Eeg-based speech activity detection

Abstract

The brain-computer interface is one of the most up-to-date communication options. The advances made in this area open up opportunities to help mentally or physically disadvantaged people. The brain-computer interface offers the possibility of re-acquiring communication skills by deaf individuals. Electroencephalography (EEG) based speech recognition is, therefore, a novel research topic, which is an important component in communication technologies. In this article, we propose a speech activity detector algorithm, which, as expected, should improve the performance of the EEG based speech recognition system. EEG data uploaded while pronouncing 50 different phrases were classified using a feed-forward neural network. As a result of detection, a 0.82 F1 score was achieved.