The Radio-Frequency Transformer for Signal Separation

• URL: http://arxiv.org/abs/2603.09201v1
• Date: Tue, 10 Mar 2026 05:22:02 GMT
• Title: The Radio-Frequency Transformer for Signal Separation
• Abstract summary: We study a problem of signal separation: estimating a signal of interest contaminated by an unknown non-Gaussian background/interference.<n>We learn a good discrete tokenizer for SOI and then train an end-to-end transformer on a cross-entropy loss.<n>Across real and synthetic mixtures from the MIT RF Challenge dataset, our method achieves competitive performance.
• Score: 29.348481060446314
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study a problem of signal separation: estimating a signal of interest (SOI) contaminated by an unknown non-Gaussian background/interference. Given the training data consisting of examples of SOI and interference, we show how to build a fully data-driven signal separator. To that end we learn a good discrete tokenizer for SOI and then train an end-to-end transformer on a cross-entropy loss. Training with a cross-entropy shows substantial improvements over the conventional mean-squared error (MSE). Our tokenizer is a modification of Google's SoundStream, which incorporates additional transformer layers and switches from VQVAE to finite-scalar quantization (FSQ). Across real and synthetic mixtures from the MIT RF Challenge dataset, our method achieves competitive performance, including a 122x reduction in bit-error rate (BER) over prior state-of-the-art techniques for separating a QPSK signal from 5G interference. The learned representation adapts to the interference type without side information and shows zero-shot generalization to unseen mixtures at inference time, underscoring its potential beyond RF. Although we instantiate our approach on radio-frequency mixtures, we expect the same architecture to apply to gravitational-wave data (e.g., LIGO strain) and other scientific sensing problems that require data-driven modeling of background and noise.

