Auto-Regressive RF Synchronization Using Deep-Learning

This work presents a novel pilot-less Deep-Learning-based synchronization mechanism that seamlessly integrates within state-of-the-art auto-encoder-based end-to-end communication systems. By re-using the idea of Radio Transformer Networks, an auto-regressive strategy is designed that learns to estim...

Full description

Saved in:
Bibliographic Details
Published in2024 IEEE International Conference on Machine Learning for Communication and Networking (ICMLCN) pp. 145 - 150
Main Authors Petry, Michael, Parlier, Benjamin, Koch, Andreas, Werner, Martin
Format Conference Proceeding
LanguageEnglish
Published IEEE 05.05.2024
Subjects
algorithm
auto-regressive
center frequency offset
Frequency modulation
Machine learning
Performance gain
Perturbation methods
Radio frequency
RF front end
RF synchronization
sample time offset
Time-frequency analysis
Transformers
Online AccessGet full text

Cover

More Information
Summary:This work presents a novel pilot-less Deep-Learning-based synchronization mechanism that seamlessly integrates within state-of-the-art auto-encoder-based end-to-end communication systems. By re-using the idea of Radio Transformer Networks, an auto-regressive strategy is designed that learns to estimate and mitigate synchronization-related perturbations for arbitrarily modulated continuous communication, i.e., sample time offset (STO) and carrier frequency offset (CFO). A performance gain of 0.6 dB in the high-SNR regime compared to classic synchronization techniques is demonstrated. The strength of this approach is a shift from sample-by-sample to batch-wise processing according to the ML paradigm, which enables efficient and fast computation required for practical deployment scenarios using hardware-accelerated ML inference engines.
DOI:10.1109/ICMLCN59089.2024.10624754