In this paper, a high-quality wideband speech coder is proposed. The coding structure resembles a LD-CELP coder, however, several novel improvements are made. The gain adapter for the stochastic codebook is driven by a neural network and it updates the excitation gain in a sample-by-sample fashion. The purpose of incorporating a neural network is to exploit both the intra- and inter-frame correlation of speech signal in a non-linear manner. A psychoacoustic model instead of a simple perceptual weighting filter is used to shape the quantization noise. Simulation result shows that the proposed coder can achieve transparent coding of wideband speech at 16 kbps.