Abstract
Surface electroencephalography is a standard and noninvasive way to measure electrical brain activity. Recent advances in artificial intelligence led to significant improvements in the automatic detection of brain patterns, allowing increasingly faster, more reliable and accessible Brain-Computer Interfaces. Different paradigms have been used to enable the human-machine interaction and the last few years have broad a mark increase in the interest for interpreting and characterizing the “inner voice” phenomenon. This paradigm, called inner speech, raises the possibility of executing an order just by thinking about it, allowing a “natural” way of controlling external devices. Unfortunately, the lack of publicly available electroencephalography datasets, restricts the development of new techniques for inner speech recognition. A ten-participant dataset acquired under this and two others related paradigms, recorded with an acquisition system of 136 channels, is presented. The main purpose of this work is to provide the scientific community with an open-access multiclass electroencephalography database of inner speech commands that could be used for better understanding of the related brain mechanisms.
Highlights
Background & SummaryBrain-Computer Interfaces (BCIs) are a promising technology for improving the quality of life of people who have lost the capability to either communicate or interact with their environment[1]
A BCI provides an alternative way of interaction to such individuals, by decoding the neural activity and transforming it into control commands for triggering wheelchairs, prosthesis, spellers or any other virtual interface device[2,3]
In BCI applications, neural activity is typically measured by electroencephalography (EEG), since it is a non-invasive technique, the measuring devices can be portable and the EEG signals have high time resolution[1,2]
Summary
Brain-Computer Interfaces (BCIs) are a promising technology for improving the quality of life of people who have lost the capability to either communicate or interact with their environment[1]. In the dataset presented in Pressel et al.[17], where all participants were native Spanish speakers, the acquisition system had only six channels, highly restricting spatial analysis As mentioned before, both datasets were focused on the imagined speech paradigm rather than on inner speech. All paradigms and the requested actions are explained in detail in the BCI Interaction Conditions Section This dataset will allow future users to explore whether inner speech activates similar mechanisms as pronounced speech or whether it is closer to visualizing a spatial location or movement. Each participant performed between 475 and 570 trials in a single day recording, obtaining a dataset with more than 9 hours of continuous EEG data recording, with over 5600 trials
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
