{"id":"https://openalex.org/W4414359284","doi":"https://doi.org/10.24963/ijcai.2025/1125","title":"METEOR: Melody-aware Texture-controllable Symbolic Music Re-Orchestration via Transformer VAE","display_name":"METEOR: Melody-aware Texture-controllable Symbolic Music Re-Orchestration via Transformer VAE","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359284","doi":"https://doi.org/10.24963/ijcai.2025/1125"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/1125","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/1125","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-05228512","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109791560","display_name":"Dinh-Viet-Toan Le","orcid":"https://orcid.org/0000-0001-6991-4079"},"institutions":[{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I7454413","display_name":"\u00c9cole Centrale de Lille","ror":"https://ror.org/01x441g73","country_code":"FR","type":"education","lineage":["https://openalex.org/I7454413"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Dinh-Viet-Toan Le","raw_affiliation_strings":["Univ. Lille, CNRS, Inria, Centrale Lille, UMR 9189 CRIStAL, F-59000 Lille, France"],"affiliations":[{"raw_affiliation_string":"Univ. Lille, CNRS, Inria, Centrale Lille, UMR 9189 CRIStAL, F-59000 Lille, France","institution_ids":["https://openalex.org/I7454413","https://openalex.org/I2279609970","https://openalex.org/I1294671590"]}]},{"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/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Hsuan Yang","raw_affiliation_strings":["National Taiwan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5109791560"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2279609970","https://openalex.org/I7454413"],"apc_list":null,"apc_paid":null,"fwci":1.428,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86047715,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"10126","last_page":"10134"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9983999729156494,"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":0.9983999729156494,"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":0.996999979019165,"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/T10860","display_name":"Speech and Audio Processing","score":0.9614999890327454,"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/melody","display_name":"Melody","score":0.7519000172615051},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.49720001220703125},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4796999990940094},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47429999709129333},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4277999997138977},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42640000581741333},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.375},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.3659999966621399}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7554000020027161},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.7519000172615051},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5328999757766724},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.49720001220703125},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49300000071525574},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4796999990940094},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47429999709129333},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4277999997138977},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42640000581741333},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.375},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.3659999966621399},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.36000001430511475},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C199168358","wikidata":"https://www.wikidata.org/wiki/Q3367000","display_name":"Orchestration","level":3,"score":0.335999995470047},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3206000030040741},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C89721942","wikidata":"https://www.wikidata.org/wiki/Q184421","display_name":"Harmony (Music)","level":3,"score":0.25110000371932983}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2025/1125","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/1125","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-05228512v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05228512","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Joint Conference on Artificial Intelligence AI, Arts & Creativity (IJCAI 2025), Aug 2025, Montreal, Canada. pp.10126-10134, ⟨10.24963/ijcai.2025/1125⟩","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-05228512v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05228512","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Joint Conference on Artificial Intelligence AI, Arts & Creativity (IJCAI 2025), Aug 2025, Montreal, Canada. pp.10126-10134, ⟨10.24963/ijcai.2025/1125⟩","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Re-orchestration":[0],"is":[1,38],"the":[2,17,20,24,41,47,94],"process":[3],"of":[4,13,46,93,126],"adapting":[5],"a":[6,10,29,56,64,80,102,121,137,143,151],"music":[7,76],"piece":[8],"for":[9,58,136,155],"different":[11],"set":[12],"instruments.":[14,49],"By":[15],"altering":[16],"original":[18],"instrumentation,":[19],"orchestrator":[21],"often":[22],"modifies":[23],"musical":[25],"texture":[26],"while":[27,100],"preserving":[28],"recognizable":[30],"melodic":[31,83],"line":[32],"and":[33,43,74,85,90,108,129],"ensures":[34],"that":[35,113],"each":[36],"part":[37],"playable":[39],"within":[40],"technical":[42],"expressive":[44],"capabilities":[45],"chosen":[48],"In":[50],"this":[51,156],"work,":[52],"we":[53,111],"propose":[54],"METEOR,":[55],"model":[57,70,115,152],"generating":[59],"Melody-aware":[60],"Texture-controllable":[61],"re-Orchestration":[62],"with":[63,79,96],"Transformer-based":[65],"variational":[66],"auto-encoder":[67],"(VAE).":[68],"This":[69],"performs":[71],"symbolic":[72],"instrumental":[73],"textural":[75,98],"style":[77,117],"transfers":[78],"focus":[81],"on":[82,120],"fidelity":[84],"controllability.":[86,130],"We":[87],"allow":[88],"bar-":[89],"track-level":[91],"controllability":[92],"accompaniment":[95],"various":[97],"attributes":[99],"keeping":[101],"homophonic":[103],"texture.":[104],"With":[105],"both":[106],"subjective":[107],"objective":[109],"evaluations,":[110],"show":[112],"our":[114],"outperforms":[116],"transfer":[118],"models":[119],"re-orchestration":[122],"task":[123,141],"in":[124],"terms":[125],"generation":[127],"quality":[128],"Moreover,":[131],"it":[132],"can":[133],"be":[134],"adapted":[135],"lead":[138],"sheet":[139],"orchestration":[140],"as":[142],"zero-shot":[144],"learning":[145],"model,":[146],"achieving":[147],"performance":[148],"comparable":[149],"to":[150],"specifically":[153],"trained":[154],"task.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}