Deep joint source-channel coding for semantic communications
File(s)
Accepted version
Author(s)
Type
Thesis
Abstract
Semantic communications is considered a promising technology that will increase the efficiency of next-generation communication systems, particularly human-machine and machine-type communications. In contrast to the source-agnostic approach of conventional wireless communication systems, semantic communications seek to ensure that only relevant information for the underlying task is communicated to the receiver. Considering most semantic communication applications have strict latency, bandwidth, and power constraints, a prominent approach is to model them as a joint source-channel coding (JSCC) problem. Although JSCC has been a long-standing open problem in communication and coding theory, remarkable performance gains have been made recently over existing separate source and channel coding systems, particularly in low-la-tency and low-power scenarios. Recent progress has been made thanks to the adoption of deep learning techniques for joint source-channel code design that outperform the concatenation of state-of-the-art compression and channel coding schemes, which are the result of decades-long research efforts. In this article, we present an adaptive deep learning based JSCC (DeepJSCC) architecture for semantic communications, introduce its design principles, highlight its benefits, and outline future research challenges that lie ahead.
Date Issued
2023-11-01
Date Acceptance
2023-11-01
Citation
IEEE Communications Magazine, 2023, 61 (11), pp.42-48
ISSN
0163-6804
Publisher
Institute of Electrical and Electronics Engineers
Start Page
42
End Page
48
Journal / Book Title
IEEE Communications Magazine
Volume
61
Issue
11
Subjects
Codes
Deep learning
Engineering
Engineering, Electrical & Electronic
Human-machine systems
IMAGE TRANSMISSION
Performance gain
Receivers
Science & Technology
Semantics
SYSTEM
Technology
Telecommunications
Wireless communication
Publication Status
Published
Date Publish Online
2023-11-23