Can LLMs Understand Unvoiced Speech? Exploring EMG-to-Text Conversion with LLMs
This work addresses a practical communication challenge for individuals with speech impairments, representing an incremental step in extending LLMs to understand articulatory biosignals.
The paper tackled the problem of converting unvoiced electromyography (EMG) signals to text for individuals unable to produce vocal speech, proposing an EMG adaptor module that maps EMG features into a large language model's input space, achieving an average word error rate of 0.49 and improving performance by nearly 20% with only six minutes of data.
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.