From Analog to Digital: Multi-Order Digital Joint Coding-Modulation for Semantic Communication

TL;DR

This paper introduces a multi-order digital joint coding-modulation scheme for semantic communication, enabling compatibility with digital systems while maintaining high performance through innovative training strategies and hierarchical information extraction.

Contribution

The paper proposes a novel multi-order digital joint coding-modulation scheme integrated into NTSCC, with a substitution training strategy for non-differentiable modules and a hierarchical dimension-reduction approach.

Findings

Outperforms existing digital and non-digital JSCC methods.

Demonstrates effective approximation of modulation/demodulation processes.

Achieves superior semantic communication performance in experiments.

Abstract

Recent studies in joint source-channel coding (JSCC) have fostered a fresh paradigm in end-to-end semantic communication. Despite notable performance achievements, present initiatives in building semantic communication systems primarily hinge on the transmission of continuous channel symbols, thus presenting challenges in compatibility with established digital systems. In this paper, we introduce a novel approach to address this challenge by developing a multi-order digital joint coding-modulation (MDJCM) scheme for semantic communications. Initially, we construct a digital semantic communication system by integrating a multi-order modulation/demodulation module into a nonlinear transform source-channel coding (NTSCC) framework. Recognizing the non-differentiable nature of modulation/demodulation, we propose a novel substitution training strategy. Herein, we treat modulation/demodulation as a constrained quantization process and introduce scaling operations alongside manually crafted noise to approximate this process. As a result, employing this approximation in training semantic communication systems can be deployed in practical modulation/demodulation scenarios with superior performance. Additionally, we demonstrate the equivalence by analyzing the involved probability distribution. Moreover, to further upgrade the performance, we develop a hierarchical dimension-reduction strategy to provide a gradual information extraction process. Extensive experimental evaluations demonstrate the superiority of our proposed method over existing digital and non-digital JSCC techniques.