{"id":"https://openalex.org/W7002463227","doi":null,"title":"A new MusAE: Adversarial Transformer Autoencoder for Music","display_name":"A new MusAE: Adversarial Transformer Autoencoder for Music","publication_year":2021,"publication_date":"2021-05-02","ids":{"openalex":"https://openalex.org/W7002463227"},"language":"en","primary_location":{"id":"pmh:oai:etd.adm.unipi.it:etd-04162021-135903","doi":null,"is_oa":true,"landing_page_url":"https://etd.adm.unipi.it/theses/available/etd-04162021-135903/","pdf_url":"https://etd.adm.unipi.it/theses/available/etd-04162021-135903/unrestricted/BertiStefanoThesis.pdf","source":{"id":"https://openalex.org/S4306401800","display_name":"Electronic Theses and Dissertations Repository (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://etd.adm.unipi.it/theses/available/etd-04162021-135903/","raw_type":"text"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://etd.adm.unipi.it/theses/available/etd-04162021-135903/unrestricted/BertiStefanoThesis.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019644595","display_name":"Stefano Berti","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"BERTI, STEFANO","raw_affiliation_strings":["UNIVERSITY OF PISA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNIVERSITY OF PISA","institution_ids":["https://openalex.org/I108290504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5019644595"],"corresponding_institution_ids":["https://openalex.org/I108290504"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.4918999969959259,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.4918999969959259,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"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/T11309","display_name":"Music and Audio Processing","score":0.4918999969959259,"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/T10941","display_name":"Musicology and Musical Analysis","score":0.00419999985024333,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"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/adversarial-autoencoder","display_name":"adversarial autoencoder","score":0.9369999766349792},{"id":"https://openalex.org/keywords/transformer","display_name":"transformer models","score":0.4729999899864197},{"id":"https://openalex.org/keywords/chord-detection","display_name":"chord detection","score":0.3700000047683716},{"id":"https://openalex.org/keywords/latent-space-sampling","display_name":"latent space sampling","score":0.7070000171661377},{"id":"https://openalex.org/keywords/relative-position-encoding","display_name":"relative position encoding","score":0.7350000143051147}],"concepts":[{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.7985000014305115},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6938999891281128},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6269000172615051},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5794000029563904},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5727999806404114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5572999715805054},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5292999744415283},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4952999949455261},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.48240000009536743},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4307999908924103},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.42980000376701355},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.42080000042915344},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3296000063419342},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31040000915527344},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2775999903678894},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.27320000529289246},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.26339998841285706},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C558987187","wikidata":"https://www.wikidata.org/wiki/Q1544924","display_name":"Musical analysis","level":3,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:etd.adm.unipi.it:etd-04162021-135903","doi":null,"is_oa":true,"landing_page_url":"https://etd.adm.unipi.it/theses/available/etd-04162021-135903/","pdf_url":"https://etd.adm.unipi.it/theses/available/etd-04162021-135903/unrestricted/BertiStefanoThesis.pdf","source":{"id":"https://openalex.org/S4306401800","display_name":"Electronic Theses and Dissertations Repository (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://etd.adm.unipi.it/theses/available/etd-04162021-135903/","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:etd.adm.unipi.it:etd-04162021-135903","doi":null,"is_oa":true,"landing_page_url":"https://etd.adm.unipi.it/theses/available/etd-04162021-135903/","pdf_url":"https://etd.adm.unipi.it/theses/available/etd-04162021-135903/unrestricted/BertiStefanoThesis.pdf","source":{"id":"https://openalex.org/S4306401800","display_name":"Electronic Theses and Dissertations Repository (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://etd.adm.unipi.it/theses/available/etd-04162021-135903/","raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7002463227.pdf","grobid_xml":"https://content.openalex.org/works/W7002463227.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2560512785","https://openalex.org/W2581485081","https://openalex.org/W2605135824","https://openalex.org/W2613904329","https://openalex.org/W2789541106","https://openalex.org/W2887254492","https://openalex.org/W2896457183","https://openalex.org/W2911109671","https://openalex.org/W2945886944","https://openalex.org/W2950558456","https://openalex.org/W2950738719","https://openalex.org/W2964121744","https://openalex.org/W2970971581","https://openalex.org/W2980282514","https://openalex.org/W3030163527","https://openalex.org/W3037932933","https://openalex.org/W3038022805","https://openalex.org/W3047386385","https://openalex.org/W3090740343","https://openalex.org/W3096567388","https://openalex.org/W4288102863","https://openalex.org/W4298289240","https://openalex.org/W4300936792"],"related_works":["https://openalex.org/W6992888885","https://openalex.org/W3182521442","https://openalex.org/W4298063238","https://openalex.org/W3038344852","https://openalex.org/W7154828706","https://openalex.org/W4224279362","https://openalex.org/W3090740343","https://openalex.org/W2995416527","https://openalex.org/W3163784447","https://openalex.org/W4385680614"],"abstract_inverted_index":{"Automatic":[0],"polyphonic":[1,17,75],"music":[2,18],"generation":[3],"is":[4,89,124,151,180],"a":[5,13,46,111,127,162],"challenging":[6],"temporal":[7,11],"task.":[8],"Asidefrom":[9],"the":[10,56,62,86,91,98,107,118,121,135,148],"dimension,":[12],"model":[14,50],"dealing":[15],"with":[16,126,134,142,161,187],"shouldunderstand":[19],"which":[20],"combination":[21],"of":[22,34,42,130],"notes":[23],"are":[24],"consonant":[25],"and":[26,157,178,189,192],"can":[27],"be":[28],"groupedtogether":[29],"into":[30],"chords.":[31],"The":[32,144],"ability":[33],"deep":[35],"generative":[36],"models":[37],"to":[38,49,69,102,115,140,153,158,165,182],"learn":[39],"from":[40,97],"bigcollection":[41],"data":[43,52],"makes":[44],"it":[45,169,179],"suitable":[47],"approach":[48],"complex":[51],"distri-butions":[53],"such":[54],"as":[55],"one":[57],"underlying":[58],"music.":[59],"Among":[60],"them,":[61],"original":[63,87,108],"MusAEmodel":[64],"leveraged":[65],"an":[66],"adversarial":[67],"autoencoder":[68],"generate":[70,183],"smooth":[71,172],"interpola-tions":[72],"between":[73,174],"two":[74,175],"musical":[76,93,185],"sequences":[77,94,177,186],"made":[78],"by":[79,85,95],"monophonic":[80],"se-quences.":[81],"A":[82],"problem":[83],"presented":[84],"MusAE":[88,109,150],"that":[90,147],"generationof":[92],"sampling":[96],"latent":[99],"space":[100],"lead":[101],"inconsistentsamples.":[103],"This":[104],"thesis":[105],"extends":[106],"integrating":[110],"state-of-the-artmodel":[112],"for":[113,171],"sequence":[114,116],"tasks:":[117],"Transformer.":[119],"Moreover,":[120],"eventdata":[122],"representation":[123,131],"replaced":[125],"new":[128,149,184],"type":[129],"that,":[132],"to-gether":[133],"relative":[136],"positional":[137],"encoding,":[138],"allows":[139,170],"deal":[141,154],"polyphonicinstruments.":[143],"experiments":[145],"show":[146],"able":[152,181],"withpolyphonic":[155],"instruments":[156],"reconstruct":[159],"songs":[160],"similar":[163],"style":[164],"thosein":[166],"input.":[167],"Furthermore":[168],"interpolations":[173],"mu-sical":[176],"appre-ciable":[188],"coherent":[190],"dynamics":[191],"structure.":[193]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}