Saved in:
Bibliographic Details
Main Authors: Mohapatra, Payal, Pandey, Akash, Zhang, Xiaoyuan, Zhu, Qi
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.00304
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912405586444288
author Mohapatra, Payal
Pandey, Akash
Zhang, Xiaoyuan
Zhu, Qi
author_facet Mohapatra, Payal
Pandey, Akash
Zhang, Xiaoyuan
Zhu, Qi
contents Unvoiced electromyography (EMG) is an effective communication tool for individuals unable to produce vocal speech. However, most prior methods rely on paired voiced and unvoiced EMG signals, along with speech data, for EMG-to-text conversion, which is not practical for such individuals. Given the rise of large language models (LLMs) in speech recognition, we explore their potential to understand unvoiced speech. To this end, we address the challenge of learning from unvoiced EMG alone and propose a novel EMG adaptor module that maps EMG features into an LLM's input space, achieving an average word error rate (WER) of 0.49 on a closed-vocabulary unvoiced EMG-to-text task. Even with a conservative data availability of just six minutes, our approach improves performance over specialized models by nearly 20%. While LLMs have been shown to be extendable to new language modalities -- such as audio -- understanding articulatory biosignals like unvoiced EMG remains more challenging. This work takes a crucial first step toward enabling LLMs to comprehend unvoiced speech using surface EMG.
format Preprint
id arxiv_https___arxiv_org_abs_2506_00304
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Can LLMs Understand Unvoiced Speech? Exploring EMG-to-Text Conversion with LLMs
Mohapatra, Payal
Pandey, Akash
Zhang, Xiaoyuan
Zhu, Qi
Computation and Language
Unvoiced electromyography (EMG) is an effective communication tool for individuals unable to produce vocal speech. However, most prior methods rely on paired voiced and unvoiced EMG signals, along with speech data, for EMG-to-text conversion, which is not practical for such individuals. Given the rise of large language models (LLMs) in speech recognition, we explore their potential to understand unvoiced speech. To this end, we address the challenge of learning from unvoiced EMG alone and propose a novel EMG adaptor module that maps EMG features into an LLM's input space, achieving an average word error rate (WER) of 0.49 on a closed-vocabulary unvoiced EMG-to-text task. Even with a conservative data availability of just six minutes, our approach improves performance over specialized models by nearly 20%. While LLMs have been shown to be extendable to new language modalities -- such as audio -- understanding articulatory biosignals like unvoiced EMG remains more challenging. This work takes a crucial first step toward enabling LLMs to comprehend unvoiced speech using surface EMG.
title Can LLMs Understand Unvoiced Speech? Exploring EMG-to-Text Conversion with LLMs
topic Computation and Language
url https://arxiv.org/abs/2506.00304