Lightweight Deep Joint Source-Channel Coding for Gauss-Markov Sources over AWGN channel

In this paper, we study the design of neural network based joint source-channel coding (JSCC) for point-to-point communication of Gauss-Markov sources over the additive white Gaussian noise (AWGN) channel with bandwidth compression. Among the existing deep learning (DL) -based JSCC methods for such sources, the long short-term memory (LSTM) based structure has good performance. However, it takes up huge time and space consumption because of its complex structure. In this work, we propose to adopt the causal convolution and dilated convolution to form our encoder and decoder due to their abilities of effectively extracting the temporal information of sources and their superiority in terms of reducing the time and space consumption. Experimental results show that the proposed model outperforms the traditional JSCC schemes and is comparable to the LSTM-based model in terms of source reconstruction quality. Besides, the proposed model shows a great robustness in the case of channel quality mismatch and correlation coefficient mismatch. Furthermore, our model takes lower time in the test phase and much lower space consumption compared to LSTM-based model.