Saved in:
Bibliographic Details
Main Authors: Lee, Kunwoo, Sreedhar, Dhivya, Saraf, Pushkar, Lee, Chaeeun, Shapovalenko, Kateryna
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.18213
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911282704154624
author Lee, Kunwoo
Sreedhar, Dhivya
Saraf, Pushkar
Lee, Chaeeun
Shapovalenko, Kateryna
author_facet Lee, Kunwoo
Sreedhar, Dhivya
Saraf, Pushkar
Lee, Chaeeun
Shapovalenko, Kateryna
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_18213
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Typing Reinvented: Towards Hands-Free Input via sEMG
Lee, Kunwoo
Sreedhar, Dhivya
Saraf, Pushkar
Lee, Chaeeun
Shapovalenko, Kateryna
Human-Computer Interaction
Machine Learning
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.
title Typing Reinvented: Towards Hands-Free Input via sEMG
topic Human-Computer Interaction
Machine Learning
url https://arxiv.org/abs/2511.18213