{"id":"https://openalex.org/W3092879656","doi":"https://doi.org/10.1145/3394171.3413671","title":"Pop Music Transformer","display_name":"Pop Music Transformer","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3092879656","doi":"https://doi.org/10.1145/3394171.3413671","mag":"3092879656"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413671","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413671","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","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/A5047723511","display_name":"Yu-Siang Huang","orcid":"https://orcid.org/0000-0002-2350-8080"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Siang Huang","raw_affiliation_strings":["Taiwan AI Labs & Academia Sinica, Taipei, Taiwan Roc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taiwan AI Labs & Academia Sinica, Taipei, Taiwan Roc","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061291906","display_name":"Yi\u2010Hsuan Yang","orcid":"https://orcid.org/0000-0002-2724-6161"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Hsuan Yang","raw_affiliation_strings":["Taiwan AI Labs & Academia Sinica, Taipei, Taiwan Roc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taiwan AI Labs & Academia Sinica, Taipei, Taiwan Roc","institution_ids":["https://openalex.org/I84653119"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I84653119"],"apc_list":null,"apc_paid":null,"fwci":16.7264,"has_fulltext":false,"cited_by_count":248,"citation_normalized_percentile":{"value":0.99523841,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1180","last_page":"1188"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.9958000183105469,"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/transformer","display_name":"Transformer","score":0.7690412998199463},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6993807554244995},{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.6262406706809998},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.6049587726593018},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4880770444869995},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3516591191291809},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.15549230575561523},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15110841393470764},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08840325474739075}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7690412998199463},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6993807554244995},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.6262406706809998},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.6049587726593018},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4880770444869995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3516591191291809},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.15549230575561523},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15110841393470764},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08840325474739075},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394171.3413671","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413671","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W625810977","https://openalex.org/W2051219610","https://openalex.org/W2076769328","https://openalex.org/W2087870700","https://openalex.org/W2113409081","https://openalex.org/W2123282787","https://openalex.org/W2144001972","https://openalex.org/W2405656250","https://openalex.org/W2527926565","https://openalex.org/W2566969886","https://openalex.org/W2896788168","https://openalex.org/W2906214917","https://openalex.org/W2940744433","https://openalex.org/W2963408210","https://openalex.org/W2963925437","https://openalex.org/W2964110616","https://openalex.org/W2971351900","https://openalex.org/W2982753834","https://openalex.org/W4205952203","https://openalex.org/W6728134609"],"related_works":["https://openalex.org/W2316271602","https://openalex.org/W2357375963","https://openalex.org/W607893370","https://openalex.org/W629160228","https://openalex.org/W584653787","https://openalex.org/W4362512397","https://openalex.org/W587444722","https://openalex.org/W2022713566","https://openalex.org/W2336023324","https://openalex.org/W633023889"],"abstract_inverted_index":{"A":[0],"great":[1],"number":[2],"of":[3,37,51,120,134,148],"deep":[4],"learning":[5],"based":[6],"models":[7],"have":[8],"been":[9],"recently":[10],"proposed":[11],"for":[12,27,78],"automatic":[13],"music":[14,79,163],"composition.":[15],"Among":[16],"these":[17],"models,":[18],"the":[19,84,92,109,121,132,143],"Transformer":[20,97,158,170],"stands":[21],"out":[22],"as":[23],"a":[24,34,86,96,105,155],"prominent":[25],"approach":[26],"generating":[28],"expressive":[29],"classical":[30],"piano":[31,162],"performance":[32],"with":[33,65,164],"coherent":[35],"structure":[36,107,124,147,167],"up":[38],"to":[39,95,103,141],"one":[40],"minute.":[41],"The":[42,127],"model":[43],"is":[44,89],"powerful":[45],"in":[46,108,125],"that":[47,72,113,159],"it":[48],"learns":[49],"abstractions":[50],"data":[52,93,129],"on":[53],"its":[54],"own,":[55],"without":[56],"much":[57],"human-imposed":[58],"domain":[59],"knowledge":[60],"or":[61],"constraints.":[62],"In":[63,99],"contrast":[64],"this":[66,69,151],"general":[67],"approach,":[68,152],"paper":[70],"shows":[71],"Transformers":[73,114],"can":[74,115],"do":[75],"even":[76],"better":[77,165],"modeling,":[80],"when":[81],"we":[82,101,153],"improve":[83],"way":[85],"musical":[87],"score":[88],"converted":[90],"into":[91],"fed":[94],"model.":[98],"particular,":[100],"seek":[102],"impose":[104],"metrical":[106],"input":[110],"data,":[111],"so":[112],"be":[116],"more":[117],"easily":[118],"aware":[119],"beat-bar-phrase":[122],"hierarchical":[123],"music.":[126,149],"new":[128],"representation":[130],"maintains":[131],"flexibility":[133],"local":[135],"tempo":[136],"changes,":[137],"and":[138,145],"provides":[139],"hurdles":[140],"control":[142],"rhythmic":[144,166],"harmonic":[146],"With":[150],"build":[154],"Pop":[156,161],"Music":[157],"composes":[160],"than":[168],"existing":[169],"models.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":21},{"year":2025,"cited_by_count":62},{"year":2024,"cited_by_count":56},{"year":2023,"cited_by_count":45},{"year":2022,"cited_by_count":31},{"year":2021,"cited_by_count":29},{"year":2020,"cited_by_count":4}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}