{"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/multi-label-music-genre-classification-from","title":"Multi-label Music Genre Classification from Audio, Text, and Images Using Deep Features","arxiv_id":"1707.04916","date":"2017-07-16","proceeding":null,"authors":["Oramas Sergio","Nieto Oriol","Barbieri Francesco","Serra Xavier"],"abstract":"Music genres allow to categorize musical items that share common\ncharacteristics. Although these categories are not mutually exclusive, most\nrelated research is traditionally focused on classifying tracks into a single\nclass. Furthermore, these categories (e.g., Pop, Rock) tend to be too broad for\ncertain applications. In this work we aim to expand this task by categorizing\nmusical items into multiple and fine-grained labels, using three different data\nmodalities: audio, text, and images. To this end we present MuMu, a new dataset\nof more than 31k albums classified into 250 genre classes. For every album we\nhave collected the cover image, text reviews, and audio tracks. Additionally,\nwe propose an approach for multi-label genre classification based on the\ncombination of feature embeddings learned with state-of-the-art deep learning\nmethodologies. Experiments show major differences between modalities, which not\nonly introduce new baselines for multi-label genre classification, but also\nsuggest that combining them yields improved results.","url_abs":"http://arxiv.org/abs/1707.04916v1","url_pdf":"http://arxiv.org/pdf/1707.04916v1.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":"multi-label-music-genre-classification-from","repo_url":"https://github.com/sergiooramas/tartarus","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"genre-classification","task_name":"Genre classification"},{"task_slug":"music-genre-classification","task_name":"Music Genre Classification"}],"methods":[],"datasets_introduced":[{"slug":"mumu","name":"MuMu","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/genre-classification-on-fma","task":"Genre classification","dataset":"FMA","model":"cnn","rank_in_archive_order":1,"of":1,"metrics":{"CNN":"855"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1707.04916","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}