Unified RF Source Separator Matches Specialized Models Without Knowing the Interference Type
Researchers show that specialized RF separators trained for a single signal/interference pair fail on unseen interference, often leaving the recovered signal worse than no processing at all. They instead train one interference-agnostic separator across all pairs using two architectures with no shared components: a convolutional WaveNet from the ICASSP 2024 RF Challenge and a band-split transformer adapted from music source separation. At the size of a single specialized model, the unified separator keeps bit error rate close to the models it replaces on nearly every pair and matches the best specialized model on interference absent from every training set, removing the need to know or label the interference type at test time.
Demonstrates a concrete, transferable research result — a single AI model for co-channel RF separation that generalizes to unseen jamming — valuable for readers building robust wireless and signal-processing systems.
Comments & Questions (0)
No comments yet
Be the first to comment!