{"id":"https://openalex.org/W6912196593","doi":"https://doi.org/10.5281/zenodo.14877299","title":"Variation Transformer: New Datasets, Models, and Comparative Evaluation for Symbolic Music Variation Generation","display_name":"Variation Transformer: New Datasets, Models, and Comparative Evaluation for Symbolic Music Variation Generation","publication_year":2024,"publication_date":"2024-11-10","ids":{"openalex":"https://openalex.org/W6912196593","doi":"https://doi.org/10.5281/zenodo.14877299"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14877299","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877299","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":""},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.14877299","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Chenyu Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chenyu Gao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Federico Reuben","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Federico Reuben","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Tom Collins","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tom Collins","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35894721,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.5898000001907349,"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"}},"topics":[{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.5898000001907349,"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/T11309","display_name":"Music and Audio Processing","score":0.36970001459121704,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.01679999940097332,"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/variation","display_name":"Variation (astronomy)","score":0.8912000060081482},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6485000252723694},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5156999826431274},{"id":"https://openalex.org/keywords/repetition","display_name":"Repetition (rhetorical device)","score":0.4650999903678894},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4577000141143799},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4438999891281128},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.3917999863624573}],"concepts":[{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.8912000060081482},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6485000252723694},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6226999759674072},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5156999826431274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5113000273704529},{"id":"https://openalex.org/C2776141515","wikidata":"https://www.wikidata.org/wiki/Q1274479","display_name":"Repetition (rhetorical device)","level":2,"score":0.4650999903678894},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4577000141143799},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4438999891281128},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.3917999863624573},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3799000084400177},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3711000084877014},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37049999833106995},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3465000092983246},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C114611597","wikidata":"https://www.wikidata.org/wiki/Q373342","display_name":"Popular music","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.2619999945163727}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14877299","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877299","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":""}],"best_oa_location":{"id":"doi:10.5281/zenodo.14877299","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877299","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":""},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Variation":[0,127],"in":[1,18,22,34],"music":[2,25,35,101,157],"is":[3,36,159],"defined":[4],"as":[5],"repetition":[6],"of":[7,42,60,63,109,120,149,156],"a":[8,110,164],"theme,":[9],"but":[10],"with":[11,170],"various":[12],"modifications,":[13],"playing":[14],"an":[15,67],"important":[16],"role":[17],"many":[19],"musical":[20],"genres":[21],"developing":[23],"core":[24],"ideas":[26],"into":[27],"longer":[28],"passages.":[29],"Existing":[30],"research":[31],"on":[32],"variation":[33,102],"mostly":[37],"confined":[38],"to":[39,50,56,69,77,177],"datasets":[40,80],"consisting":[41],"classical":[43],"theme-and-variation":[44,71,84,89],"pieces,":[45],"and":[46,74,86,96,105,113,142,172],"generative":[47],"models":[48,132],"limited":[49],"melody-only":[51],"representations.":[52],"In":[53],"this":[54,150],"paper,":[55],"address":[57],"the":[58,61,107,153],"problem":[59],"lack":[62],"datasets,":[64],"we":[65,161],"propose":[66,92],"algorithm":[68],"extract":[70],"pairs":[72],"automatically,":[73],"use":[75],"it":[76],"annotate":[78],"two":[79,122],"called":[81,126],"POP909-TVar":[82],"(2,871":[83],"pairs)":[85],"VGMIDI-TVar":[87],"(7,830":[88],"pairs).":[90],"We":[91],"both":[93],"non-deep":[94,140],"learning":[95,98,141,144],"deep":[97,143],"based":[99,145],"symbolic":[100],"generation":[103],"models,":[104,125],"report":[106],"results":[108],"listening":[111],"study":[112],"feature-based":[114],"evaluation":[115],"for":[116,136,152],"these":[117],"models.":[118],"One":[119],"our":[121],"newly":[123],"proposed":[124],"Transformer,":[128],"outperforms":[129],"all":[130],"other":[131],"that":[133,160,166],"listeners":[134],"evaluated":[135],"\"variation":[137],"success\",":[138],"including":[139],"approaches.":[146],"An":[147],"implication":[148],"work":[151],"wider":[154],"field":[155],"making":[158],"now":[162],"have":[163],"model":[165],"can":[167],"generate":[168],"material":[169],"stronger":[171],"perceivably":[173],"more":[174],"successful":[175],"relationships":[176],"some":[178],"given":[179],"prompt":[180],"or":[181],"theme.":[182]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}