Publications

In this report, we show that linear stimulus reconstruction (AAD) for EEG-based auditory attention decoding works on the KU Leuven audiovisual, gaze-controlled AAD dataset.

In this preprint, we present a new unsupervised method to estimate the performance of the stimulus reconstruction algorithm for EEG-based auditory attention decoding.

In this preprint, we present a new end-to-end deep learning model, AADnet, for auditory attention decoding from EEG in multi-talker scenarios.

In this preprint, we present a new experiment in which participants attend on of two superimposed video, and we show that we can decode their attention from EEG and gaze data.

In this paper, we present a new signal processing technique for the group analysis of stimulus-following neural responses, building upon our conference precursor. Again, all code is available!

In this paper, presented at EUSIPCO 2024, we present a probabilistic gain control system steered by brain-decoded auditory attention decoding algorithms.

In this article, we perform absolute attention decoding to speech based on EEG signals, to determine whether a subject is attending to the speech or not.

In this article, we demonstrate how a new object-based video feature leads to robust correlations with the decoded activity from EEG when subjects are watching natural videos.

In this article, we try to uncover potential biases of the CSP-based decoding of the spatial focus of auditory attention, using a multi-talker audiovisual EEG experiment.

In this paper, presented at EUSIPCO 2023, we propose a new signal processing technique to extract stimulus-following neural reponses from a group of subjects. All MATLAB code to implement the method and reproduce the experiments is available!

In this article, presented at ICASSP 2023, we present an update of the unsupervised stimulus decoder that avoids its inherent bias to the initialization.

In this article, published in Signal Processing, we present a novel sparse variable selection method for generalized Rayleigh quotient optimization and generalized eigenvalue problems, which are ubiquitous in many signal processing fields.

In this article, publlished in IEEE Journal of Biomedical and Health Informatics, we present a new time-adapative unsupervised stimulus decoder for AAD.

In this article, published in IEEE Signal Processing Magazine, we provide a broad review and a statistically grounded comparative study of EEG-based AAD algorithms and address the main signal processing challenges in this field.

In this article, presented at ICASSP 2021, we present a novel method to decode the spatial focus of auditory attention from EEG using Riemmanian geometry-based classifiers.

In this article, presented in IEEE Journal of Biomedical and Health Informatics, we present a novel unsupervised algorithm to train a stimulus decoder for AAD.

In this article, published in IEEE Transactions on Biomedical Engineering, we propose a new common spatial pattern-based algorithm to decode the spatial focus of auditory attention from EEG signals.

In this article, published in IEEE Transactions on Neural Systems and Rehabilitation Engineering, we present a novel interpretable performance metric for AAD algorithms based on an adative gain control system.

In this article, presented at EUSIPCO 2019, we present a new performance metric to evaluate AAD algorithms.

In this article, presented at ACSSC 2018, we propose a tensor-based algorithm for detection of atrial fibrillation in ECG signals.