{"id":"https://openalex.org/W4402594220","doi":"https://doi.org/10.1109/icce-taiwan62264.2024.10674555","title":"Discriminator-enhanced Music Generation Based on Multitrack Music Transformer","display_name":"Discriminator-enhanced Music Generation Based on Multitrack Music Transformer","publication_year":2024,"publication_date":"2024-07-09","ids":{"openalex":"https://openalex.org/W4402594220","doi":"https://doi.org/10.1109/icce-taiwan62264.2024.10674555"},"language":"en","primary_location":{"id":"doi:10.1109/icce-taiwan62264.2024.10674555","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icce-taiwan62264.2024.10674555","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan)","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/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":true,"raw_author_name":"Jinlong Zhu","raw_affiliation_strings":["Hokkaido University,Graduate School of Information Science and Technology,Japan"],"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"],"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"],"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"],"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"],"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":5,"corresponding_author_ids":["https://openalex.org/A5061733763"],"corresponding_institution_ids":["https://openalex.org/I205349734"],"apc_list":null,"apc_paid":null,"fwci":0.3544,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55522562,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"363","last_page":"364"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9941999912261963,"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":0.9941999912261963,"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":0.9703999757766724,"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":0.9532999992370605,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.8275020718574524},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6459509134292603},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5484045147895813},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46106892824172974},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.34429165720939636},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2260361611843109},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.2128545343875885},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.11542898416519165}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.8275020718574524},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6459509134292603},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5484045147895813},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46106892824172974},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.34429165720939636},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2260361611843109},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.2128545343875885},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.11542898416519165},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icce-taiwan62264.2024.10674555","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icce-taiwan62264.2024.10674555","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W3092879656","https://openalex.org/W3175663427","https://openalex.org/W4221148975","https://openalex.org/W4372259826","https://openalex.org/W6781678156","https://openalex.org/W6781972552","https://openalex.org/W6795892075"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4293202849","https://openalex.org/W1980965563","https://openalex.org/W1489300767","https://openalex.org/W2387995142","https://openalex.org/W4380714744","https://openalex.org/W4319453655","https://openalex.org/W2089959425","https://openalex.org/W2864363823"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,11,70],"novel":[3],"approach":[4],"for":[5],"automatic":[6],"multi-track":[7],"music":[8,83],"generation":[9],"utilizing":[10],"Generative":[12],"Adversarial":[13],"Network":[14],"(GAN)":[15],"framework":[16],"integrated":[17],"with":[18],"Transformer":[19],"architecture.":[20],"While":[21],"previous":[22],"research":[23],"has":[24],"successfully":[25],"produced":[26],"extended":[27],"multitrack":[28],"compositions,":[29],"they":[30],"often":[31],"exhibit":[32],"an":[33],"unnatural":[34],"quality.":[35],"This":[36],"is":[37],"caused":[38],"by":[39],"unusual":[40],"instrument":[41],"performance,":[42],"unconventional":[43],"composition,":[44],"and":[45,49],"inconsistencies":[46],"in":[47,62],"scale":[48],"groove,":[50],"all":[51],"contributing":[52],"to":[53,75],"the":[54,59,77,81,89],"feeling":[55,61],"of":[56,58,80,91],"absence":[57],"human":[60],"generated":[63,82],"music.":[64],"In":[65],"our":[66,92],"method,":[67],"we":[68],"incorporate":[69],"Transformer-based":[71],"discriminator":[72],"specifically":[73],"designed":[74],"assess":[76],"human-like":[78],"qualities":[79],"tracks.":[84],"Experimental":[85],"results":[86],"have":[87],"demonstrated":[88],"effectiveness":[90],"approach.":[93]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2025-10-10T00:00:00"}
