Hugo Van hamme

This study uses large language models to analyze how attention affects neural tracking of linguistic context in multi-talker speech environments.

The paper introduces SparrKULee, a large EEG dataset of speech-evoked auditory responses from 85 participants, suitable for training machine learning models and benchmarking encoding/decoding tasks.

This study uses EEG and deep learning to classify native versus foreign speech perception based on linguistic features and observes differences in neural tracking patterns.

The paper uses a convolutional neural network to analyze EEG data and shows it better captures linguistic speech features than linear models.

This paper introduces a deep neural network called VLAAI for decoding speech envelopes from EEG, showing improved performance over linear models and demonstrating good generalization across subjects and stimuli.