Self-organized Neural Network Inspired by the Immune Algorithm for the Prediction of Speech Signals

摘要

This paper presents the use of self-organized neural network inspired by the immune algorithm for the prediction of speech signal. Two speech signals are utilized, woman and man voices counting from one to ten in Arabic. The simulation results were compared with the multilayer perceptrons neural network. A new training algorithm was used with the self-organised multilayer perceptrons neural network that is inspired by the immune using weight decay. The simulation results indicated slight improvement of the use of regularisation technique for the multilayer perceptrons and no improvement when using the self-organized neural network inspired by the immune algorithm for the two speech signals.