EMGFlow: Robust and Efficient Surface Electromyography Synthesis via Flow Matching

TL;DR

EMGFlow introduces a flow matching-based generative model for synthetic surface electromyography data, improving data augmentation for gesture recognition with better efficiency and quality than existing GAN and diffusion methods.

Contribution

This is the first application of Flow Matching and continuous-time generative modeling to the sEMG domain, demonstrating superior performance and efficiency.

Findings

EMGFlow outperforms GAN and diffusion baselines in sEMG data augmentation.

It provides stronger utility in downstream tasks under the TSTR protocol.

Optimized generation dynamics improve quality-efficiency trade-offs.

Abstract

Deep learning-based surface electromyography (sEMG) gesture recognition is frequently bottlenecked by data scarcity and limited subject diversity. While synthetic data generation via Generative Adversarial Networks (GANs) and diffusion models has emerged as a promising augmentation strategy, these approaches often face challenges regarding training stability or inference efficiency. To bridge this gap, we propose EMGFlow, a conditional sEMG generation framework. To the best of our knowledge, this is the first study to investigate the application of Flow Matching (FM) and continuous-time generative modeling in the sEMG domain. To validate EMGFlow across three benchmark sEMG datasets, we employ a unified evaluation protocol integrating feature-based fidelity, distributional geometry, and downstream utility. Extensive evaluations show that EMGFlow outperforms conventional augmentation and GAN baselines, and provides stronger standalone utility than the diffusion baselines considered here under the train-on-synthetic test-on-real (TSTR) protocol. Furthermore, by optimizing generation dynamics through advanced numerical solvers and targeted time sampling, EMGFlow achieves improved quality-efficiency trade-offs. Taken together, these results suggest that Flow Matching is a promising and efficient paradigm for addressing data bottlenecks in myoelectric control systems. Our code is available at: https://github.com/Open-EXG/EMGFlow.