ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Deep Correlation Analysis for Audio-EEG Decoding

Reddy Katthi, J and Ganapathy, S (2021) Deep Correlation Analysis for Audio-EEG Decoding. In: IEEE Transactions on Neural Systems and Rehabilitation Engineering, 29 . pp. 2742-2753.

IEEE_tra_neu_29_2742-2753_2021.pdf - Published Version

Download (15MB) | Preview
Official URL: https://doi.org/10.1109/TNSRE.2021.3129790


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.

Item Type: Journal Article
Publication: IEEE Transactions on Neural Systems and Rehabilitation Engineering
Publisher: Institute of Electrical and Electronics Engineers Inc.
Additional Information: The copyright for this article belongs to the Authors.
Keywords: Audio recordings; Correlation methods; Deep learning; Electroencephalography; Job analysis; Music, Audio-electroencephalography analyse; Brain modeling; Canonical correlation analyse; Canonical correlations analysis; Correlation; Deep learning; Multiway canonical correlation analyse; Task analysis, Electrophysiology, adult; article; artifact; artificial neural network; controlled study; correlation analysis; deep learning; electroencephalogram; electroencephalography; female; human; human experiment; male; music; speech test; stimulus response; brain; electroencephalography; hearing; music; physiology; procedures; speech, Auditory Perception; Brain; Electroencephalography; Humans; Music; Speech
Department/Centre: Division of Electrical Sciences > Electrical Engineering
Date Deposited: 01 Jun 2023 09:33
Last Modified: 01 Jun 2023 09:33
URI: https://eprints.iisc.ac.in/id/eprint/81726

Actions (login required)

View Item View Item