GMM Optimization Using Neural Networks for Persian Language Detection

In this paper Persian language verification system is proposed and evaluated. This technique is constructed by using Gaussian mixture models as a basic system for tokenizing and a Neural Network as the backend processor. Performances result are presented for a used system of GMM Tokenizer in combining with Neural Network and finally the results of GMM-NN system compared with GMM-Tokenizer system. It will be shown that using the Neural Network as the backend processor will improve the results significantly.