Semantic communications have shown great potential to boost the end-to-end transmission performance. To further improve the system efficiency, in this paper, we propose a class of novel semantic coded transmission (SCT) schemes over multiple-input multiple-output (MIMO) fading channels. In particular, we propose a high-efficiency SCT system supporting concurrent transmission of multiple streams, which can maximize the multiplexing gain of end-to-end semantic communication system. By jointly considering the entropy distribution on the source semantic features and the wireless MIMO channel states, we design a spatial multiplexing mechanism to realize adaptive coding rate allocation and stream mapping. As a result, source content and channel environment will be seamlessly coupled, which maximizes the coding gain of SCT system. Moreover, our SCT system is versatile: a single model can support various transmission rates. The whole model is optimized under the constraint of transmission rate-distortion (RD) tradeoff. Experimental results verify that our scheme substantially increases the throughput of semantic communication system. It also outperforms traditional MIMO communication systems under realistic fading channels.

翻译：语义通信展示出提高端到端传输性能的巨大潜力。为了进一步提高系统效率,我们在本文中提议了一组针对多输入多输出多输出(MIMO)淡化渠道的新型语义编码传输(SCT)计划。特别是,我们提议了一个高效的SCT系统,支持同时传输多流,这可以最大限度地增加端到端的语义通信系统的多重增益。通过共同考虑源语义特征和无线MIMO频道状态的酶分布,我们设计了一个空间多轴机制,以实现适应性编码速率分配和流式绘图。结果,源的内容和频道环境将天衣无缝地结合,从而最大限度地增加SCT系统的编码收益。此外,我们的SCT系统是多功能的:一个单一模型可以支持各种传输率。整个模型在传输速率-扭曲(RD)交易的制约下得到优化。实验结果证实我们的计划大大提高了语义通信系统的吞吐量。它还超越了现实化通道下传统的MIMO通信系统。