EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Adopting State-of-the-Art Pretrained Audio Representations for Music Recommender Systems

Yan-Martin Tamm, Anna Aljanaki

ACM Transactions on Recommender Systems · 31.12.2026 · 4 (4) · 1-28

DOI: 10.1145/3808222 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Recommender Systems, online erschienen am 28.07.2026. Verfasst von Yan-Martin Tamm und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 103 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Over the years, Music Information Retrieval (MIR) research community has released various models pretrained on large amounts of music data. Transfer learning showcases the proven effectiveness of pretrained backend models for a broad spectrum of downstream tasks, including auto-tagging and genre classification. However, MIR articles generally do not explore the efficiency of pretrained models for Music Recommender Systems (MRS). In addition, the Recommender Systems community tends to favour traditional end-to-end neural network training. Our research addresses this gap and evaluates the performance of nine pretrained backend models (MusicFM, Music2Vec, MERT, EncodecMAE, Jukebox, MusiCNN, MULE, MuQ, and MuQ-MuLan) in the context of MRS. We assess them using five recommendation approaches: K-Nearest Neighbours (KNN), Shallow Neural Network, Contrastive Multi-Modal projection, a Hybrid model, and BERT4Rec both for the hot and cold-start scenarios. Our findings suggest that pretrained audio representations exhibit significant performance disparity between traditional MIR tasks and both hot and cold music recommendations, indicating that valuable aspects of musical information captured by backend models may differ depending on the task. This study establishes a foundation for further exploration of pretrained audio representations to enhance music recommendation systems.

Zitieren

APA

Tamm, Y., & Aljanaki, A. (2026). Adopting State-of-the-Art Pretrained Audio Representations for Music Recommender Systems. ACM Transactions on Recommender Systems, 4(4), 1-28. https://doi.org/10.1145/3808222

Vancouver

Tamm Y, Aljanaki A. Adopting State-of-the-Art Pretrained Audio Representations for Music Recommender Systems. ACM Transactions on Recommender Systems. 2026;4(4):1-28. doi:10.1145/3808222

BibTeX
@article{Tamm2026,
  author = {Tamm, Yan-Martin and Aljanaki, Anna},
  title = {Adopting State-of-the-Art Pretrained Audio Representations for Music Recommender Systems},
  journal = {ACM Transactions on Recommender Systems},
  year = {2026},
  volume = {4},
  number = {4},
  pages = {1--28},
  doi = {10.1145/3808222}
}
Kostenlos starten →