EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Comparison Study of Deep Learning Methodologies for Music Emotion Recognition

Pedro Lima Louro iD, Hugo Redinho iD, Ricardo Malheiro iD, Rui Pedro Paiva iD, Renato Panda iD

Sensors · 29.03.2024 · 24 (7) · 2201

DOI: 10.3390/s24072201 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 29.03.2024. Verfasst von Pedro Lima Louro und 4 weiteren Autor:innen. Beteiligte Einrichtung: CISUC, LASI, DEI, FCTUC, University of Coimbra, 3030-790 Coimbra, Portugal. Hauptthemen laut MEDLINE: Deep Learning, Music. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundação para a Ciência e Tecnologia, FCT—Foundation for Science and Technology, European Social Fund.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Classical machine learning techniques have dominated Music Emotion Recognition. However, improvements have slowed down due to the complex and time-consuming task of handcrafting new emotionally relevant audio features. Deep learning methods have recently gained popularity in the field because of their ability to automatically learn relevant features from spectral representations of songs, eliminating such necessity. Nonetheless, there are limitations, such as the need for large amounts of quality labeled data, a common problem in MER research. To understand the effectiveness of these techniques, a comparison study using various classical machine learning and deep learning methods was conducted. The results showed that using an ensemble of a Dense Neural Network and a Convolutional Neural Network architecture resulted in a state-of-the-art 80.20% F1 score, an improvement of around 5% considering the best baseline results, concluding that future research should take advantage of both paradigms, that is, combining handcrafted features with feature learning.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningMusicData AccuracyEmotionsMachine Learning

Stichwörter der Autor:innen

deep learningmusic emotion recognitionmusic information retrieval

Autor:innen und Institutionen

  • CISUC, LASI, DEI, FCTUC, University of Coimbra, 3030-790 Coimbra, Portugal.
  • School of Technology and Management, Polytechnic Institute of Leiria, 2411-901 Leiria, Portugal.
  • Ci2-Smart Cities Research Center, Polytechnic Institute of Tomar, 2300-313 Tomar, Portugal.

ORCID-Profile: Pedro Lima Louro, Hugo Redinho, Ricardo Malheiro, Rui Pedro Paiva, Renato Panda

Förderung

  • Fundação para a Ciência e Tecnologia
  • FCT—Foundation for Science and Technology
  • European Social Fund
  • Ci2

Zitieren

APA

Louro, P. L., Redinho, H., Malheiro, R., Paiva, R. P., & Panda, R. (2024). A Comparison Study of Deep Learning Methodologies for Music Emotion Recognition. Sensors, 24(7), 2201. https://doi.org/10.3390/s24072201

Vancouver

Louro PL, Redinho H, Malheiro R, Paiva RP, Panda R. A Comparison Study of Deep Learning Methodologies for Music Emotion Recognition. Sensors. 2024;24(7):2201. doi:10.3390/s24072201

BibTeX
@article{Louro2024,
  author = {Louro, Pedro Lima and Redinho, Hugo and Malheiro, Ricardo and Paiva, Rui Pedro and Panda, Renato},
  title = {A Comparison Study of Deep Learning Methodologies for Music Emotion Recognition},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {7},
  pages = {2201},
  doi = {10.3390/s24072201}
}
Kostenlos starten →