{"id":"https://openalex.org/W4372347365","doi":"https://doi.org/10.1109/icassp49357.2023.10096446","title":"Controllable Music Inpainting with Mixed-Level and Disentangled Representation","display_name":"Controllable Music Inpainting with Mixed-Level and Disentangled Representation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372347365","doi":"https://doi.org/10.1109/icassp49357.2023.10096446"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096446","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":"conference-paper","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/A5084457401","display_name":"Shiqi Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Shiqi Wei","raw_affiliation_strings":["Fudan University,School of Data Science","Music X Lab, New York University Shanghai","School of Data Science, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,School of Data Science","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Music X Lab, New York University Shanghai","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"School of Data Science, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420925","display_name":"Ziyu Wang","orcid":"https://orcid.org/0009-0000-4641-5082"},"institutions":[{"id":"https://openalex.org/I258800397","display_name":"New York University Shanghai","ror":"https://ror.org/02vpsdb40","country_code":"CN","type":"education","lineage":["https://openalex.org/I258800397","https://openalex.org/I57206974"]},{"id":"https://openalex.org/I350617331","display_name":"Shanghai Conservatory of Music","ror":"https://ror.org/012f6xc93","country_code":"CN","type":"education","lineage":["https://openalex.org/I350617331"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Ziyu Wang","raw_affiliation_strings":["New York University Shanghai,Music X Lab","Music X Lab, New York University Shanghai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University Shanghai,Music X Lab","institution_ids":["https://openalex.org/I258800397","https://openalex.org/I350617331"]},{"raw_affiliation_string":"Music X Lab, New York University Shanghai","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033363297","display_name":"Weiguo Gao","orcid":"https://orcid.org/0000-0003-0043-8320"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiguo Gao","raw_affiliation_strings":["Fudan University,School of Mathematical Sciences","School of Data Science, Fudan University","School of Mathematical Sciences, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,School of Mathematical Sciences","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Data Science, Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Mathematical Sciences, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027959958","display_name":"Gus Xia","orcid":"https://orcid.org/0000-0003-3629-906X"},"institutions":[{"id":"https://openalex.org/I258800397","display_name":"New York University Shanghai","ror":"https://ror.org/02vpsdb40","country_code":"CN","type":"education","lineage":["https://openalex.org/I258800397","https://openalex.org/I57206974"]},{"id":"https://openalex.org/I350617331","display_name":"Shanghai Conservatory of Music","ror":"https://ror.org/012f6xc93","country_code":"CN","type":"education","lineage":["https://openalex.org/I350617331"]},{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["AE","CN","US"],"is_corresponding":false,"raw_author_name":"Gus Xia","raw_affiliation_strings":["New York University Shanghai,Music X Lab","Mohamed Bin Zayed University of Artificial Intelligence","Music X Lab, New York University Shanghai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University Shanghai,Music X Lab","institution_ids":["https://openalex.org/I258800397","https://openalex.org/I350617331"]},{"raw_affiliation_string":"Mohamed Bin Zayed University of Artificial Intelligence","institution_ids":["https://openalex.org/I4210113480"]},{"raw_affiliation_string":"Music X Lab, New York University Shanghai","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9991999864578247,"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":0.9991999864578247,"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":0.9986000061035156,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.9794999957084656,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/inpainting","display_name":"Inpainting","score":0.8438352942466736},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.742144763469696},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5969504117965698},{"id":"https://openalex.org/keywords/melody","display_name":"Melody","score":0.5960152745246887},{"id":"https://openalex.org/keywords/musical-composition","display_name":"Musical composition","score":0.562009334564209},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5435753464698792},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.5394256114959717},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5344426035881042},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49351680278778076},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4810643196105957},{"id":"https://openalex.org/keywords/composition","display_name":"Composition (language)","score":0.4718575179576874},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4678643047809601},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.44039595127105713},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43621954321861267},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.23565560579299927},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12865614891052246},{"id":"https://openalex.org/keywords/music-education","display_name":"Music