In this paper, we propose two deep joint source and channel coding (DJSCC) structures with attention modules for the multi-input multi-output (MIMO) channel, including a serial structure and a parallel structure. With singular value decomposition (SVD)-based precoding scheme, the MIMO channel can be decomposed into various sub-channels, and the feature outputs will experience sub-channels with different channel qualities. In the serial structure, one single network is used at both the transmitter and the receiver to jointly process data streams of all MIMO subchannels, while data steams of different MIMO subchannels are processed independently via multiple sub-networks in the parallel structure. The attention modules in both serial and parallel architectures enable the system to adapt to varying channel qualities and adjust the quantity of information outputs in accordance with the channel qualities. Experimental results demonstrate the proposed DJSCC structures have improved image transmission performance, and reveal the phenomenon via non-parameter entropy estimation that the learned DJSCC transceivers tend to transmit more information over better sub-channels.

翻译：本文针对多输入多输出（MIMO）信道，提出了两种集成注意力模块的深度联合信源信道编码（DJSCC）结构，包括串行结构与并行结构。通过基于奇异值分解（SVD）的预编码方案，MIMO信道可分解为多个子信道，特征输出将经历具有不同信道质量的子信道。在串行结构中，发射端与接收端分别采用单一网络联合处理所有MIMO子信道的数据流；而在并行结构中，不同MIMO子信道的数据流通过多个子网络独立处理。两种架构中的注意力模块使系统能够自适应信道质量变化，并根据信道质量调整信息输出量。实验结果表明，所提出的DJSCC结构在图像传输性能上表现更优，并通过非参数熵估计揭示了一个现象：经过学习的DJSCC收发器倾向于在质量更好的子信道上传输更多信息。