Deep Multiway Canonical Correlation Analysis for Multi-Subject EEG Normalization
This addresses the challenge of inter-subject variability in EEG analysis for auditory neuroscience, offering an incremental improvement over existing linear methods.
The paper tackled the problem of normalizing EEG data from multiple subjects to remove inter-subject redundancies and boost stimulus-related components, proposing a deep learning framework that improved correlations over linear methods with absolute gains of 0.08 for speech and 0.29 for music tasks.
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.