{"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/automatic-tagging-using-deep-convolutional","title":"Automatic tagging using deep convolutional neural networks","arxiv_id":"1606.00298","date":"2016-06-01","proceeding":null,"authors":["Keunwoo Choi","George Fazekas","Mark Sandler"],"abstract":"We present a content-based automatic music tagging algorithm using fully\nconvolutional neural networks (FCNs). We evaluate different architectures\nconsisting of 2D convolutional layers and subsampling layers only. In the\nexperiments, we measure the AUC-ROC scores of the architectures with different\ncomplexities and input types using the MagnaTagATune dataset, where a 4-layer\narchitecture shows state-of-the-art performance with mel-spectrogram input.\nFurthermore, we evaluated the performances of the architectures with varying\nthe number of layers on a larger dataset (Million Song Dataset), and found that\ndeeper models outperformed the 4-layer architecture. The experiments show that\nmel-spectrogram is an effective time-frequency representation for automatic\ntagging and that more complex models benefit from more training data.","url_abs":"http://arxiv.org/abs/1606.00298v1","url_pdf":"http://arxiv.org/pdf/1606.00298v1.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":"automatic-tagging-using-deep-convolutional","repo_url":"https://github.com/Dohppak/Music_DeepEmbedding_Extractor","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"automatic-tagging-using-deep-convolutional","repo_url":"https://github.com/HephaestusProject/pytorch-FCN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"automatic-tagging-using-deep-convolutional","repo_url":"https://github.com/annahung31/moodtheme-tagging","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"automatic-tagging-using-deep-convolutional","repo_url":"https://github.com/contextemi/context_emi_on_azure","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"automatic-tagging-using-deep-convolutional","repo_url":"https://github.com/eatsleepraverepeat/emusic_net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"automatic-tagging-using-deep-convolutional","repo_url":"https://github.com/keunwoochoi/MSD_split_for_tagging","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"automatic-tagging-using-deep-convolutional","repo_url":"https://github.com/keunwoochoi/music-auto_tagging-keras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"automatic-tagging-using-deep-convolutional","repo_url":"https://github.com/labcontext/context-cloud-on-azure","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"automatic-tagging-using-deep-convolutional","repo_url":"https://github.com/maysa96/music_tagger_mine2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"automatic-tagging-using-deep-convolutional","repo_url":"https://github.com/vvnkumar1965/chitti","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"automatic-tagging-using-deep-convolutional","repo_url":"https://github.com/mindspore-ai/models/tree/master/research/audio/fcn-4","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"music-tagging","task_name":"Music Tagging"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1606.00298","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}