The traditional training methods of Gaussian Mixture Model (GMM) are sensitive to the initial model parameters

and they often lead to a sub-optimal model in practice.To resolve this problem

it proposed a new GMM optimization method.It utilized the niche techniques and Maximum Likelihood(ML) algorithm in the Genetic Algorithms(GA) training step and provided a new architecture of hybrid algorithm.The new hybrid algorithm can reduce the possibility of premature convergence presence and improve the exploitation capabilities of GA.It also used an adaptive updating strategy to control the GA mixture crossover rate and mutation rate.Besides

the other speakers’ discriminative information was integrated into fitness function to increase the accuracy of classification and make GMM more generalization ability.The experimental results show that this method can obtain more optimum GMM parameters and better results than the traditional and the two improved versions for speaker recognition.