{"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/onsets-and-frames-dual-objective-piano","title":"Onsets and Frames: Dual-Objective Piano Transcription","arxiv_id":"1710.11153","date":"2017-10-30","proceeding":null,"authors":["Curtis Hawthorne","Erich Elsen","Jialin Song","Adam Roberts","Ian Simon","Colin Raffel","Jesse Engel","Sageev Oore","Douglas Eck"],"abstract":"We advance the state of the art in polyphonic piano music transcription by\nusing a deep convolutional and recurrent neural network which is trained to\njointly predict onsets and frames. Our model predicts pitch onset events and\nthen uses those predictions to condition framewise pitch predictions. During\ninference, we restrict the predictions from the framewise detector by not\nallowing a new note to start unless the onset detector also agrees that an\nonset for that pitch is present in the frame. We focus on improving onsets and\noffsets together instead of either in isolation as we believe this correlates\nbetter with human musical perception. Our approach results in over a 100%\nrelative improvement in note F1 score (with offsets) on the MAPS dataset.\nFurthermore, we extend the model to predict relative velocities of normalized\naudio which results in more natural-sounding transcriptions.","url_abs":"http://arxiv.org/abs/1710.11153v2","url_pdf":"http://arxiv.org/pdf/1710.11153v2.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":"onsets-and-frames-dual-objective-piano","repo_url":"https://github.com/BShakhovsky/PolyphonicPianoTranscription","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"onsets-and-frames-dual-objective-piano","repo_url":"https://github.com/lucas-dunker/stem-separator-amt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"music-transcription","task_name":"Music Transcription"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1710.11153","atlas_url":"https://app.syntology.ai/?focus=1710.11153","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}