# Hierarchical Deep Feature Learning For Decoding Imagined Speech From EEG

## TL;DR

This paper introduces a hierarchical deep learning framework combining CNNs, RNNs, and autoencoders to improve the accuracy of decoding imagined speech from EEG signals, utilizing covariance matrices for spatial-temporal feature representation.

## Contribution

It presents a novel mixed deep neural network architecture with hierarchical training and covariance-based features for EEG-based speech imagery classification.

## Key findings

- Achieved approximately 23.45% accuracy improvement over baseline methods.
- Demonstrated effectiveness of hierarchical deep learning for EEG classification.
- Validated approach on a publicly available EEG speech imagery dataset.

## Abstract

We propose a mixed deep neural network strategy, incorporating parallel combination of Convolutional (CNN) and Recurrent Neural Networks (RNN), cascaded with deep autoencoders and fully connected layers towards automatic identification of imagined speech from EEG. Instead of utilizing raw EEG channel data, we compute the joint variability of the channels in the form of a covariance matrix that provide spatio-temporal representations of EEG. The networks are trained hierarchically and the extracted features are passed onto the next network hierarchy until the final classification. Using a publicly available EEG based speech imagery database we demonstrate around 23.45% improvement of accuracy over the baseline method. Our approach demonstrates the promise of a mixed DNN approach for complex spatial-temporal classification problems.