Improvement of Motor Imagery BCI using Silent Speech

Abstract

Human expression are exhibited throughout by language, which is generally used for communications. Making use of this fact, combining the language expression silently with the imagination of movement may lead to the improvement on developing the brain-computer interface (BCI) system. This paper focuses on the silent speech related to upper limbs movement. In the experiment, five subjects performed silent speech, i.e. at the same time, imagined upper limbs movement follow by two words, which are "RIGHT" or "LEFT". Furthermore, each of the participants performed another experiment doing only motor imagery (MI). In both experiments, there are five trials for each movement side. 19-channel EEG was recorded. The EEG signals were simply analyzed by using the absolute power. The result shows the clearer activation of event-related desynchronization (ERD) of the alpha band (8-12 Hz) on the motor area (C3, C4) during the combination of silent speech and MI.