Affect Decoding in Phonated and Silent Speech Production from Surface EMG

TL;DR

This study demonstrates that surface EMG can reliably decode emotional states like frustration from facial and neck muscles during both spoken and silent speech, indicating potential for affect-aware silent speech interfaces.

Contribution

Introduces a new EMG dataset and shows that affective states can be decoded from facial and neck EMG signals across different speech modes, including silent speech.

Findings

EMG can discriminate frustration with up to 0.845 AUC

Affective signatures are present in facial motor activity during silent speech

Decoding models generalize well across speech modes

Abstract

The expression of affect is integral to spoken communication, yet, its link to underlying articulatory execution remains unclear. Measures of articulatory muscle activity such as EMG could reveal how speech production is modulated by emotion alongside acoustic speech analyses. We investigate affect decoding from facial and neck surface electromyography (sEMG) during phonated and silent speech production. For this purpose, we introduce a dataset comprising 2,780 utterances from 12 participants across 3 tasks, on which we evaluate both intra- and inter-subject decoding using a range of features and model embeddings. Our results reveal that EMG representations reliably discriminate frustration with up to 0.845 AUC, and generalize well across articulation modes. Our ablation study further demonstrates that affective signatures are embedded in facial motor activity and persist in the absence of phonation, highlighting the potential of EMG sensing for affect-aware silent speech interfaces.