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

TL;DR

SplashNet introduces a novel split-and-share encoder architecture with normalization and masking techniques, significantly improving surface electromyography-based typing accuracy across users while reducing model complexity.

Contribution

The paper proposes a new neural network architecture and training modifications that enhance generalization and efficiency for sEMG-based text entry, setting a new state-of-the-art.

Findings

SplashNet reduces character error rate to 36.4% zero-shot and 5.9% after fine-tuning.

Model achieves 75% parameter reduction and 40% FLOPs reduction compared to baseline.

Significant improvements in cross-user generalization without additional data.

Abstract

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 $0.6\times$ 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, $1.15\times$ 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.