EEG-Transformer: Self-attention from Transformer Architecture for Decoding EEG of Imagined Speech

TL;DR

This paper explores the use of transformer-based self-attention modules to decode EEG signals during imagined and overt speech, demonstrating improved performance and practicality for brain-computer interfaces.

Contribution

It introduces the application of self-attention modules from transformer architecture to EEG decoding, reducing parameters and enabling single-channel EEG use.

Findings

Self-attention modules improve EEG decoding accuracy.

Single-channel EEG can effectively decode imagined speech.

Transformer-based models outperform traditional CNNs in this task.

Abstract

Transformers are groundbreaking architectures that have changed a flow of deep learning, and many high-performance models are developing based on transformer architectures. Transformers implemented only with attention with encoder-decoder structure following seq2seq without using RNN, but had better performance than RNN. Herein, we investigate the decoding technique for electroencephalography (EEG) composed of self-attention module from transformer architecture during imagined speech and overt speech. We performed classification of nine subjects using convolutional neural network based on EEGNet that captures temporal-spectral-spatial features from EEG of imagined speech and overt speech. Furthermore, we applied the self-attention module to decoding EEG to improve the performance and lower the number of parameters. Our results demonstrate the possibility of decoding brain activities of imagined speech and overt speech using attention modules. Also, only single channel EEG or ear-EEG can be used to decode the imagined speech for practical BCIs.