跳到正文
arXiv cs.AI· Maxence Albert, Rapha\"el Duroselle, Thibaud Ehret, Olivier Boeffard, Jean-Fran\c{c}ois Bonastre·· 4 小时前AI 评分38

迈向干扰无关的射频源分离

Toward Interference-Agnostic RF Source Separation

AI 导读

研究人员训练单一射频分离器处理所有信号-干扰组合,测试时不提供干扰类型标签,采用 ICASSP 2024 RF Challenge 的卷积 WaveNet 和从音乐源分离改造的 band-split transformer 两种架构。统一分离器以单个专用模型规模保持比特错误率接近各专用模型,对训练集中未出现的干扰表现与最佳专用模型相当,无需人工选择部署哪个模型。

正文 · 原文

View PDF HTML (experimental)

Abstract:Separating a radio-frequency signal of interest from a co-channel interference is mostly addressed with specialized separators, each trained for one pair of signal and interference types and therefore relying on a label that a heavily jammed receiver cannot identify. We show that this reliance is not benign: applied to an interference it was not trained on, such a separator usually fails to recover the signal, and in most of the cases we measure it leaves the signal worse than no processing at all. We then train a single separator over every pair, giving it no indication at test time of which one it faces, on two architectures with no component in common: the convolutional WaveNet of the ICASSP 2024 RF Challenge, and a band-split transformer that we adapt from music source separation. Both behave the same way. At the size of one specialized model, the unified separator stays close to the whole models it replaces, keeping the bit error rate close on almost every pair, better on one and worse on another. On an interference absent from every training set, it does as well as the best specialized model, without anyone having to choose which one to deploy.
Comments: 5 pages, 3 figures, 1 tabs. Submitted to ICASSP2027
Subjects: Artificial Intelligence (cs.AI); Signal Processing (eess.SP)
Cite as: arXiv:2611.17950 [cs.AI]
  (or arXiv:2611.17950v1 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2611.17950

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Maxence Albert [view email]
[v1] Fri, 13 Nov 2026 09:37:57 UTC (62 KB)

来源:arXiv cs.AI · arxiv.org