Toward Robust EEG-based Intention Decoding during Misarticulated Speech in Dysarthria

TL;DR

This study develops a novel EEG-based intention decoding framework that improves accuracy and stability in detecting speech intentions in individuals with dysarthria, even during misarticulations, advancing assistive communication technology.

Contribution

It introduces a soft multitask learning model with domain alignment to enhance EEG-based intention decoding in dysarthria, addressing variability caused by misarticulations.

Findings

Achieved 52.7% F1-score for correct trials, 41.4% for misarticulated trials

Improved baseline performance by 2% and 11% respectively

Demonstrated potential for more stable EEG-based communication support

Abstract

Dysarthria impairs motor control of speech, often resulting in reduced intelligibility and frequent misarticulations. Although interest in brain-computer interface technologies is growing, electroencephalogram (EEG)-based communication support for individuals with dysarthria remains limited. To address this gap, we recorded EEG data from one participant with dysarthria during a Korean automatic speech task and labeled each trial as correct or misarticulated. Spectral analysis revealed that misarticulated trials exhibited elevated frontal-central delta and alpha power, along with reduced temporal gamma activity. Building on these observations, we developed a soft multitask learning framework designed to suppress these nonspecific spectral responses and incorporated a maximum mean discrepancy-based alignment module to enhance class discrimination while minimizing domain-related variability. The proposed model achieved F1-scores of 52.7 % for correct and 41.4 % for misarticulated trials-an improvement of 2 % and 11 % over the baseline-demonstrating more stable intention decoding even under articulation errors. These results highlight the potential of EEG-based assistive systems for communication in language impaired individuals.