We consider the problem of automatic vocal melody transcription: translating an audio recording of a sung melody into a musical score. While previous work has focused on finding the closest notes to the singer\u2019s tracked pitch, we instead seek to recover the melody the singer intended to sing. Often, the melody a singer intended to sing differs from what they actually sang; our hypothesis is that this occurs in a singer-specific way. For example, a given singer may often be flat in certain parts of her range, or another may have difficulty with certain intervals. We thus pursue methods for singer-specific training which use learning to combine different methods for pitch prediction. In our experiments with human subjects, we show that via a short training procedure we can learn a singer-specific pitch predictor and significantly improve transcription of intended pitch over other methods. For an average user, our method gives a 20 to 30 percent reduction in pitch classification errors with respect to a baseline method which is comparable to commercial voice transcription tools. For some users, we achieve even more dramatic reductions. Our best results come from a combination of singer-specific-learning with non-singer-specific feature selection. We also discuss the implications of our work for training more general control signals. We make our experimental data available to allow others to replicate or extend our results.<\/p>\n","protected":false},"excerpt":{"rendered":"
We consider the problem of automatic vocal melody transcription: translating an audio recording of a sung melody into a musical score. While previous work has focused on finding the closest notes to the singer\u2019s tracked pitch, we instead seek to recover the melody the singer intended to sing. Often, the melody a singer intended to […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13551],"msr-publication-type":[193716],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-318008","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-graphics-and-multimedia","msr-locale-en_us"],"msr_publishername":"AAAI Press","msr_edition":"AAAI'10 Proceedings of the Twenty-Fourth AAAI Conference on Artificial Intelligence","msr_affiliation":"","msr_published_date":"2010-07-11","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"960-966","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"318011","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","title":"aaai2010guillory","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/11\/AAAI2010Guillory.pdf","id":318011,"label_id":0}],"msr_related_uploader":"","msr_attachments":[],"msr-author-ordering":[{"type":"user_nicename","value":"dan","user_id":31522,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=dan"},{"type":"user_nicename","value":"sumitb","user_id":33754,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=sumitb"}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[],"msr_project":[327332,326648],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","related_content":{"projects":[{"ID":327332,"post_title":"Computational Tools for Music","post_name":"computational-tools-for-music","post_type":"msr-project","post_date":"2016-11-27 16:38:01","post_modified":"2021-05-09 12:03:16","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/computational-tools-for-music\/","post_excerpt":"Work in this area seeks to use computational tools to enable musical creativity, in particular to give novices a variety of new approaches to experience musical creativity.","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/327332"}]}},{"ID":326648,"post_title":"User-Specific Training for Vocal Melody Transcription","post_name":"user-specific-training-vocal-melody-transcription","post_type":"msr-project","post_date":"2016-11-23 14:01:47","post_modified":"2021-05-09 12:03:48","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/user-specific-training-vocal-melody-transcription\/","post_excerpt":"Overview This page contains supplementary material for our AAAI 2010 paper: \u201cUser-Specific Learning for Recognizing a Singer\u2019s Intended Pitch\u201d. The full citation for our paper follows, along with a link to the paper itself: Guillory A, Basu S, and Morris D. User-Specific Learning for Recognizing a Singer\u2019s Intended Pitch. Proceedings of AAAI 2010, July 2010. For more information about this work, contact Dan Morris (dan@microsoft.com) and Sumit Basu (sumitb@microsoft.com). Abstract We consider the problem of…","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/326648"}]}}]},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/318008","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":1,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/318008\/revisions"}],"predecessor-version":[{"id":524143,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/318008\/revisions\/524143"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=318008"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=318008"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=318008"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=318008"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=318008"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=318008"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=318008"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=318008"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=318008"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=318008"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=318008"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=318008"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=318008"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=318008"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=318008"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=318008"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}