on Naïve, SVM, Random Forest, Ensemble andbasic GMM. Experimental results show that the proposed method has so betterefficiency than others.

Presenting a New Text-Independent Speaker Verification System Based on Multi Model GMM Keywords:

biometric attributes , speaker verification , Gaussian Mixture Model (GMM) , Support Vector Machine (SVM) , Decision Trees (DT) , Ensemble Classifiers