{"id":"https://openalex.org/W4391094433","doi":"https://doi.org/10.1109/bigdata59044.2023.10386311","title":"Equipping Pretrained Unconditional Music Transformers with Instrument and Genre Controls","display_name":"Equipping Pretrained Unconditional Music Transformers with Instrument and Genre Controls","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4391094433","doi":"https://doi.org/10.1109/bigdata59044.2023.10386311"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata59044.2023.10386311","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata59044.2023.10386311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","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/A5104201808","display_name":"Weihan Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weihan Xu","raw_affiliation_strings":["Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021827617","display_name":"Julian McAuley","orcid":"https://orcid.org/0000-0003-0955-7588"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julian McAuley","raw_affiliation_strings":["University of California San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042278809","display_name":"Shlomo Dubnov","orcid":"https://orcid.org/0000-0003-0222-1125"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shlomo Dubnov","raw_affiliation_strings":["University of California San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028026494","display_name":"Hao\u2010Wen Dong","orcid":"https://orcid.org/0000-0002-1020-0001"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao-Wen Dong","raw_affiliation_strings":["University of California San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":"4512","last_page":"4517"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9990000128746033,"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":0.9879999756813049,"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/transformer","display_name":"Transformer","score":0.7169936895370483},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5692477822303772},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43164175748825073},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3391529321670532},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33065059781074524},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.24392321705818176},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.24039041996002197},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.062019169330596924}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7169936895370483},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5692477822303772},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43164175748825073},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3391529321670532},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33065059781074524},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.24392321705818176},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.24039041996002197},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.062019169330596924}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata59044.2023.10386311","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata59044.2023.10386311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321408","display_name":"Ministry of Education","ror":"https://ror.org/01p262204"},{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2475687244","https://openalex.org/W2752134738","https://openalex.org/W2772474126","https://openalex.org/W2775473773","https://openalex.org/W2908510526","https://openalex.org/W2962941684","https://openalex.org/W3047386385","https://openalex.org/W3047453285","https://openalex.org/W3049247973","https://openalex.org/W3092850823","https://openalex.org/W3092879656","https://openalex.org/W3124507227","https://openalex.org/W4226351384","https://openalex.org/W4287643030","https://openalex.org/W4297097022","https://openalex.org/W4307008216","https://openalex.org/W4372259826","https://openalex.org/W4377130979","https://openalex.org/W4379251846","https://openalex.org/W4390871777","https://openalex.org/W4393178509","https://openalex.org/W6744222783","https://openalex.org/W6746528227","https://openalex.org/W6752622914","https://openalex.org/W6757817989","https://openalex.org/W6781423933","https://openalex.org/W6781553146","https://openalex.org/W6781910838","https://openalex.org/W6783970415","https://openalex.org/W6811493774","https://openalex.org/W6846234567","https://openalex.org/W6851847159","https://openalex.org/W6852997251","https://openalex.org/W6853533739"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0,96],"\u201cpretraining-and-finetuning\u201d":[1],"paradigm":[2,26],"has":[3],"become":[4],"a":[5,47,59,114],"norm":[6],"for":[7,27],"training":[8],"domain-specific":[9],"models":[10],"in":[11,126],"natural":[12],"language":[13],"processing":[14],"and":[15,72,90,111,132],"computer":[16],"vision.":[17],"In":[18,113],"this":[19,25,64],"work,":[20],"we":[21],"aim":[22],"to":[23,62],"examine":[24],"symbolic":[28,36],"music":[29,37,67,107],"generation":[30],"through":[31],"leveraging":[32],"the":[33,41,77,101,118,122],"largest":[34],"ever":[35],"dataset":[38],"sourced":[39],"from":[40],"MuseScore":[42],"forum.":[43],"We":[44,56],"first":[45],"pretrain":[46],"large":[48],"unconditional":[49,66],"transformer":[50,68],"model":[51,69,78,103,120,125],"using":[52],"1.5":[53],"million":[54],"songs.":[55],"then":[57],"propose":[58],"simple":[60],"technique":[61],"equip":[63],"pretrained":[65,123],"with":[70,79,108],"instrument":[71],"genre":[73],"controls":[74],"by":[75],"finetuning":[76],"additional":[80],"control":[81],"tokens.":[82],"Our":[83],"proposed":[84,102,119],"representation":[85],"offers":[86],"improved":[87],"high-level":[88],"controllability":[89],"expressiveness":[91],"against":[92],"two":[93],"existing":[94],"representations.":[95],"experimental":[97],"results":[98],"show":[99],"that":[100],"can":[104],"successfully":[105],"generate":[106],"user-specified":[109],"instruments":[110],"genre.":[112],"subjective":[115],"listening":[116],"test,":[117],"outperforms":[121],"baseline":[124],"terms":[127],"of":[128],"coherence,":[129],"harmony,":[130],"arrangement":[131],"overall":[133],"quality.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}