Geometry of orofacial neuromuscular signals: speech articulation decoding using surface electromyography

<i>Objective.</i>In this article, we present data and methods for decoding speech articulations using surface electromyogram (EMG) signals. EMG-based speech neuroprostheses offer a promising approach for restoring audible speech in individuals who have lost the ability to speak intelligibly due to laryngectomy, neuromuscular diseases, stroke, or trauma-induced damage (e.g. from radiotherapy) to the speech articulators.<i>Approach.</i>To achieve this, we collect EMG signals from the face, jaw, and neck as subjects articulate speech, and we perform EMG-to-speech translation.<i>Main results.</i>Our findings reveal that the manifold of symmetric positive definite matrices serves as a natural embedding space for EMG signals. Specifically, we provide an algebraic interpretation of the manifold-valued EMG data using linear transformations, and we analyze and quantify distribution shifts in EMG signals across individuals.<i>Significance.</i>Overall, our approach demonstrates significant potential for developing neural networks that are both data- and parameter-efficient-an important consideration for EMG-based systems, which face challenges in large-scale data collection and operate under limited computational resources on embedded devices.