# TokEye: Fast Signal Extraction for Fluctuating Time Series via Offline Self-Supervised Learning From Fusion Diagnostics to Bioacoustics

arXiv: https://arxiv.org/abs/2602.20317 · HTML: https://mlsanity.com/paper/2602.20317/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 62 references that are in the map.
- First posted on arXiv 23 Feb 2026.

## Builds on (most cited first, 11 of 11)

- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [Symmetric Cross Entropy for Robust Learning with Noisy Labels](https://mlsanity.com/paper/1908.06112/) (2019)
- [MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis](https://mlsanity.com/paper/1910.06711/) (2019)
- [High-Quality Self-Supervised Deep Image Denoising](https://mlsanity.com/paper/1901.10277/) (2019)
- [Exploring Efficient Asymmetric Blind-Spots for Self-Supervised Denoising in Real-World Scenarios](https://mlsanity.com/paper/2303.16783/) (2023)
- [Self-supervised Image Denoising with Downsampled Invariance Loss and Conditional Blind-Spot Network](https://mlsanity.com/paper/2304.09507/) (2023)
- [Masked and Shuffled Blind Spot Denoising for Real-World Images](https://mlsanity.com/paper/2404.09389/) (2024)
- [Automatic Identification of MHD Modes in Magnetic Fluctuations Spectrograms using Deep Learning Techniques](https://mlsanity.com/paper/2011.12615/) (2020)
- [Regulation Compliant AI for Fusion: Real-Time Image Analysis-Based Control of Divertor Detachment in Tokamaks](https://mlsanity.com/paper/2507.02897/) (2025)
- [Self-Supervised Speech Denoising Using Only Noisy Audio Signals](https://mlsanity.com/paper/2111.00242/) (2021)

## Abstract (arXiv)

Next-generation fusion facilities like ITER face a "data deluge," generating petabytes of multi-diagnostic signals daily that challenge manual analysis. We present a "signals-first" self-supervised framework for the automated extraction of coherent and transient modes from high-noise time-frequency data across a variety of sensors. We also develop a general-purpose method and tool for extracting coherent, quasi-coherent, and transient modes for fluctuation measurements in tokamaks by employing non-linear optimal techniques in multichannel signal processing with a fast neural network surrogate on fast magnetics, electron cyclotron emission, CO2 interferometers, and beam emission spectroscopy measurements from DIII-D. Results are tested on data from DIII-D, TJ-II, and non-fusion spectrograms. With an inference latency of 0.5 seconds, this framework enables real-time mode identification and large-scale automated database generation for advanced plasma control. Repository is in https://github.com/PlasmaControl/TokEye.