Abstract
Emotion is an important component of music investigated in music psychology. In recent years, the use of computational methods to assess the link between music and emotions has been promoted by advances in music emotion recognition. However, one of the main limitations of applying data-driven approaches to understand such a link is the scarce knowledge of how perceived music emotions might be inferred from automatically retrieved features. Through statistical analysis we investigate the relationship between perceived music emotions (rated by 41 listeners in terms of categories and dimensions) and multi-modal acoustic and symbolic features (automatically extracted from the audio and MIDI files of 24 pieces) in piano repertoire. We also assess the suitability of the identified features for music emotion recognition. Our results highlight the potential of assessing perception and data-driven methods in a unified framework.
Citation
Emilia
Parada-Cabaleiro,
Anton Batliner,
Maximilian Schmitt,
Björn Schuller,
Markus
Schedl
Music Emotions in Solo Piano: Bridging the Gap Between Human Perception and Machine Learning
Proceedings of the 16th International Symposium on Computer Music Multidisciplinary Research (CMMR 2023), ., 2023.
BibTeX
@inproceedings{Parada-Cabaleiro2023MusEmo_CMMR_2023,
title = {Music Emotions in Solo Piano: Bridging the Gap Between Human Perception and Machine Learning},
author = {Parada-Cabaleiro, Emilia and Batliner, Anton and Schmitt, Maximilian and Schuller, Björn and Schedl, Markus},
booktitle = {Proceedings of the 16th International Symposium on Computer Music Multidisciplinary Research (CMMR 2023), .},
location = {Tokyo, Japan, November 2023},
year = {2023}
}