Zero Perception Error Rate-Distortion for Semantic Communication

Choi, Jinho; Nam, Hyelin; Park, Jihong; Ko, Seung-Woo; Kim, Seong-Lyun

Permalink

https://hdl.handle.net/2142/130281 Copy

Description

Title

Zero Perception Error Rate-Distortion for Semantic Communication

Author(s)

• Choi, Jinho
• Nam, Hyelin
• Park, Jihong
• Ko, Seung-Woo
• Kim, Seong-Lyun

Issue Date

2025-09-17

Keyword(s)

• Rate-distortion theory
• Semantic communication
• Zero perception error

Abstract

In this paper, we explore the rate-distortion theory for semantic communication with zero perception error (ZEPE). By incorporating a ZEPE constraint, the decoder can generate a reconstructed signal that maintains ZEPE while satisfying a given distortion constraint. This approach can be viewed as a special case of the conventional rate-distortion framework. We derive the optimal transition probability and extend the ZEPE rate-distortion framework to include inferred latent variables, which can capture the semantic meaning of the observed signal. For practical implementations, we discuss the use of generative models such as variational autoencoders (VAEs).

Publisher

Allerton Conference on Communication, Control, and Computing

Series/Report Name or Number

2025 61st Allerton Conference on Communication, Control, and Computing Proceedings

ISSN

2836-4503

Type of Resource

Text

Genre of Resource

Conference Paper/Presentation

Language

eng

Handle URL

https://hdl.handle.net/2142/130281&&

Copyright and License Information

Copyright 2025 owned by the authors.

Owning Collections