The LD-CELP Gain Filter Based on BP Neural Network.

The recommendation G.728 depends on the Levinson-Durbin (L-D) algorithm to update its gain filter coefficients. In this paper, it is contrasted with BP neural network method. Because quantizer has not existed at optimizing gain filter, the quantization SNR can not be used to evaluate its performance. This paper proposes a scheme to estimate SNR so that gain predictor can be separately optimized with quantizer. Using BP neural network filter, the calculation quantity is only 6.7 percent of L-D method's and its average segment SNR is about 0.156dB higher than G.728. It is also used to evaluate the case that excitation vector is 16 or 20 samples, respectively, the BP neural network algorithm has similarly good result. [ABSTRACT FROM AUTHOR]