Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Semantics-Division Duplexing: A Novel Full-Duplex Paradigm

Kai Niu, Zijian Liang, Chao Dong, Jincheng Dai, Zhongwei Si, Ping Zhang

TL;DR

The paper tackles the reliability bottleneck of in-band full-duplex systems by introducing Semantics-Division Duplexing (SDD), which couples IBFD with AI-enabled semantic communication to suppress self-interference in the semantic domain. It proposes a four-stage processing architecture that integrates propagation/analog cancellations with digital and semantic domain processing, backed by end-to-end JSCC-based semantic models and a learned digital SIC framework. A Feasibility metric and Feasible Region are introduced to theoretically quantify SDD's potential advantages over conventional IBFD, supported by implementation demonstrations showing notable performance gains in semantic reconstruction. The work argues that SDD can approach the performance of an ideal IBFD system while enabling intelligent, concise communications suitable for future wireless deployments.

Abstract

In-band full-duplex (IBFD) is a theoretically effective solution to increase the overall throughput for the future wireless communications system by enabling transmission and reception over the same time-frequency resources. However, reliable source reconstruction remains a great challenge in the practical IBFD systems due to the non-ideal elimination of the self-interference and the inherent limitations of the separate source and channel coding methods. On the other hand, artificial intelligence-enabled semantic communication can provide a viable direction for the optimization of the IBFD system. This article introduces a novel IBFD paradigm with the guidance of semantic communication called semantics-division duplexing (SDD). It utilizes semantic domain processing to further suppress self-interference, distinguish the expected semantic information, and recover the desired sources. Further integration of the digital and semantic domain processing can be implemented so as to achieve intelligent and concise communications. We present the advantages of the SDD paradigm with theoretical explanations and provide some visualized results to verify its effectiveness.

Semantics-Division Duplexing: A Novel Full-Duplex Paradigm

TL;DR

The paper tackles the reliability bottleneck of in-band full-duplex systems by introducing Semantics-Division Duplexing (SDD), which couples IBFD with AI-enabled semantic communication to suppress self-interference in the semantic domain. It proposes a four-stage processing architecture that integrates propagation/analog cancellations with digital and semantic domain processing, backed by end-to-end JSCC-based semantic models and a learned digital SIC framework. A Feasibility metric and Feasible Region are introduced to theoretically quantify SDD's potential advantages over conventional IBFD, supported by implementation demonstrations showing notable performance gains in semantic reconstruction. The work argues that SDD can approach the performance of an ideal IBFD system while enabling intelligent, concise communications suitable for future wireless deployments.

Abstract

In-band full-duplex (IBFD) is a theoretically effective solution to increase the overall throughput for the future wireless communications system by enabling transmission and reception over the same time-frequency resources. However, reliable source reconstruction remains a great challenge in the practical IBFD systems due to the non-ideal elimination of the self-interference and the inherent limitations of the separate source and channel coding methods. On the other hand, artificial intelligence-enabled semantic communication can provide a viable direction for the optimization of the IBFD system. This article introduces a novel IBFD paradigm with the guidance of semantic communication called semantics-division duplexing (SDD). It utilizes semantic domain processing to further suppress self-interference, distinguish the expected semantic information, and recover the desired sources. Further integration of the digital and semantic domain processing can be implemented so as to achieve intelligent and concise communications. We present the advantages of the SDD paradigm with theoretical explanations and provide some visualized results to verify its effectiveness.
Paper Structure (10 sections, 5 figures)

This paper contains 10 sections, 5 figures.

Table of Contents

  1. Introduction
  2. Fundamental Principles
  3. Design architecture
  4. The Four-stage Processing Domain
  5. Semantic Communication Models
  6. Distinguishable Semantic Vectors
  7. Integration for Intelligence and Conciseness
  8. Theoretical Explanations
  9. Implementations Showcase
  10. Conclusions and Future Directions

Figures (5)

  • Figure 1: The evolution of the full-duplex systems, from the traditional FDD/TDD paradigm to the future-oriented SDD paradigm.
  • Figure 2: The illustration of the SDD transceiver's architecture with its training and semantics-division mechanisms. (a) The architecture of an SDD transceiver. (b) The training mechanisms of the neural network modules inside the SDD transceiver. (c) The semantics-division mechanism used in the Semantic Self-Interference Suppression Block of the SDD Semantic Decoder.
  • Figure 3: The duplex and coding methods of different full-duplex paradigms with their theoretical Feasible Regions.
  • Figure 4: Example of the MS-SSIM performance achieved by different full-duplex demos for the Rician-distributed self-interference scenario.
  • Figure 5: Example of visual comparisons within the SINR range of --50dB to --30dB for the Rician-distributed self-interference scenario, in which the black images represent the images that cannot be obtained by the BPG decoder at the corresponding SINR.