The research of voiceprint recognition based on genetic optimized RBF neural networks

This paper proposed an algorithm of voiceprint recognition based on the genetic optimized RBF neural network. The algorithm optimizes the center and the width of the RBF neural network by genetic algorithm and extracts Mel cepstrum coefficients that stand for personality of the speaker combining with psychoacoustic model. Experimental results show that this method can obtain better model parameters and better results than the traditional RBF neural network.