{"id":"https://openalex.org/W4406276411","doi":"https://doi.org/10.1109/gcce62371.2024.10760546","title":"Structured Polyphonic Music Generation with Diffusion Transformer","display_name":"Structured Polyphonic Music Generation with Diffusion Transformer","publication_year":2024,"publication_date":"2024-10-29","ids":{"openalex":"https://openalex.org/W4406276411","doi":"https://doi.org/10.1109/gcce62371.2024.10760546"},"language":"en","primary_location":{"id":"doi:10.1109/gcce62371.2024.10760546","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcce62371.2024.10760546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 13th Global Conference on Consumer Electronics (GCCE)","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/A5061733763","display_name":"Jinlong Zhu","orcid":"https://orcid.org/0000-0002-5723-2879"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jinlong Zhu","raw_affiliation_strings":["Hokkaido University,Graduate School of Information Science and Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Graduate School of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015994136","display_name":"Keigo Sakurai","orcid":"https://orcid.org/0009-0008-3747-0491"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keigo Sakurai","raw_affiliation_strings":["Hokkaido University,Graduate School of Information Science and Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Graduate School of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002757875","display_name":"Ren Togo","orcid":"https://orcid.org/0000-0002-4474-3995"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ren Togo","raw_affiliation_strings":["Hokkaido University,Faculty of Information Science and Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Faculty of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009032240","display_name":"Takahiro Ogawa","orcid":"https://orcid.org/0000-0001-5332-8112"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Ogawa","raw_affiliation_strings":["Hokkaido University,Faculty of Information Science and Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Faculty of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"last","author":{"id":null,"display_name":"Miki Haseyama","orcid":null},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Miki Haseyama","raw_affiliation_strings":["Hokkaido University,Faculty of Information Science and Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University,Faculty of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I205349734"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205349734"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9976999759674072,"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":0.9976999759674072,"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":0.982699990272522,"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/polyphony","display_name":"Polyphony","score":0.92420494556427},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5805104374885559},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4997367858886719},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43843531608581543},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2701151371002197},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.21767058968544006},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1387549638748169},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09850218892097473},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0748002827167511}],"concepts":[{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.92420494556427},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5805104374885559},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4997367858886719},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43843531608581543},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2701151371002197},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.21767058968544006},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1387549638748169},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09850218892097473},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0748002827167511}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/gcce62371.2024.10760546","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcce62371.2024.10760546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 13th Global Conference on Consumer Electronics (GCCE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2411659965","https://openalex.org/W2387677326","https://openalex.org/W4200063482","https://openalex.org/W2357575019","https://openalex.org/W2370117122","https://openalex.org/W2360603947","https://openalex.org/W2371528275"],"abstract_inverted_index":{"We":[0],"propose":[1,96],"a":[2,54,84,97,104,111],"novel":[3],"approach":[4],"for":[5,26,87],"structured":[6],"polyphonic":[7,28,98],"music":[8,29,99,125],"generation":[9,30,100],"utilizing":[10],"Denoising":[11],"Diffusion":[12,112],"Probabilistic":[13],"Models":[14],"(DDPMs)":[15],"with":[16,46,103,127],"Transformer":[17,105,113],"blocks":[18],"replacing":[19],"U-Net":[20,74],"as":[21],"backbone":[22,106],"architecture.":[23,75],"Previous":[24],"methods":[25],"DDPM-based":[27],"have":[31],"shown":[32],"success":[33],"in":[34,59],"creating":[35],"diverse":[36],"compositions":[37],"from":[38,67],"various":[39],"prompts.":[40],"However,":[41],"these":[42],"approaches":[43],"commonly":[44],"struggle":[45],"producing":[47],"repetitive":[48,124],"sections":[49],"of":[50,56,70,108],"music,":[51],"leading":[52],"to":[53,81,122],"lack":[55],"structural":[57],"coherence":[58],"the":[60,68,71,79],"generated":[61],"music.":[62],"This":[63],"issue":[64],"mainly":[65],"stems":[66],"limitations":[69],"widely":[72],"used":[73],"Specifically,":[76],"it":[77],"lacks":[78],"capability":[80],"retain":[82],"memory,":[83],"critical":[85],"requirement":[86],"generating":[88],"repeated":[89],"melodic":[90],"phrases.":[91],"In":[92],"our":[93,119],"method,":[94],"we":[95],"diffusion":[101],"model":[102],"instead":[107],"U-Net,":[109],"forming":[110],"(DiT).":[114],"Experimental":[115],"results":[116],"show":[117],"that":[118],"method":[120],"manages":[121],"create":[123],"phrases":[126],"high":[128],"quality.":[129]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
