Extracting Spatial Muscle Activation Patterns in Facial and Neck Muscles for Silent Speech Recognition Using High-Density sEMG

Abstract

Human is capable of producing versatile and precise speech owing to the complex neuromuscular systems that control the movement of facial and neck muscle groups. Silent speech recognition (SSR) based on surface electromyography (sEMG) has been widely researched, which enables speech communication in the absence of an audible acoustic signal. However, the differences in the activities of facial and neck muscle groups under different phoneme pronunciation conditions have not been well investigated. The present work aims to quantify the macroscopic spatial patterns of the muscle activations at the phoneme level during the movement of facial and neck speech articulator muscle groups (SAMGs) using 320-channel high-density (HD) electrode arrays. Ten subjects performed 14 vowel speech tasks and 15 consonant speech tasks in audible speech (AS) and silent speech (SS) modes, respectively. Specifically, the root-mean-square heat maps of sEMG signals were used to characterize the SAMGs activation patterns. The results show that the muscle activation regions are overlapped under different phoneme pronunciation conditions and are symmetric between the left and right sides of the face and neck with an average correlation coefficient >0.9. In addition, the best result can achieve a classification accuracy of 85.78% for consonants and 79.42% for vowels in SS mode. The overall results can provide a reference to the hardware or electrode design of portable devices for practical use in future work.