Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

VQ-DSC-R: Robust Vector Quantized-Enabled Digital Semantic Communication With OFDM Transmission

Jianqiao Chen, Nan Ma, Xiaodong Xu, Tingting Zhu, Huishi Song, Chen Dong, Wenkai Liu, Rui Meng, Ping Zhang

TL;DR

A robust vector quantized-enabled digital semantic communication (VQ-DSC-R) system built upon orthogonal frequency division multiplexing (OFDM) transmission, and a differentiable vector quantization with adaptive noise-variance (ANDVQ) scheme to mitigate quantization errors in SQC.

Abstract

Digital mapping of semantic features is essential for achieving interoperability between semantic communication and practical digital infrastructure. However, current research efforts predominantly concentrate on analog semantic communication with simplified channel models. To bridge these gaps, we develop a robust vector quantized-enabled digital semantic communication (VQ-DSC-R) system built upon orthogonal frequency division multiplexing (OFDM) transmission. Our work encompasses the framework design of VQ-DSC-R, followed by a comprehensive optimization study. Firstly, we design a Swin Transformer-based backbone for hierarchical semantic feature extraction, integrated with VQ modules that map the features into a shared semantic quantized codebook (SQC) for efficient index transmission. Secondly, we propose a differentiable vector quantization with adaptive noise-variance (ANDVQ) scheme to mitigate quantization errors in SQC, which dynamically adjusts the quantization process using K-nearest neighbor statistics, while exponential moving average mechanism stabilizes SQC training. Thirdly, for robust index transmission over multipath fading channel and noise, we develop a conditional diffusion model (CDM) to refine channel state information, and design an attention-based module to dynamically adapt to channel noise. The entire VQ-DSC-R system is optimized via a three-stage training strategy. Extensive experiments demonstrate superiority of VQ-DSC-R over benchmark schemes, achieving high compression ratios and robust performance in practical scenarios.

VQ-DSC-R: Robust Vector Quantized-Enabled Digital Semantic Communication With OFDM Transmission

TL;DR

A robust vector quantized-enabled digital semantic communication (VQ-DSC-R) system built upon orthogonal frequency division multiplexing (OFDM) transmission, and a differentiable vector quantization with adaptive noise-variance (ANDVQ) scheme to mitigate quantization errors in SQC.

Abstract

Digital mapping of semantic features is essential for achieving interoperability between semantic communication and practical digital infrastructure. However, current research efforts predominantly concentrate on analog semantic communication with simplified channel models. To bridge these gaps, we develop a robust vector quantized-enabled digital semantic communication (VQ-DSC-R) system built upon orthogonal frequency division multiplexing (OFDM) transmission. Our work encompasses the framework design of VQ-DSC-R, followed by a comprehensive optimization study. Firstly, we design a Swin Transformer-based backbone for hierarchical semantic feature extraction, integrated with VQ modules that map the features into a shared semantic quantized codebook (SQC) for efficient index transmission. Secondly, we propose a differentiable vector quantization with adaptive noise-variance (ANDVQ) scheme to mitigate quantization errors in SQC, which dynamically adjusts the quantization process using K-nearest neighbor statistics, while exponential moving average mechanism stabilizes SQC training. Thirdly, for robust index transmission over multipath fading channel and noise, we develop a conditional diffusion model (CDM) to refine channel state information, and design an attention-based module to dynamically adapt to channel noise. The entire VQ-DSC-R system is optimized via a three-stage training strategy. Extensive experiments demonstrate superiority of VQ-DSC-R over benchmark schemes, achieving high compression ratios and robust performance in practical scenarios.
Paper Structure (17 sections, 41 equations, 7 figures, 2 tables, 2 algorithms)

This paper contains 17 sections, 41 equations, 7 figures, 2 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Background and Significance
  3. Related Works and Contributions
  4. System model and problem formulation
  5. System Model
  6. Problem Formulation
  7. Proposed VQ-DSC-R System
  8. VQ-enabled Semantic Feature Extraction, Quantization, Transmission and Reconstruction
  9. Proposed ANDVQ Scheme for SQC Update
  10. Proposed CDM-based Scheme for CSI Refinement
  11. Training Strategy
  12. Experiments and Results Discussion
  13. Experiments Setup
  14. Performance of SQC Update Schemes
  15. Performance of Channel Estimation Schemes
  16. ...and 2 more sections

Figures (7)

  • Figure 1: Architecture of VQ-DSC-R system with OFDM transmission. (a) Overall system architecture; (b) Illustration of time-frequency grids of OFDM symbols.
  • Figure 2: Architectures of SQC-SE and SQC-SD for DSC. (a) Architecture of SQC-SE; (b) Architecture of SQC-SD; (c) Feature Fusion layer; (d) Up-sampling layer; (e) SNR ModNet layer.
  • Figure 3: The architecture of designed conditional U-Net.
  • Figure 5: NMSE and BER performance curves for different schemes versus different SNR conditions. (a) NMSE Performance; (b) BER Performance.
  • Figure 6: PSNR and MS-SSIM performance of SQC update schemes under different channel estimation schemes and BCRs. (a) and (d) present the performance of STE scheme; (b) and (e) present the performance of NSVQ scheme; (c) and (f) present the performance of ANDVQ scheme.
  • ...and 2 more figures