Electroencephalography-Based Auditory Attention Decoding: Toward Neurosteered Hearing Devices

Simon Geirnaert (1) , Servaas Vandecappelle (1) , Emina Alickovic (2) , Alain de Cheveigné (3, 4, 5) , Edmund Lalor (6) , Bernd Meyer , Sina Miran (1) , Tom Francart (1) , Alexander Bertrand (1)

1 KU Leuven - Catholic University of Leuven = Katholieke Universiteit Leuven
2 Oticon A/S [Danemark]
3 CNRS - Centre National de la Recherche Scientifique
4 DEC - Département d'Etudes Cognitives - ENS Paris
5 LSP - Laboratoire des systèmes perceptifs
6 University of Rochester [USA]

People suffering from hearing impairment often have difficulties participating in conversations in so-called `cocktail party' scenarios with multiple people talking simultaneously. Although advanced algorithms exist to suppress background noise in these situations, a hearing device also needs information on which of these speakers the user actually aims to attend to. Recent neuroscientific advances have shown that it is possible to determine the focus of auditory attention from non-invasive neurorecording techniques, such as electroencephalography (EEG). Based on these new insights, a multitude of auditory attention decoding (AAD) algorithms have been proposed, which could, in combination with the appropriate speaker separation algorithms and miniaturized EEG sensor devices, lead to a new generation of so-called neuro-steered hearing devices. In this paper, we address the main signal processing challenges in this field and provide a review and comparative study of state-of-the-art AAD algorithms.

Domaines: Sciences cognitives

Simon Geirnaert, Servaas Vandecappelle, Emina Alickovic, Alain de Cheveigné, Edmund Lalor, et al.. Electroencephalography-Based Auditory Attention Decoding: Toward Neurosteered Hearing Devices. IEEE Signal Processing Magazine, 2021, 38 (4), pp.89-102. ⟨10.1109/MSP.2021.3075932⟩. ⟨hal-03090994⟩