{"id":"https://openalex.org/W4375869480","doi":"https://doi.org/10.1109/icassp49357.2023.10095935","title":"Diffroll: Diffusion-Based Generative Music Transcription with Unsupervised Pretraining Capability","display_name":"Diffroll: Diffusion-Based Generative Music Transcription with Unsupervised Pretraining Capability","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869480","doi":"https://doi.org/10.1109/icassp49357.2023.10095935"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095935","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095935","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069612434","display_name":"Kin Wai Cheuk","orcid":"https://orcid.org/0000-0003-3213-8242"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Kin Wai Cheuk","raw_affiliation_strings":["Singapore University of Technology and Design,Singapore","Singapore University of Technology and Design, Singapore","Agency for Science, Technology and Research, Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design,Singapore","institution_ids":["https://openalex.org/I152815399"]},{"raw_affiliation_string":"Singapore University of Technology and Design, Singapore","institution_ids":["https://openalex.org/I152815399"]},{"raw_affiliation_string":"Agency for Science, Technology and Research, Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010892279","display_name":"Ryosuke Sawata","orcid":"https://orcid.org/0000-0003-3230-4335"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ryosuke Sawata","raw_affiliation_strings":["Sony Group Corporation,Tokyo,Japan","Sony Group Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Tokyo,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034556374","display_name":"Toshimitsu Uesaka","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Toshimitsu Uesaka","raw_affiliation_strings":["Sony Group Corporation,Tokyo,Japan","Sony Group Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Tokyo,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031225419","display_name":"Naoki Murata","orcid":"https://orcid.org/0000-0001-7418-5173"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naoki Murata","raw_affiliation_strings":["Sony Group Corporation,Tokyo,Japan","Sony Group Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Tokyo,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101589290","display_name":"Naoya Takahashi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naoya Takahashi","raw_affiliation_strings":["Sony Group Corporation,Tokyo,Japan","Sony Group Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Tokyo,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104117184","display_name":"Shusuke Takahashi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shusuke Takahashi","raw_affiliation_strings":["Sony Group Corporation,Tokyo,Japan","Sony Group Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Tokyo,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069548004","display_name":"Dorien Herremans","orcid":"https://orcid.org/0000-0001-8607-1640"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dorien Herremans","raw_affiliation_strings":["Singapore University of Technology and Design,Singapore","Singapore University of Technology and Design, Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design,Singapore","institution_ids":["https://openalex.org/I152815399"]},{"raw_affiliation_string":"Singapore University of Technology and Design, Singapore","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088754502","display_name":"Yuki Mitsufuji","orcid":"https://orcid.org/0000-0002-6806-6140"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuki Mitsufuji","raw_affiliation_strings":["Sony Group Corporation,Tokyo,Japan","Sony Group Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Tokyo,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Tokyo, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5069612434"],"corresponding_institution_ids":["https://openalex.org/I115228651","https://openalex.org/I152815399"],"apc_list":null,"apc_paid":null,"fwci":2.649,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.90798122,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8664450645446777},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7275331020355225},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7084743976593018},{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.708267331123352},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5976477861404419},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5782144665718079},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5665844082832336},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5403019189834595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5308704376220703},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5295922160148621},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4507637917995453},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.11446049809455872}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8664450645446