{"id":"https://openalex.org/W6930766218","doi":"https://doi.org/10.5281/zenodo.14877377","title":"MMT-BERT: Chord-Aware Symbolic Music Generation Based on Multitrack Music Transformer and MusicBERT","display_name":"MMT-BERT: Chord-Aware Symbolic Music Generation Based on Multitrack Music Transformer and MusicBERT","publication_year":2024,"publication_date":"2024-11-10","ids":{"openalex":"https://openalex.org/W6930766218","doi":"https://doi.org/10.5281/zenodo.14877377"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14877377","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877377","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"type":"conference-paper","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.14877377","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jinlong Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinlong Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Keigo Sakurai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keigo Sakurai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ren Togo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren Togo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Takahiro Ogawa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takahiro Ogawa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Miki Haseyama","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miki Haseyama","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.8215000033378601,"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":0.8215000033378601,"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":0.08489999920129776,"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":0.03669999912381172,"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":0.7461000084877014},{"id":"https://openalex.org/keywords/the-symbolic","display_name":"The Symbolic","score":0.6665999889373779},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5221999883651733},{"id":"https://openalex.org/keywords/symbolic-trajectory-evaluation","display_name":"Symbolic trajectory evaluation","score":0.4198000133037567},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41850000619888306},{"id":"https://openalex.org/keywords/pop-music-automation","display_name":"Pop music automation","score":0.4108000099658966},{"id":"https://openalex.org/keywords/computer-music","display_name":"Computer music","score":0.4065999984741211},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.4020000100135803}],"concepts":[{"id":"https://openalex.org/C194147245","wikidata":"https://www.wikidata.org/wiki/Q1076368","display_name":"Chord (peer-to-peer)","level":2,"score":0.7461000084877014},{"id":"https://openalex.org/C2776095079","wikidata":"https://www.wikidata.org/wiki/Q489538","display_name":"The Symbolic","level":2,"score":0.6665999889373779},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6507999897003174},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5221999883651733},{"id":"https://openalex.org/C23123167","wikidata":"https://www.wikidata.org/wiki/Q7661193","display_name":"Symbolic trajectory evaluation","level":3,"score":0.4198000133037567},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41850000619888306},{"id":"https://openalex.org/C73520026","wikidata":"https://www.wikidata.org/wiki/Q7229091","display_name":"Pop music automation","level":4,"score":0.4108000099658966},{"id":"https://openalex.org/C34259666","wikidata":"https://www.wikidata.org/wiki/Q1122550","display_name":"Computer music","level":3,"score":0.4065999984741211},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4020000100135803},{"id":"https://openalex.org/C143857728","wikidata":"https://www.wikidata.org/wiki/Q193544","display_name":"Music theory","level":3,"score":0.39980000257492065},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3971000015735626},{"id":"https://openalex.org/C65620979","wikidata":"https://www.wikidata.org/wiki/Q7661176","display_name":"Symbolic data analysis","level":2,"score":0.3944000005722046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3774999976158142},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3596999943256378},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C109568592","wikidata":"https://www.wikidata.org/wiki/Q207628","display_name":"Musical composition","level":3,"score":0.3118000030517578},{"id":"https://openalex.org/C114611597","wikidata":"https://www.wikidata.org/wiki/Q373342","display_name":"Popular music","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.29010000824928284},{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.26809999346733093}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14877377","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877377","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.5281/zenodo.14877377","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877377","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6798610091209412,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,99],"propose":[1,100],"a":[2,38,110,117],"novel":[3],"symbolic":[4,16,24,46,77,91,139],"music":[5,18,25,32,47,78,92,113,140,150],"representation":[6,93],"and":[7,34,61,63,126,147],"Generative":[8],"Adversarial":[9],"Network":[10],"(GAN)":[11],"framework":[12],"specially":[13,67],"designed":[14,68],"for":[15],"multitrack":[17,112],"generation.":[19],"The":[20],"main":[21],"theme":[22],"of":[23,31,37,57,66,76,138,149,160],"generation":[26,48],"primarily":[27],"encompasses":[28],"the":[29,35,64,73,85,106,124,135,145,158,166],"preprocessing":[30],"data":[33],"implementation":[36],"deep":[39],"learning":[40],"framework.":[41],"Current":[42],"techniques":[43],"dedicated":[44],"to":[45,72,105,121],"generally":[49],"encounter":[50],"two":[51],"significant":[52],"challenges:":[53],"training":[54],"data's":[55],"lack":[56],"information":[58],"about":[59],"chords":[60],"scales":[62],"requirement":[65],"model":[69,120],"architecture":[70,103],"adapted":[71],"unique":[74],"format":[75],"representation.":[79,107],"In":[80],"this":[81],"paper,":[82],"we":[83,115],"solve":[84],"above":[86],"problems":[87],"by":[88,134,152],"introducing":[89],"new":[90],"with":[94],"MusicLang":[95],"chord":[96],"analysis":[97],"model.":[98],"our":[101,153,161],"MMT-BERT":[102],"adapting":[104],"To":[108],"build":[109],"robust":[111],"generator,":[114],"fine-tune":[116],"pre-trained":[118],"MusicBERT":[119],"serve":[122],"as":[123],"discriminator,":[125],"incorporate":[127],"relativistic":[128],"standard":[129],"loss.":[130],"This":[131],"approach,":[132],"supported":[133],"in-depth":[136],"understanding":[137],"encoded":[141],"within":[142],"MusicBERT,":[143],"fortifies":[144],"consonance":[146],"humanity":[148],"generated":[151],"method.":[154],"Experimental":[155],"results":[156],"demonstrate":[157],"effectiveness":[159],"approach":[162],"which":[163],"strictly":[164],"follows":[165],"state-of-the-art":[167],"methods.":[168]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}