Deep Correlation Analysis for Audio-EEG Decoding

TL;DR

This paper introduces a neural network framework for audio-EEG correlation analysis that outperforms traditional linear methods by effectively reducing artifacts and enhancing stimulus-response correlation in brain recordings.

Contribution

It presents novel deep learning models for intra- and inter-subject audio-EEG analysis that directly optimize correlation, improving accuracy over linear techniques.

Findings

Deep models significantly improve Pearson correlation (up to 29.3% in music tasks).

Models effectively suppress EEG artifacts while preserving stimulus-related components.

Analysis of model parameters reveals their impact on correlation performance.

Abstract

The electroencephalography (EEG), which is one of the easiest modes of recording brain activations in a non-invasive manner, is often distorted due to recording artifacts which adversely impacts the stimulus-response analysis. The most prominent techniques thus far attempt to improve the stimulus-response correlations using linear methods. In this paper, we propose a neural network based correlation analysis framework that significantly improves over the linear methods for auditory stimuli. A deep model is proposed for intra-subject audio-EEG analysis based on directly optimizing the correlation loss. Further, a neural network model with a shared encoder architecture is proposed for improving the inter-subject stimulus response correlations. These models attempt to suppress the EEG artifacts while preserving the components related to the stimulus. Several experiments are performed using EEG recordings from subjects listening to speech and music stimuli. In these experiments, we show that the deep models improve the Pearson correlation significantly over the linear methods (average absolute improvements of 7.4% in speech tasks and 29.3% in music tasks). We also analyze the impact of several model parameters on the stimulus-response correlation.