A Deep Learning Model for Correlation Analysis between Electroencephalography Signal and Speech Stimuli

In recent years, the use of electroencephalography (EEG) has grown as a tool for diagnostic and brain function monitoring, being simple non-invasive method compared with other procedures like histological sampling. Typically, in order to extract functional responses from EEG signals, prolonged repeated stimuli are needed because artifacts generated recordings which adversely impact stimulus-response analysis. To mitigate artifact effect, correlation analysis (CA) methods applied literature, where predominant approaches focus on enhancing correlations through linear canonical (CCA). This paper introduces novel CA framework based neural network loss specifically designed maximize between speech stimuli. Compared deep learning (DCCAs) this single multilayer perceptron (MLP) instead two networks each stimulus. validate proposed approach, comparison CCA (LCCA) DCCA was performed, using dataset containing traces subjects listening The experimental results show that improves overall Pearson by 10.56% state-of-the-art method.