{"id":"https://openalex.org/W7108699899","doi":"https://doi.org/10.5281/zenodo.17811354","title":"Generating Symbolic Music from Natural Language Prompts using an LLM-Enhanced Dataset","display_name":"Generating Symbolic Music from Natural Language Prompts using an LLM-Enhanced Dataset","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7108699899","doi":"https://doi.org/10.5281/zenodo.17811354"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.17811354","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811354","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"type":"conference-paper","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.17811354","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Weihan Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weihan Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Julian McAuley","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Julian McAuley","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Taylor Berg-Kirkpatrick","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Taylor Berg-Kirkpatrick","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Shlomo Dubnov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shlomo Dubnov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Hao-Wen Dong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao-Wen Dong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.5884000062942505,"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":0.5884000062942505,"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":0.2167000025510788,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.016100000590085983,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/natural-language","display_name":"Natural language","score":0.6108999848365784},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5048999786376953},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.49390000104904175},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48030000925064087},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.47119998931884766},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.4503999948501587},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4221999943256378},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.4077000021934509}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.782800018787384},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.6108999848365784},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5385000109672546},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5048999786376953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5001999735832214},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.49390000104904175},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48030000925064087},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.47119998931884766},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.4503999948501587},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4221999943256378},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.4077000021934509},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3978999853134155},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39309999346733093},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.3702000081539154},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.3544999957084656},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.2971999943256378},{"id":"https://openalex.org/C73520026","wikidata":"https://www.wikidata.org/wiki/Q7229091","display_name":"Pop music automation","level":4,"score":0.29440000653266907},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.27880001068115234},{"id":"https://openalex.org/C174252522","wikidata":"https://www.wikidata.org/wiki/Q3816772","display_name":"Natural language user interface","level":3,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.17811354","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811354","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.5281/zenodo.17811354","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811354","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8115841150283813}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2],"seen":[3],"many":[4],"audio-domain":[5],"text-to-music":[6,73,150,157,180],"generation":[7,23,101],"models":[8,153,174],"that":[9,103,132,146],"rely":[10],"on":[11],"large":[12,79],"amounts":[13],"of":[14,32,53,115,137],"text-audio":[15],"pairs":[16],"for":[17],"training.":[18],"However,":[19],"symbolic-domain":[20],"controllable":[21],"music":[22,36,69,100,108,123],"has":[24],"lagged":[25],"behind":[26],"partly":[27],"due":[28],"to":[29,83,105,195],"the":[30,90,93,110,148,179,188],"lack":[31],"a":[33,49,77,98,129,134,155,160,164,183],"large-scale":[34],"symbolic":[35,107],"dataset":[37,51],"with":[38,58],"extensive":[39],"metadata":[40],"and":[41,120,151],"captions.":[42],"In":[43,125],"this":[44],"work,":[45],"we":[46,75,96,127],"present":[47],"MetaScore,":[48,95],"new":[50],"consisting":[52],"963K":[54],"musical":[55],"scores":[56],"paired":[57],"rich":[59],"metadata,":[60],"including":[61],"free-form":[62,122,170,197],"user-annotated":[63],"tags,":[64],"collected":[65],"from":[66,89,109],"an":[67],"online":[68],"forum.":[70],"To":[71],"approach":[72],"generation,":[74],"leverage":[76],"pretrained":[78],"language":[80,87,199],"model":[81,102,158],"(LLM)":[82],"generate":[84,106],"pseudo":[85,111],"natural":[86,185,198],"captions":[88],"metadata.":[91],"With":[92],"LLM-enhanced":[94],"train":[97,128],"text-conditioned":[99],"learns":[104],"captions,":[112],"allowing":[113],"control":[114],"instruments,":[116],"genre,":[117],"composer,":[118],"complexity":[119],"other":[121],"descriptors.":[124],"addition,":[126],"tag-conditioned":[130],"system":[131,181],"supports":[133,169],"predefined":[135],"set":[136],"tags":[138],"available":[139],"in":[140,159],"MetaScore.":[141],"Our":[142],"experimental":[143],"results":[144],"show":[145],"both":[147],"proposed":[149],"tags-to-music":[152,189],"outperform":[154],"baseline":[156],"listening":[161],"test.":[162],"While":[163],"concurrent":[165],"work":[166],"Text2MIDI":[167],"also":[168],"text":[171],"input,":[172],"our":[173],"achieve":[175],"comparable":[176],"performance.":[177],"Moreover,":[178],"offers":[182],"more":[184],"interface":[186],"than":[187],"model,":[190],"as":[191],"it":[192],"allows":[193],"users":[194],"provide":[196],"prompts.":[200]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}