Decoding High-level Imagined Speech using Attention-based Deep Neural Networks

TL;DR

This paper presents an attention-based deep neural network model that improves the decoding accuracy of imagined speech EEG signals, demonstrating the feasibility of more intuitive brain-computer interfaces.

Contribution

The study introduces a modified deep learning model that enhances local feature learning for decoding imagined speech EEG signals, achieving significant accuracy improvements.

Findings

Average accuracy of 0.5648 for four-word classification

Model effectively learns local features in EEG signals

Demonstrates feasibility of robust imagined speech decoding

Abstract

Brain-computer interface (BCI) is the technology that enables the communication between humans and devices by reflecting status and intentions of humans. When conducting imagined speech, the users imagine the pronunciation as if actually speaking. In the case of decoding imagined speech-based EEG signals, complex task can be conducted more intuitively, but decoding performance is lower than that of other BCI paradigms. We modified our previous model for decoding imagined speech-based EEG signals. Ten subjects participated in the experiment. The average accuracy of our proposed method was 0.5648 for classifying four words. In other words, our proposed method has significant strength in learning local features. Hence, we demonstrated the feasibility of decoding imagined speech-based EEG signals with robust performance.