Transfer Learning for Covert Speech Classification Using EEG Hilbert Envelope and Temporal Fine Structure

TL;DR

This study demonstrates that transferring classifiers trained on overt speech EEG data to covert speech improves classification accuracy and reduces training effort in brain-computer interfaces.

Contribution

The paper introduces a transfer learning approach using EEG features from Hilbert envelope and temporal fine structure for covert speech classification.

Findings

Achieved 86.44% accuracy on overt speech

Achieved 79.82% accuracy on covert speech

Reduced training burden for covert speech BCIs

Abstract

Brain-Computer Interfaces (BCIs) can decode imagined speech from neural activity. However, these systems typically require extensive training sessions where participants imaginedly repeat words, leading to mental fatigue and difficulties identifying the onset of words, especially when imagining sequences of words. This paper addresses these challenges by transferring a classifier trained in overt speech data to covert speech classification. We used electroencephalogram (EEG) features derived from the Hilbert envelope and temporal fine structure, and used them to train a bidirectional long-short-term memory (BiLSTM) model for classification. Our method reduces the burden of extensive training and achieves state-of-the-art classification accuracy: 86.44% for overt speech and 79.82% for covert speech using the overt speech classifier.