Non-invasive electromyographic speech neuroprosthesis: a geometric perspective

In this article, we present a high-bandwidth egocentric neuromuscular speech interface for translating silently voiced speech articulations into textand audio. Specifically, we collect electromyogram (EMG) signals from multiple articulatorysites on the face and neck as individuals articulate speech in an alaryngeal manner to perform EMG-to-text or EMG-to-audio translation. Such an interface is useful for restoring audible speech in individuals who have lost the ability to speak intelligibly due to laryngectomy, neuromuscular disease, stroke, or trauma-induced damage (e.g., radiotherapy toxicity) to speech articulators. Previous works have focused on training text or speech synthesis models using EMG collected during audible speech articulations or by transferring audio targets from EMG collected during audible articulation to EMG collected during silent articulation. However, such paradigms are not suited for individuals who have already lost the ability to audibly articulate speech. We are the first to present an alignment-free EMG-to-text and EMG-to-audio conversion using only EMG collected during silently articulated speech in an open-sourced manner. On a limited vocabulary corpora, our approach achieves almost 2.4x improvement in word error rate with a model that is 25x smaller by leveraging the inherent geometry of EMG.

Upper limb surface electromyography -- geometry, spectral characteristics, temporal evolution, and demographic confounds

Brain-body-computer interfaces aim to provide a fluid and natural way for humans to interact with technology. Among noninvasive interfaces, surface electromyogram (sEMG) signals have shown particular utility. However, much remains unknown about how sEMG is affected by various physiological and anatomical factors and how these confounds might affect gesture decoding across individuals or groups. In this article, we show that sEMG signals evince non-Euclidean graph data structure that is defined by a set of orthogonal axes and explain the signal distribution shift across individuals. We provide a dataset of upper limb sEMG signals and physiological measures of 91 adults as they perform 10 different hand gestures. Participants were selected to be representative of various age groups (18to 92 years) and BMI (healthy, overweight, and obese). Additional anatomical or physiological measures that might impact sEMG signals were also collected, such as skin hydration and elasticity. The article describes the inherent structure of sEMG data and provides methods to construct differentiable signal features that can be used with machine learning algorithms that use backpropagation. We then analyze how those parameters correlate with various physiological measures to probe if they can induce bias against (or towards) certain population groups. We find that higher frequencies in sEMG, although comprising less power than lower ones, provide better gesture decoding and show less bias with regard to demographic, circumstantial, and physiological confounds (such as age, skin hydration, and skin elasticity).