Abstract: When using traditional clustering algorithms based on RBF to recognize human speakers, it is hard to decide the number and locations of the cluster centers.To overcome these shortcomings, an RBF network based on artificial immune mechanism for human speaker recognition is proposed.The artificial immune mechanism can adaptively compute the number and initial locations of the centers in the hidden layer of the RBF network based on the audio sample data set.Experimental tests show that the system has a fast learning speed for network weights.The system is very good at searching for global optimum.It has a high recognition rate and is a new practical method for human speaker recognition.