Applied AI-Enhanced RF Interference Rejection
Researchers have developed an AI-enhanced method using Autoregressive Transformer Decoder models to reject RF interference in radio signals, demonstrating improved performance over traditional techniques. The system effectively recovers analog FM signals corrupted by OFDM interference, a common type in modern RF environments, while maintaining low latency. Testing shows significant improvements in speech intelligibility using metrics like PESQ, even under poor SINR conditions. The approach operates efficiently on lightweight GPUs, suggesting applicability in tactical, national security, and commercial settings.
Opening excerpt (first ~120 words) tap to expand
Electrical Engineering and Systems Science > Signal Processing arXiv:2604.22816 (eess) [Submitted on 14 Apr 2026] Title:Applied AI-Enhanced RF Interference Rejection Authors:Rahul Jain, Pierre Trepagnier, Rick Gentile, Joey Botero, Alexia Schulz View a PDF of the paper titled Applied AI-Enhanced RF Interference Rejection, by Rahul Jain and 4 other authors View PDF HTML (experimental) Abstract:AI-enhanced interference rejection in radio frequency (RF) transmissions has recently attracted interest because deep learning approaches trained on both the signal of interest (SOI) and the signal mixture (SOI plus interference) can outperform traditional approaches which only consider the SOI.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI