CLEAR: Channel Learning and Enhanced Adaptive Reconstruction for Semantic Communication in Complex Time-Varying Environments

TL;DR

CLEAR tackles robust semantic communication over complex, time-varying wireless channels by integrating DeepJSCC with an adaptive diffusion denoising model (ADDM) and leveraging real-time CSI for dynamic parameter updates. The method fuses end-to-end trainable encoding/decoding with diffusion-based denoising to mitigate multipath, fading, phase noise, and Doppler distortions, achieving higher semantic fidelity than prior DeepJSCC variants. Empirical results demonstrate significant PSNR gains (e.g., ~2.3 dB over DeepJSCC-V) and strong robustness across AWGN, Rayleigh, and high-m Doppler/phase-noise scenarios, validating the approach’s practicality for dynamic wireless environments. The work advances semantic communication by enabling joint, CSI-guided optimization of encoding, diffusion-based denoising, and decoding in a unified framework with potential applications in adaptive multimedia transmission and IoT networks.

Abstract

To address the challenges of robust data transmission over complex time-varying channels, this paper introduces channel learning and enhanced adaptive reconstruction (CLEAR) strategy for semantic communications. CLEAR integrates deep joint source-channel coding (DeepJSCC) with an adaptive diffusion denoising model (ADDM) to form a unique framework. It leverages a trainable encoder-decoder architecture to encode data into complex semantic codes, which are then transmitted and reconstructed while minimizing distortion, ensuring high semantic fidelity. By addressing multipath effects, frequency-selective fading, phase noise, and Doppler shifts, CLEAR achieves high semantic fidelity and reliable transmission across diverse signal-to-noise ratios (SNRs) and channel conditions. Extensive experiments demonstrate that CLEAR achieves a 2.3 dB gain on peak signal-to-noise ratio (PSNR) over the existing state-of-the-art method, DeepJSCC-V. Furthermore, the results verify that CLEAR is robust against varying channel conditions, particularly in scenarios characterized by high Doppler shifts and strong phase noise.

Figures (9)

• Figure 1: The architecture of CLEAR. The framework integrates DeepJSCC with ADDM, using real-time CSI for dynamic adaption. The encoder extracts semantic features, the channel introduce noise, and the ADDM mitigates distortion to ensure high-quality reconstruction by the decoder.
• Figure 2: The training loss in terms of epochs in the CLEAR system.
• Figure 3: PSNR performance on CIFAR10 and DIV2K datasets under various channel conditions and SNR values. $Ds$ stands for Doppler shifts, and $Pn$ represents phase noise.
• Figure 4: Effect of compression rate on PSNR performance in AWGN channels with varying SNR values.
• Figure 5: Effect of compression rate on PSNR performance in Rayleigh fading channel at varying SNR.