{"id":"https://openalex.org/W3201026571","doi":"https://doi.org/10.1145/3503161.3548084","title":"Structure-Enhanced Pop Music Generation via Harmony-Aware Learning","display_name":"Structure-Enhanced Pop Music Generation via Harmony-Aware Learning","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W3201026571","doi":"https://doi.org/10.1145/3503161.3548084","mag":"3201026571"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548084","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548084","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2109.06441","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100617727","display_name":"Xueyao Zhang","orcid":"https://orcid.org/0000-0003-2615-019X"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueyao Zhang","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076799733","display_name":"Jinchao Zhang","orcid":"https://orcid.org/0000-0002-5279-0468"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinchao Zhang","raw_affiliation_strings":["Pattern Recognition Center, WeChat AI, Tencent Inc, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pattern Recognition Center, WeChat AI, Tencent Inc, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101263790","display_name":"Yao Qiu","orcid":"https://orcid.org/0009-0009-0276-0904"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Qiu","raw_affiliation_strings":["Pattern Recognition Center, WeChat AI, Tencent Inc, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pattern Recognition Center, WeChat AI, Tencent Inc, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100336197","display_name":"Li Wang","orcid":"https://orcid.org/0000-0003-2165-0080"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Wang","raw_affiliation_strings":["Communication University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100620306","display_name":"Jie Zhou","orcid":"https://orcid.org/0000-0001-7701-234X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhou","raw_affiliation_strings":["Pattern Recognition Center, WeChat AI, Tencent Inc, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pattern Recognition Center, WeChat AI, Tencent Inc, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1204","last_page":"1213"},"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":0.9991999864578247,"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/T10860","display_name":"Speech and Audio Processing","score":0.9595000147819519,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/chord","display_name":"Chord (peer-to-peer)","score":0.8735780119895935},{"id":"https://openalex.org/keywords/harmony","display_name":"Harmony (color)","score":0.6994669437408447},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6856331825256348},{"id":"https://openalex.org/keywords/popular-music","display_name":"Popular music","score":0.4806448519229889},{"id":"https://openalex.org/keywords/pop-music-automation","display_name":"Pop music automation","score":0.465561181306839},{"id":"https://openalex.org/keywords/harmony","display_name":"Harmony (Music)","score":0.4609087109565735},{"id":"https://openalex.org/keywords/musical-notation","display_name":"Musical notation","score":0.43778195977211},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.4356843829154968},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40107667446136475},{"id":"https://openalex.org/keywords/aesthetics","display_name":"Aesthetics","score":0.3255387544631958},{"id":"https://openalex.org/keywords/musical-composition","display_name":"Musical composition","score":0.2849825620651245},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.23235389590263367},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.19342872500419617}],"concepts":[{"id":"https://openalex.org/C194147245","wikidata":"https://www.wikidata.org/wiki/Q1076368","display_name":"Chord (peer-to-peer)","level":2,"score":0.8735780119895935},{"id":"https://openalex.org/C2776453491","wikidata":"https://www.wikidata.org/wiki/Q5659234","display_name":"Harmony (color)","level":2,"score":0.6994669437408447},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6856331825256348},{"id":"https://openalex.org/C114611597","wikidata":"https://www.wikidata.org/wiki/Q373342","display_name":"Popular music","level":2,"score":0.4806448519229889},{"id":"https://openalex.org/C73520026","wikidata":"https://www.wikidata.org/wiki/Q7229091","display_name":"Pop music automation","level":4,"score":0.465561181306839},{"id":"https://openalex.org/C89721942","wikidata":"https://www.wikidata.org/wiki/Q184421","display_name":"Harmony (Music)","level":3,"score":0.4609087109565735},{"id":"https://openalex.org/C88639978","wikidata":"https://www.wikidata.org/wiki/Q233861","display_name":"Musical