Joint Source-Channel Coding: Fundamentals and Recent Progress in Practical Designs

TL;DR

The paper analyzes JSCC as an end-to-end alternative to traditional SSCC, showing that finite-blocklength and uncertain-channel scenarios favor JSCC and that deep learning enables practical DeepJSCC designs transcending conventional digital bottlenecks. It covers information-theoretic foundations (including remote sources, feedback, side information, and multi-user settings) and surveys a spectrum of practical designs—from classical joint or hybrid coding to state-of-the-art DL-based schemes for images, video, text, and beyond. It also discusses extensions to non-standard distortion criteria and networked contexts (relays, broadcast channels, and multi-user cases), highlighting the graceful degradation and potential performance gains over SSCC. The authors argue for reconsidering strictly separated architectures to realize low-latency, high-fidelity communication for applications such as autonomous systems, AR/VR, and drone networks, while addressing challenges in architecture, standardization, and security. Overall, the work provides a unified view of theory and practice, showcasing how DL-based JSCC can dramatically impact next-generation communication systems.

Abstract

Semantic- and task-oriented communication has emerged as a promising approach to reducing the latency and bandwidth requirements of next-generation mobile networks by transmitting only the most relevant information needed to complete a specific task at the receiver. This is particularly advantageous for machine-oriented communication of high data rate content, such as images and videos, where the goal is rapid and accurate inference, rather than perfect signal reconstruction. While semantic- and task-oriented compression can be implemented in conventional communication systems, joint source-channel coding (JSCC) offers an alternative end-to-end approach by optimizing compression and channel coding together, or even directly mapping the source signal to the modulated waveform. Although all digital communication systems today rely on separation, thanks to its modularity, JSCC is known to achieve higher performance in finite blocklength scenarios, and to avoid cliff and the levelling-off effects in time-varying channel scenarios. This article provides an overview of the information theoretic foundations of JSCC, surveys practical JSCC designs over the decades, and discusses the reasons for their limited adoption in practical systems. We then examine the recent resurgence of JSCC, driven by the integration of deep learning techniques, particularly through DeepJSCC, highlighting its many surprising advantages in various scenarios. Finally, we discuss why it may be time to reconsider today's strictly separate architectures, and reintroduce JSCC to enable high-fidelity, low-latency communications in critical applications such as autonomous driving, drone surveillance, or wearable systems.

Figures (18)

• Figure 1: Schematic diagram of a general communication system according to Shannon (reproduced from Shannon).
• Figure 2: Illustration of a JSCC problem over a noisy communication channel.
• Figure 3: Separation-based architecture for the JSSC problem.
• Figure 4: Illustration of a JSCC problem with a remote source $S^m$ that has to be reconstructed at the decoder.
• Figure 5: JSCC problem in the presence of correlated side information at the receiver.