Modeling the relationship between acoustic stimulus and EEG with a dilated convolutional neural network

Current tests to measure whether a person can understand speech require behavioral responses from the person,which is in practice not always possible (e.g. young children). Therefore there is a need for objective measures of speech intelligibility. Recently, it has been shown that speech intelligibility can be measured by letting a person listen to natural speech,recording the electroencephalogram (EEG) and decoding the speech envelope from the EEG signal. Linear decoders are used,which is sub-optimal, as the human brain is a complex non-linear system and cannot easily be modeled by a linear decoder. Wetherefore propose an approach based on deep learning which canmodel complex non-linear relationships. Our approach is basedon dilated convolutions as used in WaveNet to maximize thereceptive field with regard to the number of tunable parameters.Comparison with a model based on a state of the art linear decoder and a convolutional baseline model shows that our proposed model significantly improves on both models (from62.3% to 90.6% (p <0.001) and from 78.8% to 90.6% (p <0.001)respectively). Best results are achieved with a receptive field size between 250-500ms, which is longer than the optimal integration window for a linear decoder

ISBN:978-9-0827-9705-3

Jaar van publicatie:2021

BOF-keylabel:ja

IOF-keylabel:ja

Authors from:Higher Education

Toegankelijkheid:Closed