777},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7275331020355225},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7084743976593018},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.708267331123352},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5976477861404419},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5782144665718079},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5665844082832336},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5403019189834595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5308704376220703},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5295922160148621},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4507637917995453},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11446049809455872},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095935","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095935","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.75,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W1532956126","https://openalex.org/W2096354165","https://openalex.org/W2104298926","https://openalex.org/W2129069237","https://openalex.org/W2198584637","https://openalex.org/W2295460171","https://openalex.org/W2566755135","https://openalex.org/W2772474126","https://openalex.org/W2910577860","https://openalex.org/W2950547518","https://openalex.org/W2991439390","https://openalex.org/W2998160449","https://openalex.org/W3036167779","https://openalex.org/W3091273176","https://openalex.org/W3121370741","https://openalex.org/W3123097577","https://openalex.org/W3129576130","https://openalex.org/W3129651364","https://openalex.org/W3160787318","https://openalex.org/W3200791433","https://openalex.org/W3206146520","https://openalex.org/W3209419355","https://openalex.org/W3212589040","https://openalex.org/W4221159371","https://openalex.org/W4223440379","https://openalex.org/W4225113803","https://openalex.org/W4225759859","https://openalex.org/W4282913091","https://openalex.org/W4283360488","https://openalex.org/W4287250916","https://openalex.org/W4288099666","https://openalex.org/W4293775315","https://openalex.org/W4300425011","https://openalex.org/W4320028097","https://openalex.org/W4322615164","https://openalex.org/W6631871913","https://openalex.org/W6697000175","https://openalex.org/W6731203071","https://openalex.org/W6745851314","https://openalex.org/W6755182157","https://openalex.org/W6758675244","https://openalex.org/W6763354517","https://openalex.org/W6772982332","https://openalex.org/W6779823529","https://openalex.org/W6782760101","https://openalex.org/W6783182287","https://openalex.org/W6783713337","https://openalex.org/W6790978476","https://openalex.org/W6793578827","https://openalex.org/W6803088475","https://openalex.org/W6803577363","https://openalex.org/W6809814386","https://openalex.org/W6809884996","https://openalex.org/W6809940947","https://openalex.org/W6810809420","https://openalex.org/W6839133533","https://openalex.org/W6839196917","https://openalex.org/W6840815571","https://openalex.org/W6844872470","https://openalex.org/W6846575651"],"related_works":["https://openalex.org/W2987280934","https://openalex.org/W2093104230","https://openalex.org/W4390874210","https://openalex.org/W4384918963","https://openalex.org/W4365211920","https://openalex.org/W2128027845","https://openalex.org/W4386184937","https://openalex.org/W3014948380","https://openalex.org/W1493875009","https://openalex.org/W2751624083"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,36,46],"propose":[4],"a":[5,21,41],"novel":[6],"generative":[7,43],"approach,":[8],"DiffRoll,":[9],"to":[10,30,50,69,77,85],"tackle":[11],"automatic":[12],"music":[13],"transcription":[14],"(AMT).":[15],"Instead":[16],"of":[17,38],"treating":[18],"AMT":[19,65],"as":[20,40],"discriminative":[22,104],"task":[23,44],"in":[24],"which":[25],"the":[26,78],"model":[27,49],"is":[28,82],"trained":[29,87],"convert":[31],"spectrograms":[32],"into":[33],"piano":[34,54,93],"rolls,":[35],"think":[37],"it":[39,118],"conditional":[42],"where":[45,91],"train":[47],"our":[48,112],"generate":[51,71],"realistic":[52],"looking":[53],"rolls":[55,94],"from":[56],"pure":[57],"Gaussian":[58],"noise":[59],"conditioned":[60],"on":[61,88],"spectrograms.":[62],"This":[63],"new":[64],"formulation":[66],"enables":[67],"DiffRoll":[68,81,101],"transcribe,":[70],"and":[72,111,127],"even":[73],"inpaint":[74],"music.":[75],"Due":[76],"classifier-free":[79],"nature,":[80],"also":[83,115],"able":[84],"be":[86],"unpaired":[89],"datasets":[90],"only":[92],"are":[95,129],"available.":[96],"Our":[97],"experiments":[98],"show":[99],"that":[100,117],"outperforms":[102,119],"its":[103],"counterpart":[105],"by":[106,123],"19":[107],"percentage":[108],"points":[109],"(ppt.)":[110],"ablation":[113],"studies":[114],"indicate":[116],"similar":[120],"existing":[121],"methods":[122],"4.8":[124],"ppt.Source":[125],"code":[126],"demonstration":[128],"available":[130],"at":[131],"https://sony.github.io/DiffRoll/.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
