IIST BCI Dataset-5 for Malayalam Vowels and Consonants

This paper presents a dataset of brain Electroencephalogram (EEG) signals created when Malayalam vowels and consonants are spoken. The dataset was created by capturing EEG signals utilizing the OpenBCI Cyton device while a volunteer spoke Malayalam vowels and consonants. It includes recordings obtained from both sub-vocal and vocal. The creation of this dataset aims to support individuals who speak Malayalam and suffer from neurodegenerative diseases. Moreover, this dataset is expected to advance brain-computer interface technology and has potential in developing effective communication solutions for individuals with limited verbal abilities.

本文提出了一个数据集，包含马拉雅拉姆语元音和辅音发声时产生的脑脑电图（Electroencephalogram, EEG）信号。该数据集通过使用OpenBCI Cyton设备捕获志愿者发声马拉雅拉姆语元音和辅音时的EEG信号构建而成，包含无声言语（sub-vocal）和发声言语（vocal）两种模式下的记录。构建该数据集旨在支持讲马拉雅拉姆语且患有神经退行性疾病的人群。此外，该数据集有望推动脑机接口（brain-computer interface）技术的发展，并在为言语能力受限人群开发高效沟通解决方案方面具有潜力。