# The Radio-Frequency Transformer for Signal Separation

arXiv: https://arxiv.org/abs/2603.09201 · HTML: https://mlsanity.com/paper/2603.09201/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 42 references that are in the map.
- First posted on arXiv 10 Mar 2026.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [SoundStream: An End-to-End Neural Audio Codec](https://mlsanity.com/paper/2107.03312/) (2021)
- [Finite Scalar Quantization: VQ-VAE Made Simple](https://mlsanity.com/paper/2309.15505/) (2023)
- [Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation](https://mlsanity.com/paper/1809.07454/) (2018)
- [Supervised Speech Separation Based on Deep Learning: An Overview](https://mlsanity.com/paper/1708.07524/) (2017)
- [Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation](https://mlsanity.com/paper/1804.03619/) (2018)
- [Hybrid Transformers for Music Source Separation](https://mlsanity.com/paper/2211.08553/) (2022)
- [Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation](https://mlsanity.com/paper/1806.03185/) (2018)
- [TasNet: time-domain audio separation network for real-time, single-channel speech separation](https://mlsanity.com/paper/1711.00541/) (2017)
- [The Conversation: Deep Audio-Visual Speech Enhancement](https://mlsanity.com/paper/1804.04121/) (2018)
- [Particle Transformer for Jet Tagging](https://mlsanity.com/paper/2202.03772/) (2022)
- [Demucs: Deep Extractor for Music Sources with extra unlabeled data remixed](https://mlsanity.com/paper/1909.01174/) (2019)
- [Sudo rm -rf: Efficient Networks for Universal Audio Source Separation](https://mlsanity.com/paper/2007.06833/) (2020)
- [Source Separation with Deep Generative Priors](https://mlsanity.com/paper/2002.07942/) (2020)
- [Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation: Results with Advanced LIGO Data](https://mlsanity.com/paper/1711.03121/) (2017)
- [MMDenseLSTM: An efficient combination of convolutional and recurrent neural networks for audio source separation](https://mlsanity.com/paper/1805.02410/) (2018)
- [Annealed Langevin Dynamics for Massive MIMO Detection](https://mlsanity.com/paper/2205.05776/) (2022)
- [Multitrack Music Transcription with a Time-Frequency Perceiver](https://mlsanity.com/paper/2306.10785/) (2023)
- [Pileup Mitigation with Machine Learning (PUMML)](https://mlsanity.com/paper/1707.08600/) (2017)
- [Denoising Auto-encoder with Recurrent Skip Connections and Residual Regression for Music Source Separation](https://mlsanity.com/paper/1807.01898/) (2018)
- [Score-based Source Separation with Applications to Digital Communication Signals](https://mlsanity.com/paper/2306.14411/) (2023)
- [Continual Audio-Visual Sound Separation](https://mlsanity.com/paper/2411.02860/) (2024)
- [End-to-end Source Separation with Adaptive Front-Ends](https://mlsanity.com/paper/1705.02514/) (2017)
- [RF Challenge: The Data-Driven Radio Frequency Signal Separation Challenge](https://mlsanity.com/paper/2409.08839/) (2024)
- [On Neural Architectures for Deep Learning-based Source Separation of Co-Channel OFDM Signals](https://mlsanity.com/paper/2303.06438/) (2023)
- [A Novel Approach to WaveNet Architecture for RF Signal Separation with Learnable Dilation and Data Augmentation](https://mlsanity.com/paper/2402.09461/) (2024)

## Built on by (most cited first, 3 of 3)

- [Applied AI-Enhanced RF Interference Rejection](https://mlsanity.com/paper/2604.22816/) (2026)
- [Clearing the Underbrush: AI-Enhanced RF Interference Suppression](https://mlsanity.com/paper/2608.24974/) (2026)
- [FlowSep-RF: Rectified Flow Matching for Single-Channel Radio-Frequency Signal Separation](https://mlsanity.com/paper/2610.20269/) (2026)

## Abstract (arXiv)

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.