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

TL;DR

This paper explores decoding speech from facial EMG signals, revealing a geometric approach that enhances neural network efficiency for speech neuroprostheses, especially useful in clinical scenarios with limited data and computational resources.

Contribution

It introduces a novel geometric framework for EMG signal analysis using SPD manifolds, improving speech decoding and neural network efficiency.

Findings

SPD manifold is a natural embedding space for EMG signals

Linear transformations interpret manifold-valued EMG data

Significant distribution shifts across individuals

Abstract

Objective. 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. Approach. To achieve this, we collect EMG signals from the face, jaw, and neck as subjects articulate speech, and we perform EMG-to-speech translation. Main results. Our findings reveal that the manifold of symmetric positive definite (SPD) 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. Significance. 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.