{"id":"https://openalex.org/W3015625764","doi":"https://doi.org/10.1109/icassp40776.2020.9054554","title":"Transformer VAE: A Hierarchical Model for Structure-Aware and Interpretable Music Representation Learning","display_name":"Transformer VAE: A Hierarchical Model for Structure-Aware and Interpretable Music Representation Learning","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015625764","doi":"https://doi.org/10.1109/icassp40776.2020.9054554","mag":"3015625764"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5018786002","display_name":"Junyan Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junyan Jiang","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027959958","display_name":"Gus Xia","orcid":"https://orcid.org/0000-0003-3629-906X"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gus G. Xia","raw_affiliation_strings":["Music X Lab, New York University, Shanghai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music X Lab, New York University, Shanghai","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068765358","display_name":"Dave B. Carlton","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dave B. Carlton","raw_affiliation_strings":["Hooktheory, LLC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hooktheory, LLC","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060087064","display_name":"Chris Anderson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chris N. Anderson","raw_affiliation_strings":["Hooktheory, LLC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hooktheory, LLC","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057866893","display_name":"Ryan Miyakawa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ryan H. Miyakawa","raw_affiliation_strings":["Hooktheory, LLC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hooktheory, LLC","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.8745,"has_fulltext":false,"cited_by_count":93,"citation_normalized_percentile":{"value":0.98688574,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"2020","issue":null,"first_page":"516","last_page":"520"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9965000152587891,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9937000274658203,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.853992223739624},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7347935438156128},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7056164741516113},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6651508212089539},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6150121688842773},{"id":"https://openalex.org/keywords/analogy","display_name":"Analogy","score":0.5304908752441406},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4686177372932434},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4433283507823944},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3990095853805542},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34588897228240967},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32287847995758057},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08152511715888977}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.853992223739624},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7347935438156128},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7056164741516113},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6651508212089539},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6150121688842773},{"id":"https://openalex.org/C521332185","wikidata":"https://www.wikidata.org/wiki/Q185816","display_name":"Analogy","level":2,"score":0.5304908752441406},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4686177372932434},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4433283507823944},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3990095853805542},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34588897228240967},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32287847995758057},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08152511715888977},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"mag:3175353731","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=202002255660058054","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1560346234","https://openalex.org/W2099471712","https://openalex.org/W2109663430","https://openalex.org/W2467604901","https://openalex.org/W2475287302","https://openalex.org/W2577946330","https://openalex.org/W2753738274","https://openalex.org/W2792210438","https://openalex.org/W2901139351","https://openalex.org/W2948574791","https://openalex.org/W2963403868","https://openalex.org/W2963418779","https://openalex.org/W2963801305","https://openalex.org/W2963985773","https://openalex.org/W2964121744","https://openalex.org/W2964669873","https://openalex.org/W2991178431","https://openalex.org/W4293771587","https://openalex.org/W4297747548","https://openalex.org/W4320013936","https://openalex.org/W4385245566","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6633572075","https://openalex.org/W6676568895","https://openalex.org/W6720208624","https://openalex.org/W6732248266","https://openalex.org/W6739901393","https://openalex.org/W6744627333","https://openalex.org/W6746569791","https://openalex.org/W6749351710","https://openalex.org/W6749669830","https://openalex.org/W6755406732","https://openalex.org/W6763362620"],"related_works":["https://openalex.org/W2983142544","https://openalex.org/W2891059443","https://openalex.org/W4281663961","https://openalex.org/W3208888551","https://openalex.org/W4313561566","https://openalex.org/W3208386644","https://openalex.org/W4220682630","https://openalex.org/W4389832810","https://openalex.org/W3181622257","https://openalex.org/W3163146846"],"abstract_inverted_index":{"Structure":[0],"awareness":[1],"and":[2,20,35,68,81,112],"interpretability":[3],"are":[4,29],"two":[5,40,57],"of":[6,11,56,100,137,148],"the":[7,45,54,65,82,110,113,116,120,126,134,145],"most":[8],"desired":[9],"properties":[10],"music":[12,22,62,146],"generation":[13],"algorithms.":[14],"Structure-aware":[15],"models":[16,28],"generate":[17],"more":[18,30],"natural":[19],"coherent":[21],"with":[23,125],"long-term":[24,76],"dependencies,":[25],"while":[26],"interpretable":[27,85],"friendly":[31],"for":[32],"human-computer":[33],"interaction":[34],"co-creation.":[36],"To":[37],"achieve":[38,130],"these":[39],"goals":[41],"simultaneously,":[42],"we":[43,128],"designed":[44],"Transformer":[46,67,95],"Variational":[47],"AutoEncoder,":[48],"a":[49,89,102,140],"hierarchical":[50,104],"model":[51],"that":[52,94],"unifies":[53],"efforts":[55],"recent":[58],"breakthroughs":[59],"in":[60],"deep":[61],"generation:":[63],"1)":[64],"Music":[66,71],"2)":[69],"Deep":[70],"Analogy.":[72],"The":[73],"former":[74],"learns":[75,84],"dependencies":[77,114],"using":[78,88],"attention":[79],"mechanism,":[80],"latter":[83],"latent":[86],"representations":[87,108,118],"disentangled":[90],"conditional-VAE.":[91],"We":[92],"showed":[93],"VAE":[96],"is":[97,142],"essentially":[98],"capable":[99],"learning":[101],"context-sensitive":[103],"representation,":[105],"regarding":[106],"local":[107,117],"as":[109,119],"context":[111,131],"among":[115],"global":[121],"structure.":[122],"By":[123],"interacting":[124],"model,":[127],"can":[129],"transfer,":[132],"realizing":[133],"imaginary":[135],"situation":[136],"\"what":[138],"if\"":[139],"piece":[141],"developed":[143],"following":[144],"flow":[147],"another":[149],"piece.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":2}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}