Classifying Music-Induced Emotion Using Multi-Modal Ensembles of EEG and Audio Feature Models
Philipp Paukner, Marisa Ripoll, Dilvan Sabir, Deniz Onat Erdogan, Luca Sacchetto, Klaus Diepold
Abstract
In this paper, we present our submission to the EEG-Music Emotion Recognition Challenge at ICASSP 2025. Our work focused on Task 2, where the objective was to classify the emotional state of subjects in a discrete valence-arousal space while they listen to music. Our proposed solution adopts an ensemble approach, integrating electroencephalography (EEG) signals, raw audio signals, and song features. We incorporated a diverse set of models, including Audio Spectrogram Transformer (AST) [1] and a dedicated EEG model. By combining insights from these modalities, we aimed to capture the interplay between music and emotional responses. We achieved a balanced accuracy of 41.34% on held-out data, improving the baseline by more than 11% and thus 2<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">nd</sup> place in the competition.
BibTeX
@inproceedings{icassp2025_classifyingmusic,
title = {Classifying Music-Induced Emotion Using Multi-Modal Ensembles of EEG and Audio Feature Models},
author = {Philipp Paukner and Marisa Ripoll and Dilvan Sabir and Deniz Onat Erdogan and Luca Sacchetto and Klaus Diepold},
booktitle = {ICASSP 2025},
year = {2025}
}