{"id":"https://openalex.org/W6893727217","doi":"https://doi.org/10.5281/zenodo.5137922","title":"Musical Duet Generation with Tree-Structured Variational Autoencoder","display_name":"Musical Duet Generation with Tree-Structured Variational Autoencoder","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W6893727217","doi":"https://doi.org/10.5281/zenodo.5137922"},"language":"en","primary_location":{"id":"pmh:oai:zenodo.org:5137922","is_oa":true,"landing_page_url":"https://zenodo.org/record/5137922","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/5137922","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Oudad, Adam","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Oudad, Adam","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Taketo Akama","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Taketo Akama","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Saito, Hiroaki","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saito, Hiroaki","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23927773,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.8485000133514404,"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":0.8485000133514404,"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":0.09939999878406525,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.009700000286102295,"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/autoencoder","display_name":"Autoencoder","score":0.8281000256538391},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.8001000285148621},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.6040999889373779},{"id":"https://openalex.org/keywords/midi","display_name":"MIDI","score":0.5627999901771545},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.529699981212616},{"id":"https://openalex.org/keywords/melody","display_name":"Melody","score":0.5108000040054321},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4311000108718872}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8281000256538391},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.8001000285148621},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6496000289916992},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.6040999889373779},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5956000089645386},{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.5627999901771545},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.529699981212616},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.5108000040054321},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5027999877929688},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4311000108718872},{"id":"https://openalex.org/C88639978","wikidata":"https://www.wikidata.org/wiki/Q233861","display_name":"Musical notation","level":3,"score":0.35839998722076416},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3321000039577484},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33090001344680786},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2549000084400177}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:zenodo.org:5137922","is_oa":true,"landing_page_url":"https://zenodo.org/record/5137922","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"},{"id":"doi:10.5281/zenodo.5137922","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.5137922","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:5137922","is_oa":true,"landing_page_url":"https://zenodo.org/record/5137922","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"},"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":{"Recent":[0],"successful":[1],"latent":[2],"space":[3],"models":[4,114,142],"based":[5],"on":[6,115,135],"Variational":[7],"AutoEncoder":[8],"(VAE)":[9],"can":[10],"generate":[11,76],"polyphonic":[12],"music":[13],"for":[14],"solo":[15],"instrument.":[16],"Polyphony":[17],"with":[18,49],"multiple":[19],"tracks":[20,57],"is":[21,43],"more":[22],"challenging":[23],"in":[24],"many":[25],"aspects.":[26],"Towards":[27],"this":[28,40,90],"goal,":[29],"we":[30],"propose":[31,81],"the":[32,132],"intermediate":[33],"task":[34],"of":[35,151],"musical":[36,68,109],"duet":[37],"generation.":[38],"In":[39,138],"setting,":[41],"it":[42],"common":[44],"to":[45,47,75,88,107,122,145],"have":[46],"deal":[48],"two":[50,82],"different":[51],"instruments":[52],"and":[53,86,92,99,119],"note":[54],"overlaps":[55,63,152],"among":[56,153],"occur":[58],"frequently.":[59],"Unfortunately,":[60],"these":[61,104],"meaningful":[62],"are":[64,143],"discarded":[65],"by":[66],"current":[67],"models.":[69],"This":[70],"limitation":[71,91],"hinders":[72],"their":[73],"ability":[74],"multi-track":[77],"music.":[78],"We":[79,111],"thus":[80],"data":[83,105],"structures,":[84],"MergedTree":[85,95,128],"HierarchicalTree,":[87],"overcome":[89],"three":[93],"models,":[94],"VAE,":[96,101],"SharedHierarchicalTree":[97],"VAE":[98,125,129],"HierarchicalTree":[100],"which":[102],"leverage":[103],"representations":[106],"reconstruct":[108],"duets3.":[110],"evaluate":[112],"our":[113],"Lakh":[116],"MIDI":[117],"dataset":[118],"compare":[120],"them":[121],"a":[123,147],"PianoTree":[124],"baseline.":[126],"Our":[127],"model":[130,134],"outperforms":[131],"baseline":[133],"reconstruction":[136],"scores.":[137],"addition,":[139],"all":[140],"proposed":[141],"able":[144],"incorporate":[146],"statistically":[148],"relevant":[149],"ratio":[150],"tracks.":[154]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
