{"id":2485,"date":"2024-11-07T10:38:00","date_gmt":"2024-11-07T09:38:00","guid":{"rendered":"https:\/\/reach.ircam.fr\/?p=2485"},"modified":"2024-12-09T10:46:32","modified_gmt":"2024-12-09T09:46:32","slug":"a-new-dataset-for-tag-and-text-based-controllable-symbolic-music-generation","status":"publish","type":"post","link":"https:\/\/reach.ircam.fr\/index.php\/2024\/11\/07\/a-new-dataset-for-tag-and-text-based-controllable-symbolic-music-generation\/","title":{"rendered":"A New Dataset for Tag- and Text-based Controllable Symbolic Music Generation"},"content":{"rendered":"\n<p>By Weihan Xu, Julian McAuley, Taylor Berg-Kirkpatrick, Shlomo Dubnov,<br>Hao-Wen Dong<\/p>\n\n\n\n<p><em>ISMIR Late-Breaking Demos<\/em>, Nov 2024, San Francisco, United States<\/p>\n\n\n\n<p><a href=\"https:\/\/hal.science\/hal-04770589v1\/file\/metascore_ismir2024_lbd.pdf\">Read full publication.<\/a><\/p>\n\n\n\n<p><strong>Abstract<\/strong>: Recent years have seen many audio-domain text-to-music generation models that rely on large amounts of text-audio pairs for training. However, similar attempts for symbolic-domain controllable music generation has been hindered due to the lack of a large-scale symbolic music dataset with extensive metadata and captions. In this paper, we introduce MetaScore, a novel dataset of 963K musical scores, along with extensive metadata collected from an online music forum. Additionally, we provide machine-generated captions for each score. With MetaScore, we explore controllable symbolic music generation and showcase the potential of our proposed dataset in enabling generating symbolic music using free-form natural language.<\/p>\n\n\n\n<p><a href=\"https:\/\/hal.science\/hal-04770589v1\/file\/metascore_ismir2024_lbd.pdf\">Read full publication.<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>By Weihan Xu, Julian McAuley, Taylor Berg-Kirkpatrick, Shlomo Dubnov,Hao-Wen Dong ISMIR Late-Breaking Demos, Nov 2024, San Francisco, United States Read full publication. Abstract: Recent years have seen many audio-domain text-to-music generation models that rely on large amounts of text-audio pairs for training. However, similar attempts for symbolic-domain controllable music generation has been hindered due to [&hellip;]<\/p>\n","protected":false},"author":3,"featured_media":2486,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"footnotes":""},"categories":[46],"tags":[],"class_list":["post-2485","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-publications-research"],"aioseo_notices":[],"blog_post_layout_featured_media_urls":{"thumbnail":["https:\/\/reach.ircam.fr\/wp-content\/uploads\/2024\/12\/Screenshot-2024-12-09-104434-150x150.png",150,150,true],"full":["https:\/\/reach.ircam.fr\/wp-content\/uploads\/2024\/12\/Screenshot-2024-12-09-104434.png",1374,583,false]},"categories_names":{"46":{"name":"Publications","link":"https:\/\/reach.ircam.fr\/index.php\/category\/research\/publications-research\/"}},"tags_names":[],"comments_number":"0","wpmagazine_modules_lite_featured_media_urls":{"thumbnail":["https:\/\/reach.ircam.fr\/wp-content\/uploads\/2024\/12\/Screenshot-2024-12-09-104434-150x150.png",150,150,true],"cvmm-medium":["https:\/\/reach.ircam.fr\/wp-content\/uploads\/2024\/12\/Screenshot-2024-12-09-104434-300x300.png",300,300,true],"cvmm-medium-plus":["https:\/\/reach.ircam.fr\/wp-content\/uploads\/2024\/12\/Screenshot-2024-12-09-104434-305x207.png",305,207,true],"cvmm-portrait":["https:\/\/reach.ircam.fr\/wp-content\/uploads\/2024\/12\/Screenshot-2024-12-09-104434-400x583.png",400,583,true],"cvmm-medium-square":["https:\/\/reach.ircam.fr\/wp-content\/uploads\/2024\/12\/Screenshot-2024-12-09-104434-600x583.png",600,583,true],"cvmm-large":["https:\/\/reach.ircam.fr\/wp-content\/uploads\/2024\/12\/Screenshot-2024-12-09-104434-1024x583.png",1024,583,true],"cvmm-small":["https:\/\/reach.ircam.fr\/wp-content\/uploads\/2024\/12\/Screenshot-2024-12-09-104434-130x95.png",130,95,true],"full":["https:\/\/reach.ircam.fr\/wp-content\/uploads\/2024\/12\/Screenshot-2024-12-09-104434.png",1374,583,false]},"_links":{"self":[{"href":"https:\/\/reach.ircam.fr\/index.php\/wp-json\/wp\/v2\/posts\/2485","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/reach.ircam.fr\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/reach.ircam.fr\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/reach.ircam.fr\/index.php\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/reach.ircam.fr\/index.php\/wp-json\/wp\/v2\/comments?post=2485"}],"version-history":[{"count":1,"href":"https:\/\/reach.ircam.fr\/index.php\/wp-json\/wp\/v2\/posts\/2485\/revisions"}],"predecessor-version":[{"id":2487,"href":"https:\/\/reach.ircam.fr\/index.php\/wp-json\/wp\/v2\/posts\/2485\/revisions\/2487"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/reach.ircam.fr\/index.php\/wp-json\/wp\/v2\/media\/2486"}],"wp:attachment":[{"href":"https:\/\/reach.ircam.fr\/index.php\/wp-json\/wp\/v2\/media?parent=2485"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/reach.ircam.fr\/index.php\/wp-json\/wp\/v2\/categories?post=2485"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/reach.ircam.fr\/index.php\/wp-json\/wp\/v2\/tags?post=2485"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}