Enhancing Semantic Communication with Deep Generative Models -- An ICASSP Special Session Overview

TL;DR

This paper overviews how deep generative models can advance semantic communication by improving data extraction, robustness to channel issues, and enabling future AI-driven communication systems.

Contribution

It introduces the role of deep generative models in semantic communication and outlines new research directions for integrating these models into future frameworks.

Findings

Deep generative models enhance semantic data extraction.

They improve robustness to channel corruptions.

New research pathways for generative semantic communication are proposed.

Abstract

Semantic communication is poised to play a pivotal role in shaping the landscape of future AI-driven communication systems. Its challenge of extracting semantic information from the original complex content and regenerating semantically consistent data at the receiver, possibly being robust to channel corruptions, can be addressed with deep generative models. This ICASSP special session overview paper discloses the semantic communication challenges from the machine learning perspective and unveils how deep generative models will significantly enhance semantic communication frameworks in dealing with real-world complex data, extracting and exploiting semantic information, and being robust to channel corruptions. Alongside establishing this emerging field, this paper charts novel research pathways for the next generative semantic communication frameworks.