Development of Syllable Labelling Tool for Electroencephalogram Data

Abstract

EEG (Electroencephalogram) is an electrical signal representing activity of the brain and have been used for healthcare and brain-machine interface. Recently, research to estimate imagined linguistic information from EEG signals was launched. The research needs labeled EEG dataset that are given boundaries of imagined syllables. In this paper, we propose the syllable labeling tool for research on EEG. Labelers can adjust boundaries of each syllable using a mouse or a keyboard while observing features extracted from EEG signals. They can also easily reuse analytical methods developed by themselves because this tool runs on MATLAB. Moreover, in this paper, we describe a semi-automatic labeling method to improve operating efficiency.