{"id":"https://openalex.org/W6930636488","doi":"https://doi.org/10.5281/zenodo.14877427","title":"Do Music Generation Models Encode Music Theory?","display_name":"Do Music Generation Models Encode Music Theory?","publication_year":2024,"publication_date":"2024-11-10","ids":{"openalex":"https://openalex.org/W6930636488","doi":"https://doi.org/10.5281/zenodo.14877427"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14877427","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877427","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.14877427","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Megan Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Megan Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Michael Freeman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Freeman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Chris Donahue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chris Donahue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Chen Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Sun","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":1,"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/T12648","display_name":"Academic Writing and Publishing","score":0.06310000270605087,"subfield":{"id":"https://openalex.org/subfields/1207","display_name":"History and Philosophy of Science"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12648","display_name":"Academic Writing and Publishing","score":0.06310000270605087,"subfield":{"id":"https://openalex.org/subfields/1207","display_name":"History and Philosophy of Science"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12836","display_name":"History and Developments in Astronomy","score":0.036400001496076584,"subfield":{"id":"https://openalex.org/subfields/3103","display_name":"Astronomy and Astrophysics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13495","display_name":"Biographical and Historical Analysis","score":0.02449999935925007,"subfield":{"id":"https://openalex.org/subfields/1202","display_name":"History"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/chord","display_name":"Chord (peer-to-peer)","score":0.7973999977111816},{"id":"https://openalex.org/keywords/music-theory","display_name":"Music theory","score":0.6179999709129333},{"id":"https://openalex.org/keywords/pop-music-automation","display_name":"Pop music automation","score":0.6111000180244446},{"id":"https://openalex.org/keywords/midi","display_name":"MIDI","score":0.5601999759674072},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.5339000225067139},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5141000151634216},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.4968999922275543},{"id":"https://openalex.org/keywords/music-psychology","display_name":"Music psychology","score":0.45660001039505005},{"id":"https://openalex.org/keywords/musical-composition","display_name":"Musical composition","score":0.4535999894142151}],"concepts":[{"id":"https://openalex.org/C194147245","wikidata":"https://www.wikidata.org/wiki/Q1076368","display_name":"Chord (peer-to-peer)","level":2,"score":0.7973999977111816},{"id":"https://openalex.org/C143857728","wikidata":"https://www.wikidata.org/wiki/Q193544","display_name":"Music theory","level":3,"score":0.6179999709129333},{"id":"https://openalex.org/C73520026","wikidata":"https://www.wikidata.org/wiki/Q7229091","display_name":"Pop music automation","level":4,"score":0.6111000180244446},{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.5601999759674072},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.5339000225067139},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5224000215530396},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5141000151634216},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.4968999922275543},{"id":"https://openalex.org/C146902061","wikidata":"https://www.wikidata.org/wiki/Q476590","display_name":"Music psychology","level":3,"score":0.45660001039505005},{"id":"https://openalex.org/C109568592","wikidata":"https://www.wikidata.org/wiki/Q207628","display_name":"Musical composition","level":3,"score":0.4535999894142151},{"id":"https://openalex.org/C113194728","wikidata":"https://www.wikidata.org/wiki/Q4130159","display_name":"Musicality","level":3,"score":0.4032000005245209},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.4009000062942505},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.38519999384880066},{"id":"https://openalex.org/C10864753","wikidata":"https://www.wikidata.org/wiki/Q4353948","display_name":"Music and emotion","level":4,"score":0.37439998984336853},{"id":"https://openalex.org/C114611597","wikidata":"https://www.wikidata.org/wiki/Q373342","display_name":"Popular music","level":2,"score":0.37290000915527344},{"id":"https://openalex.org/C13553968","wikidata":"https://www.wikidata.org/wiki/Q27908","display_name":"Music education","level":2,"score":0.34619998931884766},{"id":"https://openalex.org/C2779732396","wikidata":"https://www.wikidata.org/wiki/Q2207288","display_name":"Craft","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33250001072883606},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3294999897480011},{"id":"https://openalex.org/C154233639","wikidata":"https://www.wikidata.org/wiki/Q164204","display_name":"Musicology","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.2800000011920929},{"id":"https://openalex.org/C178300618","wikidata":"https://www.wikidata.org/wiki/Q1898509","display_name":"Extant taxon","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C2781291010","wikidata":"https://www.wikidata.org/wiki/Q178580","display_name":"Period (music)","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C508278066","wikidata":"https://www.wikidata.org/wiki/Q2289786","display_name":"Programming","level":4,"score":0.26649999618530273},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.25839999318122864},{"id":"https://openalex.org/C535889608","wikidata":"https://www.wikidata.org/wiki/Q638","display_name":"Music","level":3,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14877427","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877427","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.14877427","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877427","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Music":[0],"foundation":[1,152,179],"models":[2,77,153,180],"possess":[3],"impressive":[4],"music":[5,18,48,56,75,79,102,122,147,151,173],"generation":[6,49,76],"capabilities.":[7],"When":[8],"people":[9],"compose":[10],"music,":[11],"they":[12,161,187],"may":[13],"infuse":[14],"their":[15,20,166],"understanding":[16],"of":[17,47,64,126],"into":[19],"work,":[21],"by":[22,191],"using":[23],"notes":[24],"and":[25,34,120,134,155,157,181,194],"intervals":[26],"to":[27,31,36,143,185],"craft":[28],"melodies,":[29],"chords":[30],"build":[32],"progressions,":[33],"tempo":[35],"create":[37],"a":[38,117,141],"rhythmic":[39],"feel.":[40],"To":[41],"what":[42],"extent":[43],"is":[44],"this":[45],"true":[46],"models?":[50,66],"More":[51],"specifically,":[52],"are":[53,94,176,188],"fundamental":[54],"Western":[55],"theory":[57,103,123,148,174],"concepts":[58,104,149,164,175],"observable":[59],"within":[60,96,165,178],"the":[61,183],"\"inner":[62],"workings\"":[63],"these":[65,97,146,163],"Recent":[67],"work":[68],"proposed":[69],"leveraging":[70],"latent":[71],"audio":[72,121],"representations":[73],"from":[74],"towards":[78],"information":[80],"retrieval":[81],"tasks":[82],"(e.g.":[83,105],"genre":[84],"classification,":[85],"emotion":[86],"recognition),":[87],"which":[88,186],"suggests":[89],"that":[90,172,182],"high-level":[91],"musical":[92],"characteristics":[93],"encoded":[95],"models.":[98],"However,":[99],"probing":[100],"individual":[101],"tempo,":[106],"pitch":[107],"class,":[108],"chord":[109,135],"quality)":[110],"remains":[111],"under-explored.":[112],"Thus,":[113],"we":[114],"introduce":[115],"SynTheory,":[116],"synthetic":[118],"MIDI":[119],"dataset,":[124],"consisting":[125],"tempos,":[127],"time":[128],"signatures,":[129],"notes,":[130],"intervals,":[131],"scales,":[132],"chords,":[133],"progressions":[136],"concepts.":[137],"We":[138],"then":[139],"propose":[140],"framework":[142],"probe":[144],"for":[145],"in":[150],"(Jukebox":[154],"MusicGen)":[156],"assess":[158],"how":[159],"strongly":[160],"encode":[162],"internal":[167],"representations.":[168],"Our":[169],"findings":[170],"suggest":[171],"discernible":[177],"degree":[184],"detectable":[189],"varies":[190],"model":[192],"size":[193],"layer.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}