education","score":0.09935611486434937},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.09540614485740662},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.08911043405532837},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.08838635683059692}],"concepts":[{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.8438352942466736},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.742144763469696},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5969504117965698},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.5960152745246887},{"id":"https://openalex.org/C109568592","wikidata":"https://www.wikidata.org/wiki/Q207628","display_name":"Musical composition","level":3,"score":0.562009334564209},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5435753464698792},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.5394256114959717},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5344426035881042},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49351680278778076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4810643196105957},{"id":"https://openalex.org/C40231798","wikidata":"https://www.wikidata.org/wiki/Q1333743","display_name":"Composition (language)","level":2,"score":0.4718575179576874},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4678643047809601},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.44039595127105713},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43621954321861267},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.23565560579299927},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12865614891052246},{"id":"https://openalex.org/C13553968","wikidata":"https://www.wikidata.org/wiki/Q27908","display_name":"Music education","level":2,"score":0.09935611486434937},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.09540614485740662},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.08911043405532837},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.08838635683059692},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096446","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":[{"display_name":"Quality Education","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2753868141","https://openalex.org/W2896457183","https://openalex.org/W2948574791","https://openalex.org/W2954957095","https://openalex.org/W2963575853","https://openalex.org/W2997586082","https://openalex.org/W3005680577","https://openalex.org/W3015369675","https://openalex.org/W3034999214","https://openalex.org/W3047453285","https://openalex.org/W3049247973","https://openalex.org/W3049637270","https://openalex.org/W3097059217","https://openalex.org/W4224933341","https://openalex.org/W4225630208","https://openalex.org/W4385245566","https://openalex.org/W4394640856","https://openalex.org/W6631190155","https://openalex.org/W6730558285","https://openalex.org/W6739901393","https://openalex.org/W6744574196","https://openalex.org/W6755207826","https://openalex.org/W6763362620","https://openalex.org/W6765207196","https://openalex.org/W6774314701","https://openalex.org/W6781553146","https://openalex.org/W6781910838","https://openalex.org/W6782602824","https://openalex.org/W6784348365","https://openalex.org/W6800194770","https://openalex.org/W6810995942"],"related_works":["https://openalex.org/W2380775572","https://openalex.org/W2213520135","https://openalex.org/W2244018504","https://openalex.org/W4242046654","https://openalex.org/W3174923100","https://openalex.org/W3134074939","https://openalex.org/W4309969796","https://openalex.org/W2515310029","https://openalex.org/W2598521311","https://openalex.org/W104702370"],"abstract_inverted_index":{"Music":[0],"inpainting,":[1],"which":[2],"is":[3,15,83],"to":[4,84,96,134,159],"complete":[5],"the":[6,34,43,98,111,135,138,150],"missing":[7],"part":[8],"of":[9,19,37,47,89,101,110,114],"a":[10,28,102],"piece":[11],"given":[12],"some":[13],"context,":[14],"an":[16],"important":[17],"task":[18],"automated":[20],"music":[21,40,112,132],"generation.":[22],"In":[23],"this":[24],"study,":[25],"we":[26],"contribute":[27],"controllable":[29],"inpainting":[30],"model":[31,52,81,127,144],"by":[32],"combining":[33],"high":[35],"expressivity":[36],"mixed-level,":[38],"disentangled":[39,87],"representations":[41,88],"and":[42,63,65,77,137,152],"strong":[44],"predictive":[45],"power":[46],"masked":[48],"language":[49],"modeling.":[50],"The":[51,79],"enables":[53],"flexible":[54],"user":[55],"controls":[56],"over":[57],"both":[58],"time":[59,91],"scope":[60],"(inpainted":[61],"length":[62],"location)":[64],"semantic":[66,116],"features":[67,117],"that":[68,125,142,156],"composers":[69],"often":[70],"consider":[71],"during":[72],"composition,":[73],"say":[74],"rhythm":[75],"pattern":[76],"chords.":[78],"key":[80],"design":[82,94],"simultaneously":[85],"predict":[86],"different":[90,119],"ranges.":[92],"Such":[93],"aims":[95],"mirror":[97],"thought":[99],"process":[100],"professional":[103],"composer":[104],"who":[105],"can":[106,153],"take":[107],"into":[108],"account":[109],"flow":[113],"various":[115],"at":[118],"hierarchies":[120],"in":[121],"parallel.":[122],"Results":[123],"show":[124],"our":[126,143],"produces":[128],"much":[129,146],"higher":[130],"quality":[131],"compared":[133],"baseline,":[136],"subjective":[139],"evaluation":[140],"shows":[141],"generates":[145],"better":[147],"results":[148],"than":[149],"baseline":[151],"generate":[154],"melodies":[155],"are":[157],"similar":[158],"human":[160],"composition.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}
