摘要
With advancements in Beyond 5G (B5G) and 6G, semantic communication is emerging as a promising technique for supporting diverse multimodal AIoT tasks. However, previous research has not fully addressed the practical challenges when jointly considering transmission efficiency and system robustness. In this paper, we design a Multimodal Data Fusion Semantic Communication (MDF-SC) system with a cross-attention strategy to integrate multiple modalities at the transmitter. We ensure robust noise resilience across low and high SNR regimes by extracting critical features under symbol constraints. This fusion-aware approach eliminates the need for modality-specific encoders and decoders, significantly reducing parameter count and computational complexity as a unified semantic communication system. Experiment results demonstrate that our MDF-SC system outperforms existing state-of-the-art (SOTA) transformer-based approaches, achieving superior performance with 26.7% fewer transmitted semantic symbols using Rayleigh fading channel, 22% fewer model parameters, and 37.5% computational load reduction while maintaining robust performance across varying SNR regimes. © 2025 IEEE.