EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

FakeMusicCaps: A Dataset for Detection and Attribution of Synthetic Music Generated via Text-to-Music Models

Luca Comanducci iD, Paolo Bestagini iD, Stefano Tubaro

Journal of Imaging · 18.07.2025 · 11 (7) · 242

DOI: 10.3390/jimaging11070242 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 18.07.2025. Verfasst von Luca Comanducci und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronics, Information and Bioengineering (DEIB), Politecnico di Milano, 20133 Milano, Italy. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Defense Advanced Research Projects Agency (DARPA), European Union, Italian Ministry of University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Text-to-music (TTM) models have recently revolutionized the automatic music generation research field, specifically by being able to generate music that sounds more plausible than all previous state-of-the-art models and by lowering the technical proficiency needed to use them. For these reasons, they have readily started to be adopted for commercial uses and music production practices. This widespread diffusion of TTMs poses several concerns regarding copyright violation and rightful attribution, posing the need of serious consideration of them by the audio forensics community. In this paper, we tackle the problem of detection and attribution of TTM-generated data. We propose a dataset, FakeMusicCaps, that contains several versions of the music-caption pairs dataset MusicCaps regenerated via several state-of-the-art TTM techniques. We evaluate the proposed dataset by performing initial experiments regarding the detection and attribution of TTM-generated audio considering both closed-set and open-set classification.

Schlagwörter

Stichwörter der Autor:innen

DeepFakeaudio forensicsmusic generationtext-to-music

Autor:innen und Institutionen

  • Department of Electronics, Information and Bioengineering (DEIB), Politecnico di Milano, 20133 Milano, Italy.

ORCID-Profile: Luca Comanducci, Paolo Bestagini

Förderung

  • Defense Advanced Research Projects Agency (DARPA)
  • European Union
  • Italian Ministry of University

Zitieren

APA

Comanducci, L., Bestagini, P., & Tubaro, S. (2025). FakeMusicCaps: A Dataset for Detection and Attribution of Synthetic Music Generated via Text-to-Music Models. Journal of Imaging, 11(7), 242. https://doi.org/10.3390/jimaging11070242

Vancouver

Comanducci L, Bestagini P, Tubaro S. FakeMusicCaps: A Dataset for Detection and Attribution of Synthetic Music Generated via Text-to-Music Models. Journal of Imaging. 2025;11(7):242. doi:10.3390/jimaging11070242

BibTeX
@article{Comanducci2025,
  author = {Comanducci, Luca and Bestagini, Paolo and Tubaro, Stefano},
  title = {FakeMusicCaps: A Dataset for Detection and Attribution of Synthetic Music Generated via Text-to-Music Models},
  journal = {Journal of Imaging},
  year = {2025},
  volume = {11},
  number = {7},
  pages = {242},
  doi = {10.3390/jimaging11070242}
}
Kostenlos starten →