Typing Reinvented: Towards Hands-Free Input via sEMG
By: Kunwoo Lee , Dhivya Sreedhar , Pushkar Saraf and more
Potential Business Impact:
Control computers with muscle movements for typing.
We explore surface electromyography (sEMG) as a non-invasive input modality for mapping muscle activity to keyboard inputs, targeting immersive typing in next-generation human-computer interaction (HCI). This is especially relevant for spatial computing and virtual reality (VR), where traditional keyboards are impractical. Using attention-based architectures, we significantly outperform the existing convolutional baselines, reducing online generic CER from 24.98% -> 20.34% and offline personalized CER from 10.86% -> 10.10%, while remaining fully causal. We further incorporate a lightweight decoding pipeline with language-model-based correction, demonstrating the feasibility of accurate, real-time muscle-driven text input for future wearable and spatial interfaces.
Similar Papers
Muscle Anatomy-aware Geometric Deep Learning for sEMG-based Gesture Decoding
Human-Computer Interaction
Reads your hand movements from arm signals.
Generative Muscle Stimulation: Physical Assistance by Constraining Multimodal-AI with Biomechanical Knowledge
Human-Computer Interaction
Helps robots understand and do tasks from your words.
Reconstruction of Surface EMG Signal using IMU data for Upper Limb Actions
Machine Learning (CS)
Predicts muscle signals from movement sensors.