Related papers

• GenAI for Energy-Efficient and Interference-Aware Compressed Sensing of GNSS Signals on a Google Edge TPU [37.74014735747033]
  This paper introduces a novel method for compressing and classifying jamming threats using generative artificial intelligence (GenAI)<n>Our proposed approach efficiently compresses data streams directly at the hardware receiver while simultaneously classifying jamming and spoofing attacks in real time.<n>The hardware-centric GenAI approach also substantially reduces jammer signal transmission costs, offering a practical solution for interference mitigation.
  arXiv  Detail & Related papers  (2026-05-14T13:43:55Z)
• Applied AI-Enhanced RF Interference Rejection [2.3977391435533373]
  deep learning approaches trained on both the signal of interest (SOI) and the signal mixture (SOI plus interference) can outperform traditional approaches.<n>We show that unintelligible transmissions become intelligible via metrics such as Perceptual Evaluation of Speech Quality (PESQ)<n>We believe these same techniques can be applied to a broader set of national security scenarios, as well as having commercial applications.
  arXiv  Detail & Related papers  (2026-04-14T18:55:12Z)
• Learning to Separate RF Signals Under Uncertainty: Detect-Then-Separate vs. Unified Joint Models [53.79667447811139]
  We show that a single deep neural architecture learns to jointly detect and separate when applied directly to the received signal.<n>These findings highlight UJM as a scalable and practical alternative to DTS, while opening new directions for unified separation under broader estimation.
  arXiv  Detail & Related papers  (2026-02-04T15:25:02Z)
• Doppler Invariant CNN for Signal Classification [0.0]
  We propose a convolutional neural network (CNN) architecture with complex-valued layers that exploits convolutional shift equivariance in the frequency domain.<n>We show that our model maintains consistent classification accuracy with and without random Doppler shifts despite being trained on no Doppler-shifted examples.
  arXiv  Detail & Related papers  (2025-11-18T16:31:13Z)
• Transmitter Identification via Volterra Series Based Radio Frequency Fingerprint [3.7848713545513317]
  Radio Frequency Fingerprinting (RFF) offers a promising solution as it requires no cryptography and resists spoofing.<n>Existing RFF approaches often lack a unified theory and effective feature extraction.<n>In this work, we model the transmitter as a black box and analyze its impact on transmitted signals.<n> Experiments on a public LoRa dataset show state-of-the-art performance, with over 98% accuracy in static channels and above 90% under multipath and Doppler effects.
  arXiv  Detail & Related papers  (2025-10-22T10:11:41Z)
• Frequency Domain-Based Diffusion Model for Unpaired Image Dehazing [92.61216319417208]
  We propose a novel frequency domain-based diffusion model, named ours, for fully exploiting the beneficial knowledge in unpaired clear data.<n>Inspired by the strong generative ability shown by Diffusion Models (DMs), we tackle the dehazing task from the perspective of frequency domain reconstruction.
  arXiv  Detail & Related papers  (2025-07-02T01:22:46Z)
• FreSca: Scaling in Frequency Space Enhances Diffusion Models [55.75504192166779]
  This paper explores frequency-based control within latent diffusion models.<n>We introduce FreSca, a novel framework that decomposes noise difference into low- and high-frequency components.<n>FreSca operates without any model retraining or architectural change, offering model- and task-agnostic control.
  arXiv  Detail & Related papers  (2025-04-02T22:03:11Z)
• Unsupervised CP-UNet Framework for Denoising DAS Data with Decay Noise [13.466125373185399]
  Distributed acoustic sensor (DAS) technology leverages optical fiber cables to detect acoustic signals.<n>DAS exhibits a lower signal-to-noise ratio (S/N) compared to geophones.<n>This reduced S/N can negatively impact data analyses containing inversion and interpretation.
  arXiv  Detail & Related papers  (2025-02-19T03:09:49Z)
• RF Challenge: The Data-Driven Radio Frequency Signal Separation Challenge [66.33067693672696]
  We address the critical problem of interference rejection in radio-frequency (RF) signals using a data-driven approach that leverages deep-learning methods.<n>A primary contribution of this paper is the introduction of the RF Challenge, which is a publicly available, diverse RF signal dataset.
  arXiv  Detail & Related papers  (2024-09-13T13:53:41Z)
• Diffusion-Driven Semantic Communication for Generative Models with Bandwidth Constraints [66.63250537475973]
  This paper introduces a diffusion-driven semantic communication framework with advanced VAE-based compression for bandwidth-constrained generative model.<n>Our experimental results demonstrate significant improvements in pixel-level metrics like peak signal to noise ratio (PSNR) and semantic metrics like learned perceptual image patch similarity (LPIPS)
  arXiv  Detail & Related papers  (2024-07-26T02:34:25Z)
• Latency-Distortion Tradeoffs in Communicating Classification Results over Noisy Channels [8.159697831570593]
  We study the scenario where a probability vector needs to be transmitted over a noisy channel. We analyze the trade-off between transmission latency and the distortion. Our results show that there is an interesting interplay between source distortion (i.e., distortion for the probability vector measured via f-divergence) and the subsequent channel encoding/decoding parameters.
  arXiv  Detail & Related papers  (2024-04-22T21:22:12Z)
• Deep-Learned Compression for Radio-Frequency Signal Classification [0.49109372384514843]
  Next-generation cellular concepts rely on the processing of large quantities of radio-frequency (RF) samples. We propose a deep learned compression model, HQARF, to compress the complex-valued samples of RF signals. We are assessing the effects of HQARF on the performance of an AI model trained to infer the modulation class of the RF signal.
  arXiv  Detail & Related papers  (2024-03-05T17:42:39Z)
• Conditioning Trick for Training Stable GANs [70.15099665710336]
  We propose a conditioning trick, called difference departure from normality, applied on the generator network in response to instability issues during GAN training. We force the generator to get closer to the departure from normality function of real samples computed in the spectral domain of Schur decomposition.
  arXiv  Detail & Related papers  (2020-10-12T16:50:22Z)
• A Compressive Sensing Approach for Federated Learning over Massive MIMO Communication Systems [82.2513703281725]
  Federated learning is a privacy-preserving approach to train a global model at a central server by collaborating with wireless devices. We present a compressive sensing approach for federated learning over massive multiple-input multiple-output communication systems.
  arXiv  Detail & Related papers  (2020-03-18T05:56:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.