{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/comparative-analysis-of-pretrained-audio","title":"Comparative Analysis of Pretrained Audio Representations in Music Recommender Systems","arxiv_id":"2409.08987","date":"2024-09-13","proceeding":null,"authors":["Yan-Martin Tamm","Anna Aljanaki"],"abstract":"Over the years, Music Information Retrieval (MIR) has proposed various models pretrained on large amounts of music data. Transfer learning showcases the proven effectiveness of pretrained backend models with a broad spectrum of downstream tasks, including auto-tagging and genre classification. However, MIR papers 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 learning over these models. Our research addresses this gap and evaluates the applicability of six pretrained backend models (MusicFM, Music2Vec, MERT, EncodecMAE, Jukebox, and MusiCNN) in the context of MRS. We assess their performance using three recommendation models: K-nearest neighbours (KNN), shallow neural network, and BERT4Rec. Our findings suggest that pretrained audio representations exhibit significant performance variability between traditional MIR tasks and MRS, 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.","url_abs":"https://arxiv.org/abs/2409.08987v1","url_pdf":"https://arxiv.org/pdf/2409.08987v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"comparative-analysis-of-pretrained-audio","repo_url":"https://github.com/Darel13712/pretrained-audio-representations","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"genre-classification","task_name":"Genre classification"},{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"music-information-retrieval","task_name":"Music Information Retrieval"},{"task_slug":"music-recommendation","task_name":"Music Recommendation"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dilated-convolution","method_name":"Dilated Convolution"},{"method_slug":"jukebox","method_name":"Jukebox"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"vq-vae","method_name":"VQ-VAE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}