In this paper, non-linear predictors based on different artificial neural network (ANN) are compared. General radical basis function (GERBF) neural network, a modified RBF network, is introduced. From the comparison with BP, RNN and RBF, it is obvious that GERBF has priority in the prediction of speech signal. The experiment results show: the speech coding systems based on ANN have better synthesized speech than ITU's G721 and the speech coding system based on GERBF has higher mean segmental SNR but less computation than that of other systems.