# SplashNet: Split-and-Share Encoders for Accurate and Efficient Typing with Surface Electromyography

arXiv: https://arxiv.org/abs/2506.12356 · HTML: https://mlsanity.com/paper/2506.12356/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 26 references that are in the map.
- First posted on arXiv 14 Jun 2025.

## Builds on (most cited first, 10 of 10)

- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Chirality Nets for Human Pose Regression](https://mlsanity.com/paper/1911.00029/) (2019)
- [Sequence-to-Sequence Speech Recognition with Time-Depth Separable Convolutions](https://mlsanity.com/paper/1904.02619/) (2019)
- [emg2pose: A Large and Diverse Benchmark for Surface Electromyographic Hand Pose Estimation](https://mlsanity.com/paper/2412.02725/) (2024)
- [emg2qwerty: A Large Dataset with Baselines for Touch Typing using Surface Electromyography](https://mlsanity.com/paper/2410.20081/) (2024)
- [Multi-Stream End-to-End Speech Recognition](https://mlsanity.com/paper/1906.08041/) (2019)
- [Sliding-Window Normalization to Improve the Performance of Machine-Learning Models for Real-Time Motion Prediction Using Electromyography](https://mlsanity.com/paper/2205.09301/) (2022)
- [Word-level Sign Language Recognition with Multi-stream Neural Networks Focusing on Local Regions and Skeletal Information](https://mlsanity.com/paper/2106.15989/) (2021)
- [Natural Typing Recognition via Surface Electromyography](https://mlsanity.com/paper/2109.10743/) (2021)
- [Physical Action Categorization using Signal Analysis and Machine Learning](https://mlsanity.com/paper/2008.06971/) (2020)

## Built on by (most cited first, 1 of 1)

- [A Montage-Agnostic Encoder for Calibration-Light Cross-User Gesture Recognition from Surface Electromyography](https://mlsanity.com/paper/2607.27565/) (2026)

## Abstract (arXiv)

Surface electromyography (sEMG) at the wrists could enable natural, keyboard-free text entry, yet the state-of-the-art emg2qwerty baseline still misrecognizes 51.8% of characters in the zero-shot setting on unseen users and 7.0% after user-specific fine-tuning. We trace many of these errors to mismatched cross-user signal statistics, fragile reliance on high-order feature dependencies, and the absence of architectural inductive biases aligned with the bilateral nature of typing. To address these issues, we introduce three simple modifications: (i) Rolling Time Normalization, which adaptively aligns input distributions across users; (ii) Aggressive Channel Masking, which encourages reliance on low-order feature combinations more likely to generalize across users; and (iii) a Split-and-Share encoder that processes each hand independently with weight-shared streams to reflect the bilateral symmetry of the neuromuscular system. Combined with a five-fold reduction in spectral resolution (33!rightarrow!6 frequency bands), these components yield a compact Split-and-Share model, SplashNet-mini, which uses only tfrac14 the parameters and 0.6× the FLOPs of the baseline while reducing character-error rate (CER) to 36.4% zero-shot and 5.9% after fine-tuning. An upscaled variant, SplashNet (tfrac12 the parameters, 1.15× the FLOPs of the baseline), further lowers error to 35.7% and 5.5%, representing relative improvements of 31% and 21% in the zero-shot and fine-tuned settings, respectively. SplashNet therefore establishes a new state of the art without requiring additional data.