Deep Multiway Canonical Correlation Analysis for Multi-Subject EEG Normalization

TL;DR

This paper introduces a deep learning framework called DMCCA that enhances the correlation of multi-subject EEG data during audio listening tasks by extending linear multi-way CCA with an auto-encoder architecture.

Contribution

It presents a novel deep multi-way CCA model that improves EEG data normalization across subjects for auditory stimuli, outperforming linear CCA methods.

Findings

Significant correlation improvements for speech and music EEG data.

Deep multi-way CCA outperforms linear CCA in EEG normalization.

Model trained with combined correlation and reconstruction loss.

Abstract

The normalization of brain recordings from multiple subjects responding to the natural stimuli is one of the key challenges in auditory neuroscience. The objective of this normalization is to transform the brain data in such a way as to remove the inter-subject redundancies and to boost the component related to the stimuli. In this paper, we propose a deep learning framework to improve the correlation of electroencephalography (EEG) data recorded from multiple subjects engaged in an audio listening task. The proposed model extends the linear multi-way canonical correlation analysis (CCA) for audio-EEG analysis using an auto-encoder network with a shared encoder layer. The model is trained to optimize a combined loss involving correlation and reconstruction. The experiments are performed on EEG data collected from subjects listening to natural speech and music. In these experiments, we show that the proposed deep multi-way CCA (DMCCA) based model significantly improves the correlations over the linear multi-way CCA approach with absolute improvements of 0.08 and 0.29 in terms of the Pearson correlation values for speech and music tasks respectively.