Surface Electromyographic Control of a Three-Steps Speller Interface

Many individuals require Aided Augmentative and Alternative Communication (AAAC) to communicate, especially when traditional AAC, like sign language, is not an option due to some movement impairments. This paper presents a high tech AAAC using Surface Electromyography (sEMG) signals as an input modality for the direct control of a speller presented on a Graphical User Interface (GUI). The GUI displays alphabetical letters, special characters, and a delete option. The aim of this study is to introduce and examine the performance of a three-steps sEMG-based speller which does not depend on the movement of a system cursor. Seven subjects participated in the experiment to test the spelling system. Each participant had to undergo a familiarization task first, after which the main spelling task took place. Experimental data were recorded and the resulted mean accuracy and information transfer rate (ITR) for the main spelling task were 89.10% and 55.10 bits/min, respectively, at an average spelling speed of 10.29 char/min. Results and users' feedback also indicated that the spelling performance could be further enhanced through training and the regular use of the speller.