Speech Imagery Classification using Length-Wise Training based on Deep Learning

TL;DR

This paper introduces a length-wise training approach with a hierarchical CNN and specialized loss function to improve speech imagery classification from EEG signals, addressing challenges of non-stationarity and spatial feature extraction.

Contribution

It proposes a novel length-wise training method combined with a hierarchical CNN architecture and loss function for better speech imagery EEG classification.

Findings

The method achieved competitive classification performance.

Word length serves as a useful cue for improving accuracy.

Hierarchical CNN effectively captures relevant features.

Abstract

Brain-computer interface uses brain signals to control external devices without actual control behavior. Recently, speech imagery has been studied for direct communication using language. Speech imagery uses brain signals generated when the user imagines speech. Unlike motor imagery, speech imagery still has unknown characteristics. Additionally, electroencephalography has intricate and non-stationary properties resulting in insufficient decoding performance. In addition, speech imagery is difficult to utilize spatial features. In this study, we designed length-wise training that allows the model to classify a series of a small number of words. In addition, we proposed hierarchical convolutional neural network structure and loss function to maximize the training strategy. The proposed method showed competitive performance in speech imagery classification. Hence, we demonstrated that the length of the word is a clue at improving classification performance.