{"id":1684,"date":"2014-11-03T17:27:03","date_gmt":"2014-11-03T16:27:03","guid":{"rendered":"http:\/\/www.meanboyfriend.com\/overdue_ideas\/?p=1684"},"modified":"2014-11-03T17:49:23","modified_gmt":"2014-11-03T16:49:23","slug":"digital-music-lab-analysing-big-music-data","status":"publish","type":"post","link":"http:\/\/www.meanboyfriend.com\/overdue_ideas\/2014\/11\/digital-music-lab-analysing-big-music-data\/","title":{"rendered":"Digital Music Lab: Analysing Big Music Data"},"content":{"rendered":"<p>This blog post was written during a presentation at the <a href=\"http:\/\/britishlibrary.typepad.co.uk\/digital-scholarship\/2014\/10\/british-library-labs-symposium-2014.html\">British Library Labs Symposium<\/a> in November 2014. It is likely full of errors and omissions having been written real-time.<\/p>\n<p>Adam Tovell, Digital Music Curator, British Library &amp; Daniel Wolff, City University<\/p>\n<p>Goal is to develop research methods and s\/w infrastructure for exploring and analysing large-scale music collection &amp; provide researchers and users with datasets and computational tool to analyse music audio, scores and metadata.<\/p>\n<ul>\n<li>Develop and evaluate music research methods for big data<\/li>\n<li>Develop and infrastructure (technical, insitutional, legal) for large-scale music analysis<\/li>\n<li>Develop tools for larg-scale computational musicology<\/li>\n<li>Use and produce Big Music Data sets<\/li>\n<\/ul>\n<p>It is possible to use software to analyse aspects of a musical recording. For example looking at:<br \/>\n* Visualisation<br \/>\n* Timings<br \/>\n* Intonation<br \/>\n* Dynamics<br \/>\n* Chord progressions<br \/>\n* Melody<\/p>\n<p>Derived data from s\/w analysis can be used to inform research questions.<\/p>\n<p>So far these approaches have been applied to small amounts of music<\/p>\n<p>Field of Music Information Retrieval apply the same techniques to larger bodies of music. These kinds of approaches are behind things like some music recommendation services.<\/p>\n<p>To bring together MIR techniques with musicology academic research approaches need a large body of recorded music &#8211; which is where the BL music collection comes in &#8211; enabling Large-scale Musicology. BL has over 400 different recording of Chopin&#8217;s Nocturne in E-flat major op.9, no.2 &#8211; you can ask questions like:<br \/>\n* how has performance changed over time?<br \/>\n* do performers influence each other?<br \/>\n* does place affect performance?<br \/>\n* etc.<\/p>\n<p>BL music collections have over 3 million unique recordings covering a very wide range of genres &#8211; popular, traditional, classical, with detailed metadata and a legal framework for making them available to people &#8211; sometimes online, and sometimes on-site.<\/p>\n<p><strong>Musicological Questions<\/strong><br \/>\n* Automatic analysis of scores<br \/>\n* structural analysis from audio<br \/>\n* analysing styles &amp; trends over time<br \/>\n* new similarity metrics (e.g. performance based)<br \/>\n* &#8230;<\/p>\n<p>Data sets currently being used:<br \/>\n* British Library &#8211; currently curating available music data collections from BL sound archive (currently done around 40k recordings)<br \/>\n* CHARM &#8211; 5000 copyright-free recordings + metadata<br \/>\n* ILikeMusic &#8211; commercial music library of 1.2M tracks<\/p>\n<p>Analysis results so far:<br \/>\n* ILikeMusic &#8211; chord detection<br \/>\n* CHARM &#8211; instrumentation analysis<br \/>\n* MIDI-scal transcription<br \/>\n* High-res transcription (create scores from recording)<br \/>\n* BL &#8211; key detection, + more<\/p>\n<p>Visualisations &#8211; available at http:\/\/dml.city.ac.uk<\/p>\n<p>Automatic Tagging &#8211; e.g. genre, style, period. To expensive to tag large datasets, automated classification challenging especially without &#8216;ground truth&#8217;.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>This blog post was written during a presentation at the British Library Labs Symposium in November 2014. It is likely full of errors and omissions having been written real-time. Adam Tovell, Digital Music Curator, British Library &amp; Daniel Wolff, City University Goal is to develop research methods and s\/w infrastructure for exploring and analysing large-scale [&hellip;]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[99],"class_list":["post-1684","post","type-post","status-publish","format-standard","hentry","category-uncategorized","tag-bl_labs"],"_links":{"self":[{"href":"http:\/\/www.meanboyfriend.com\/overdue_ideas\/wp-json\/wp\/v2\/posts\/1684","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/www.meanboyfriend.com\/overdue_ideas\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.meanboyfriend.com\/overdue_ideas\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.meanboyfriend.com\/overdue_ideas\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"http:\/\/www.meanboyfriend.com\/overdue_ideas\/wp-json\/wp\/v2\/comments?post=1684"}],"version-history":[{"count":4,"href":"http:\/\/www.meanboyfriend.com\/overdue_ideas\/wp-json\/wp\/v2\/posts\/1684\/revisions"}],"predecessor-version":[{"id":1702,"href":"http:\/\/www.meanboyfriend.com\/overdue_ideas\/wp-json\/wp\/v2\/posts\/1684\/revisions\/1702"}],"wp:attachment":[{"href":"http:\/\/www.meanboyfriend.com\/overdue_ideas\/wp-json\/wp\/v2\/media?parent=1684"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.meanboyfriend.com\/overdue_ideas\/wp-json\/wp\/v2\/categories?post=1684"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.meanboyfriend.com\/overdue_ideas\/wp-json\/wp\/v2\/tags?post=1684"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}