EEG-based detection of the locus of auditory attention with convolutional neural networks

Abstract
Data availability
Article and author information
Metrics

Abstract

In a multi-speaker scenario, the human auditory system is able to attend to one particular speaker of interest and ignore the others. It has been demonstrated that it is possible to use electroencephalography (EEG) signals to infer to which speaker someone is attending by relating the neural activity to the speech signals. However, classifying auditory attention within a short time interval remains the main challenge. We present a convolutional neural network-based approach to extract the locus of auditory attention (left/right) without knowledge of the speech envelopes. Our results show that it is possible to decode the locus of attention within 1 to 2 s, with a median accuracy of around 81%. These results are promising for neuro-steered noise suppression in hearing aids, in particular in scenarios where per-speaker envelopes are unavailable.

Data availability

Code used for training and evaluating the network has been made available at https://github.com/exporl/locus-of-auditory-attention-cnn. The CNN models used to generate the results shown in the paper are also available at that location. The dataset used in this study had been made available earlier at https://zenodo.org/record/3377911.

The following previously published data sets were used

1. Das
2. Neetha
3. Francart
4. Tom
5. & Bertrand
6. Alexander
(2019) Auditory Attention Detection Dataset KULeuven
http://doi.org/10.5281/zenodo.3377911.

https://zenodo.org/record/3377911

Article and author information

Author details

Servaas Vandecappelle

Department of Neurosciences, Katholieke Universiteit Leuven, Leuven, Belgium

For correspondence
servaas.vandecappelle@gmail.com

Competing interests
The authors declare that no competing interests exist.

"This ORCID iD identifies the author of this article:" 0000-0002-0266-7293
Lucas Deckers

Department of Neurosciences, Katholieke Universiteit Leuven, Leuven, Belgium

Competing interests
The authors declare that no competing interests exist.
Neetha Das

Department of Neurosciences, Katholieke Universiteit Leuven, Leuven, Belgium

Competing interests
The authors declare that no competing interests exist.
Amir Hossein Ansari

Department of Electrical Engineering, Katholieke Universiteit Leuven, Leuven, Belgium

Competing interests
The authors declare that no competing interests exist.
Alexander Bertrand

Department of Electrical Engineering, Katholieke Universiteit Leuven, Leuven, Belgium

Competing interests
The authors declare that no competing interests exist.

"This ORCID iD identifies the author of this article:" 0000-0002-4827-8568
Tom Francart

Dept. of Neurosciences, Katholieke Universiteit Leuven, Leuven, Belgium

For correspondence
tom.francart@kuleuven.be

Competing interests
The authors declare that no competing interests exist.

Funding

KU Leuven Special Research Fund (C14/16/057)

Tom Francart

KU Leuven Special Research Fund (C24/18/099)

Alexander Bertrand

Research Foundation Flanders (1.5.123.16N)

Alexander Bertrand

Research Foundation Flanders (G0A4918N)

Alexander Bertrand

European Research Council (637424)

Tom Francart

European Research Council (802895)

Alexander Bertrand

The funders had no role in study design, data collection and interpretation, or the decision to submit the work for publication.

Ethics

Human subjects: The experiment was approved by the Ethics Committee Research UZ/KU Leuven (S57102) and every participant signed an informed consent form approved by the same commitee.

Copyright

This article is distributed under the terms of the Creative Commons Attribution License permitting unrestricted use and redistribution provided that the original author and source are credited.