Velum movement detection based on surface electromyography for speech interface

Abstract

Conventional speech communication systems do not perform well in the absence of an intelligible acoustic signal. Silent Speech Interfaces enable speech communication to take place with speech-handicapped users and in noisy environments. However, since no acoustic signal is available, information on nasality may be absent, which is an important and relevant characteristic of several languages, particularly European Portuguese. In this paper we propose a non-invasive method - surface Electromyography (EMG) electrodes - positioned in the face and neck regions to explore the existence of useful information about the velum movement. The applied procedure takes advantage of Real-Time Magnetic Resonance Imaging (RT-MRI) data, collected from the same speakers, to interpret and validate EMG data. By ensuring compatible scenario conditions and proper alignment between the EMG and RT-MRI data, we are able to estimate when the velum moves and the probable type of movement under a nasality occurrence. Overall results of this experiment revealed interesting and distinct characteristics in the EMG signal when a nasal vowel is uttered and that it is possible to detect velum movement, particularly by sensors positioned below the ear between the mastoid process and the mandible in the upper neck region.