Non-Orthogonal Multiple Access Enhanced Multi-User Semantic Communication

Semantic communication has served as a novel paradigm and attracted a broad interest from researchers. One critical aspect of it is the multi-user semantic communication theory, which can further enhance its application for the practical network environment. While most existing works have focused on the design of end-to-end single-user semantic transmission, a novel non-orthogonal multiple access (NOMA)-based multi-user semantic communication system named NOMASC is proposed in this study. The proposed system can support semantic transmission of multiple users with diverse modalities of source information. To avoid high demand for the hardware, an asymmetric quantizer is employed at the end of the semantic encoder for discretizing the continuous full-resolution semantic feature. In addition, a neural network model is used for mapping the discrete feature into self-learned symbols and accomplishing intelligent multi-user detection (MUD) at the receiver side. Simulation results demonstrate that the proposed system attains sound performance in non-orthogonal transmission of multiple user signals and outperforms the other methods, particularly with low-to-medium signal-to-noise ratios (SNRs). Moreover, it has shown high robustness under various simulation settings and mismatched testing scenarios.