{"id":"https://openalex.org/W7118208971","doi":"https://doi.org/10.1007/s40747-025-02210-2","title":"A chord-controlled transformer for controllable and coherent music generation","display_name":"A chord-controlled transformer for controllable and coherent music generation","publication_year":2026,"publication_date":"2026-01-05","ids":{"openalex":"https://openalex.org/W7118208971","doi":"https://doi.org/10.1007/s40747-025-02210-2"},"language":"en","primary_location":{"id":"doi:10.1007/s40747-025-02210-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-02210-2","pdf_url":null,"source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex &amp; Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1007/s40747-025-02210-2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121933696","display_name":"Zhiqiang Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210146051","display_name":"Anyang Institute of Technology","ror":"https://ror.org/03sd3t490","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210146051"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiqiang Gao","raw_affiliation_strings":["School of Music and Dance, Anyang Preschool Education College, 455000, Anyang, Henan Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Music and Dance, Anyang Preschool Education College, 455000, Anyang, Henan Province, China","institution_ids":["https://openalex.org/I4210146051"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5121933696"],"corresponding_institution_ids":["https://openalex.org/I4210146051"],"apc_list":{"value":1320,"currency":"GBP","value_usd":1619},"apc_paid":{"value":1320,"currency":"GBP","value_usd":1619},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03555922,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":"2","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9449999928474426,"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":0.9449999928474426,"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":0.00989999994635582,"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":0.008999999612569809,"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":0.8741000294685364},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6161999702453613},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6003000140190125},{"id":"https://openalex.org/keywords/musical-notation","display_name":"Musical notation","score":0.4862000048160553},{"id":"https://openalex.org/keywords/chunking","display_name":"Chunking (psychology)","score":0.42640000581741333},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.4169999957084656},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.41280001401901245},{"id":"https://openalex.org/keywords/computational-intelligence","display_name":"Computational intelligence","score":0.40939998626708984}],"concepts":[{"id":"https://openalex.org/C194147245","wikidata":"https://www.wikidata.org/wiki/Q1076368","display_name":"Chord (peer-to-peer)","level":2,"score":0.8741000294685364},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6646999716758728},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6161999702453613},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6003000140190125},{"id":"https://openalex.org/C88639978","wikidata":"https://www.wikidata.org/wiki/Q233861","display_name":"Musical notation","level":3,"score":0.4862000048160553},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4731000065803528},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.42640000581741333},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.4169999957084656},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.41280001401901245},{"id":"https://openalex.org/C139502532","wikidata":"https://www.wikidata.org/wiki/Q1122090","display_name":"Computational intelligence","level":2,"score":0.40939998626708984},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.3837999999523163},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.3659999966621399},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.3434000015258789},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.334199994802475},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.31360000371932983},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C2777182073","wikidata":"https://www.wikidata.org/wiki/Q1224135","display_name":"Bass (fish)","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C27362006","wikidata":"https://www.wikidata.org/wiki/Q272021","display_name":"Gestalt psychology","level":3,"score":0.2985999882221222},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C2983311337","wikidata":"https://www.wikidata.org/wiki/Q34379","display_name":"Musical instrument","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C131770355","wikidata":"https://www.wikidata.org/wiki/Q876215","display_name":"Harmonic analysis","level":2,"score":0.26010000705718994}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s40747-025-02210-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-02210-2","pdf_url":null,"source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex &amp; Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:fd99d6d217db4dbc8d576431d83b8114","is_oa":true,"landing_page_url":"https://doaj.org/article/fd99d6d217db4dbc8d576431d83b8114","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Complex & Intelligent Systems, Vol 12, Iss 2, Pp 1-14 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s40747-025-02210-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-02210-2","pdf_url":null,"source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex &amp; Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6146101951599121,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2067621398","https://openalex.org/W2475687244","https://openalex.org/W2964110616","https://openalex.org/W3015625764","https://openalex.org/W3049247973","https://openalex.org/W3092879656","https://openalex.org/W3173187964","https://openalex.org/W3175663427","https://openalex.org/W3201026571","https://openalex.org/W3213549365","https://openalex.org/W4381786045"],"related_works":[],"abstract_inverted_index":{"AI":[0],"music":[1,83,134],"generation":[2],"faces":[3],"significant":[4],"challenges":[5],"in":[6,13,64,186],"musical":[7,60,151],"coherence":[8],"and":[9,118,153,164,172,190],"user":[10,175],"controllability,":[11,187],"particularly":[12,38],"adhering":[14],"to":[15,57,101,147],"specific":[16],"harmonic":[17,67,155],"structures":[18],"like":[19],"chord":[20,106,131],"progressions.":[21],"While":[22],"recent":[23],"large-scale":[24],"models":[25,40,185],"have":[26],"shown":[27],"increasing":[28],"promise,":[29],"achieving":[30],"long-term":[31],"structural":[32,188],"integrity":[33],"remains":[34],"a":[35,42,76,92,109,113,120,140,173],"persistent":[36],"challenge,":[37],"for":[39,48,80],"of":[41],"more":[43],"moderate":[44],"scale":[45],"that":[46,128,178],"aim":[47],"computational":[49],"efficiency.":[50],"Many":[51],"existing":[52,183],"end-to-end":[53],"approaches":[54],"still":[55],"struggle":[56],"effectively":[58],"integrate":[59],"theory,":[61],"often":[62],"resulting":[63],"outputs":[65],"with":[66,133],"inconsistencies.":[68],"To":[69],"address":[70],"this,":[71],"we":[72],"propose":[73],"the":[74,103,125,145,162,179],"Chord-Transformer,":[75],"novel":[77],"architecture":[78,123],"designed":[79],"chord-conditioned":[81],"symbolic":[82],"generation.":[84],"The":[85],"framework":[86],"features":[87],"two":[88],"main":[89],"contributions:":[90],"(1)":[91],"dynamic":[93],"programming":[94],"algorithm":[95],"based":[96],"on":[97],"an":[98],"energy":[99],"function":[100],"extract":[102],"most":[104],"salient":[105],"progression":[107],"from":[108,168],"given":[110],"sequence,":[111],"providing":[112],"robust":[114],"high-level":[115],"semantic":[116],"guide;":[117],"(2)":[119],"parallel":[121],"fusion":[122],"within":[124],"Transformer":[126],"decoder":[127],"synergistically":[129],"combines":[130],"cross-attention":[132],"self-attention.":[135],"This":[136],"mechanism,":[137],"enhanced":[138],"by":[139],"chord-aligned":[141],"positional":[142],"encoding,":[143],"allows":[144],"model":[146],"maintain":[148],"both":[149,169],"local":[150],"flow":[152],"global":[154],"coherence.":[156],"We":[157],"conduct":[158],"extensive":[159],"experiments":[160],"using":[161],"Pop909":[163],"LMD":[165],"datasets.":[166],"Results":[167],"objective":[170],"metrics":[171],"subjective":[174],"study":[176],"show":[177],"Chord-Transformer":[180],"significantly":[181],"outperforms":[182],"mainstream":[184],"rationality,":[189],"overall":[191],"musicality.":[192]},"counts_by_year":[],"updated_date":"2026-01-22T23:29:09.771500","created_date":"2026-01-05T00:00:00"}