notation","level":3,"score":0.43778195977211},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.4356843829154968},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40107667446136475},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.3255387544631958},{"id":"https://openalex.org/C109568592","wikidata":"https://www.wikidata.org/wiki/Q207628","display_name":"Musical composition","level":3,"score":0.2849825620651245},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.23235389590263367},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.19342872500419617},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3503161.3548084","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548084","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2109.06441","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.06441","pdf_url":"https://arxiv.org/pdf/2109.06441","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2109.06441","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.06441","pdf_url":"https://arxiv.org/pdf/2109.06441","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W293399241","https://openalex.org/W395933519","https://openalex.org/W614201078","https://openalex.org/W1491994475","https://openalex.org/W2012502309","https://openalex.org/W2012726852","https://openalex.org/W2018738723","https://openalex.org/W2051924267","https://openalex.org/W2067621398","https://openalex.org/W2402588270","https://openalex.org/W2478051194","https://openalex.org/W2560674852","https://openalex.org/W2752134738","https://openalex.org/W2797329263","https://openalex.org/W2809621972","https://openalex.org/W2902052009","https://openalex.org/W2906933017","https://openalex.org/W2919624000","https://openalex.org/W2963032576","https://openalex.org/W2963403868","https://openalex.org/W2963408210","https://openalex.org/W2963985773","https://openalex.org/W2964121744","https://openalex.org/W2970971581","https://openalex.org/W2982753834","https://openalex.org/W2996287690","https://openalex.org/W3014731244","https://openalex.org/W3015625764","https://openalex.org/W3030056709","https://openalex.org/W3034573343","https://openalex.org/W3049174246","https://openalex.org/W3049247973","https://openalex.org/W3092879656","https://openalex.org/W3093276169","https://openalex.org/W3111037961","https://openalex.org/W3112895167","https://openalex.org/W3163784447","https://openalex.org/W3173531154","https://openalex.org/W3175663427","https://openalex.org/W3183478142","https://openalex.org/W6600553734"],"related_works":["https://openalex.org/W2547055343","https://openalex.org/W2082086839","https://openalex.org/W2563249704","https://openalex.org/W2080724131","https://openalex.org/W4252264844","https://openalex.org/W4307957021","https://openalex.org/W1966698465","https://openalex.org/W2921491545","https://openalex.org/W4226108805","https://openalex.org/W2375856378"],"abstract_inverted_index":{"Pop":[0],"music":[1,22,44],"generation":[2],"has":[3],"always":[4],"been":[5],"an":[6],"attractive":[7],"topic":[8],"for":[9,14,41],"both":[10],"musicians":[11],"and":[12,112,149,182,196],"scientists":[13],"a":[15,24,29,175],"long":[16],"time.":[17],"However,":[18],"automatically":[19],"composing":[20],"pop":[21,43],"with":[23,68],"satisfactory":[25],"structure":[26,71,98,144,159,181],"is":[27,65],"still":[28],"challenging":[30],"issue.":[31],"In":[32],"this":[33],"paper,":[34],"we":[35,132],"propose":[36,133],"to":[37,123,156,169],"leverage":[38],"harmony-aware":[39],"learning":[40,126],"structure-enhanced":[42],"generation.":[45],"On":[46,76],"the":[47,52,58,69,74,77,80,89,92,96,101,110,118,124,128,134,143,147,151,158,170,180,187,194],"one":[48,50],"hand,":[49,79],"of":[51,54,61,72,83,91,99,127,179,189],"participants":[53],"harmony,":[55,84],"chord,":[56],"represents":[57],"harmonic":[59],"set":[60],"multiple":[62],"notes,":[63],"which":[64,94,121,140],"integrated":[66],"closely":[67],"spatial":[70],"music,":[73,93,100,148,191],"texture.":[75,197],"other":[78,81],"participant":[82],"chord":[85,108],"progression,":[86,109],"usually":[87],"accompanies":[88],"development":[90],"promotes":[95],"temporal":[97],"form.":[102],"Moreover,":[103],"when":[104],"chords":[105],"evolve":[106],"into":[107],"texture":[111],"form":[113,195],"can":[114,141,184],"be":[115],"bridged":[116],"by":[117],"harmony":[119],"naturally,":[120],"contributes":[122],"joint":[125],"two":[129],"structures.":[130],"Furthermore,":[131],"Harmony-Aware":[135],"Hierarchical":[136],"Music":[137],"Transformer":[138],"(HAT),":[139],"exploit":[142],"adaptively":[145],"from":[146],"make":[150],"musical":[152,162],"tokens":[153],"interact":[154],"hierarchically":[155],"enhance":[157],"in":[160,193],"multi-level":[161],"elements.":[163],"Experimental":[164],"results":[165],"reveal":[166],"that":[167],"compared":[168],"existing":[171],"methods,":[172],"HAT":[173],"owns":[174],"much":[176],"better":[177],"understanding":[178],"it":[183],"also":[185],"improve":[186],"quality":[188],"generated":[190],"especially":[192]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}