Eeg signals reveal musical mode and melody direction during piano play
EEG-Based Decoding of Musical Mode and Melodic Direction Using Empirical Mode Decomposition
Sound
Summary
Understanding how the brain responds to music involves detecting features like musical mode (happy or sad feeling) and the shape of a melody. The authors show that by breaking down brainwave recordings using a method called Empirical Mode Decomposition, they can extract features that help identify these musical aspects. They trained a neural network to recognize these patterns and achieved about 80% accuracy across different people. This method works regardless of which hand the player uses and highlights brain areas linked to music processing.
What this means in practice
- •For music therapy professionals: Identify specific brain responses to musical modes and melodies for tailoring therapeutic interventions using EEG data.
- •For brain-computer interface developers: Incorporate EMD-based feature extraction to improve recognition of musical features from EEG signals in real-time music-controlled interfaces.
Authors
Sergio Guillén, Lorenzo J. Tardón, Ana M. Barbancho, Isabel Barbancho
Abstract
Electroencephalography (EEG) has proven to be a powerful tool for decoding neural activity in real-life scenarios, including the perception and processing of emotions elicited by music. Among the various musical features that modulate these responses, musical mode and melodic direction (or contour) play a central role. This work proposes a novel EEG feature extraction framework based on Empirical Mode Decomposition (EMD) to decompose EEG signals recorded during active piano performance for the detection of these two musical features. Energy-based descriptors were computed from the first four Intrinsic Mode Functions (IMFs) obtained through EMD and used to train a Wide Neural Network classifier. The model performance was benchmarked against several standard classifiers commonly employed in EEG classification tasks. Two experimental scenarios were explored: intra-subject and intersubject. In the former case, the proposed framework achieved average accuracies of 84%, whereas in the inter-subject case, accuracies reached 81% on average using the first IMF, with AUC-ROC values of 0.9 on average in both cases. A frequency-domain analysis revealed a strong correspondence between the IMFs and conventional EEG sub-bands, except for certain specific frequency components that were not fully represented. Predominant activations were observed over the frontal, temporal, and parietooccipital regions, areas consistently associated with music processing. Furthermore, the proposed method demonstrated robustness to handedness, successfully classifying EEG data across participants regardless of their dominant hand. These findings highlight the potential of EMD-based feature extraction for identifying music-related neural patterns and contribute to advancing research in Music Information Retrieval (MIR), affective neuroscience, and the broader understanding of the neural encoding of musical structure.