{"id":"https://openalex.org/W4288013262","doi":"https://doi.org/10.48550/arxiv.2202.12243","title":"Flat Latent Manifolds for Human-machine Co-creation of Music","display_name":"Flat Latent Manifolds for Human-machine Co-creation of Music","publication_year":2022,"publication_date":"2022-02-23","ids":{"openalex":"https://openalex.org/W4288013262","doi":"https://doi.org/10.48550/arxiv.2202.12243"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2202.12243","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2202.12243","pdf_url":"https://arxiv.org/pdf/2202.12243","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2202.12243","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014597367","display_name":"Nutan Chen","orcid":"https://orcid.org/0000-0001-7571-0742","observed_orcids":["https://orcid.org/0000-0001-7571-0742"]},"institutions":[{"id":"https://openalex.org/I1319473763","display_name":"Volkswagen Group (Germany)","ror":"https://ror.org/01f3bhg26","country_code":"DE","type":"company","lineage":["https://openalex.org/I1319473763"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Chen, Nutan","raw_affiliation_strings":["Machine Learning Research Lab , Volkswagen Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning Research Lab , Volkswagen Group","institution_ids":["https://openalex.org/I1319473763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088480694","display_name":"Djalel Benbouzid","orcid":"https://orcid.org/0009-0007-9022-0291","observed_orcids":["https://orcid.org/0009-0007-9022-0291"]},"institutions":[{"id":"https://openalex.org/I1319473763","display_name":"Volkswagen Group (Germany)","ror":"https://ror.org/01f3bhg26","country_code":"DE","type":"company","lineage":["https://openalex.org/I1319473763"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Benbouzid, Djalel","raw_affiliation_strings":["Machine Learning Research Lab , Volkswagen Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning Research Lab , Volkswagen Group","institution_ids":["https://openalex.org/I1319473763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077656092","display_name":"Francesco Ferroni","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ferroni, Francesco","raw_affiliation_strings":["ArgoAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ArgoAI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001442939","display_name":"Mathis Nitschke","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I25485817","display_name":"University of Applied Sciences St P\u00f6lten","ror":"https://ror.org/039a2re55","country_code":"AT","type":"education","lineage":["https://openalex.org/I25485817"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Nitschke, Mathis","raw_affiliation_strings":["St . P\u00f6lten University of Applied Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"St . P\u00f6lten University of Applied Sciences","institution_ids":["https://openalex.org/I25485817"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005653473","display_name":"Luciano Pinna","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pinna, Luciano","raw_affiliation_strings":["St Joost School of Art and Design"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"St Joost School of Art and Design","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022626150","display_name":"Patrick van der Smagt","orcid":"https://orcid.org/0000-0003-4418-4916","observed_orcids":["https://orcid.org/0000-0003-4418-4916"]},"institutions":[{"id":"https://openalex.org/I1319473763","display_name":"Volkswagen Group (Germany)","ror":"https://ror.org/01f3bhg26","country_code":"DE","type":"company","lineage":["https://openalex.org/I1319473763"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"van der Smagt, Patrick","raw_affiliation_strings":["Machine Learning Research Lab , Volkswagen Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning Research Lab , Volkswagen Group","institution_ids":["https://openalex.org/I1319473763"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9833999872207642,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9833999872207642,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.012500000186264515,"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/T10941","display_name":"Musicology and Musical Analysis","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/music-generation","display_name":"music generation","score":0.843999981880188},{"id":"https://openalex.org/keywords/recurrent-variational-autoencoder","display_name":"recurrent variational autoencoder","score":0.7749999761581421},{"id":"https://openalex.org/keywords/latent-space-interpolation","display_name":"latent space interpolation","score":0.8610000014305115},{"id":"https://openalex.org/keywords/human-machine-co-creation","display_name":"human-machine co-creation","score":0.871999979019165},{"id":"https://openalex.org/keywords/drumming","display_name":"drumming","score":0.6370000243186951},{"id":"https://openalex.org/keywords/interpretability","display_name":"interpretability","score":0.7590000033378601}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6333608627319336},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5415239334106445},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5045992136001587},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.5020096302032471},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.43170538544654846},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.41094258427619934},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3805530071258545},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.326540470123291},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25534218549728394},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09364938735961914},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2202.12243","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2202.12243","pdf_url":"https://arxiv.org/pdf/2202.12243","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2202.12243","doi":"https://doi.org/10.48550/arxiv.2202.12243","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2202.12243","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2202.12243","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2202.12243","pdf_url":"https://arxiv.org/pdf/2202.12243","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4288013262.pdf","grobid_xml":"https://content.openalex.org/works/W4288013262.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W1884859883","https://openalex.org/W2964199361","https://openalex.org/W4302343661"],"related_works":["https://openalex.org/W2936858163","https://openalex.org/W4280644428","https://openalex.org/W4386556392","https://openalex.org/W3216504281","https://openalex.org/W6989408332","https://openalex.org/W3015625764","https://openalex.org/W4415593986","https://openalex.org/W3008434711","https://openalex.org/W2999344275","https://openalex.org/W2792210438"],"abstract_inverted_index":{"The":[0,200],"use":[1],"of":[2,13,16,65,102,165,181,232,235],"machine":[3],"learning":[4],"in":[5,37,91,104,113,151],"artistic":[6],"music":[7,116,184],"generation":[8],"leads":[9],"to":[10,33,44,46,62,72,142,219],"controversial":[11],"discussions":[12],"the":[14,51,54,63,81,114,124,128,143,152,163,207,217,221,224,242,245],"quality":[15],"art,":[17],"for":[18,50,175,191],"which":[19],"objective":[20],"quantification":[21],"is":[22,43,140],"nonsensical.":[23],"We":[24,171],"therefore":[25],"consider":[26],"a":[27,31,34,38,77,132,137,147,179,197],"music-generating":[28],"algorithm":[29],"as":[30],"counterpart":[32],"human":[35,78],"musician,":[36],"setting":[39],"where":[40],"reciprocal":[41],"interplay":[42],"lead":[45],"new":[47],"experiences,":[48],"both":[49],"musician":[52],"and":[53,70,126,157,186,214,241],"audience.":[55],"To":[56,118],"obtain":[57],"this":[58],"behaviour,":[59],"we":[60,84,122,168,187],"resort":[61],"framework":[64],"recurrent":[66],"Variational":[67],"Auto-Encoders":[68],"(VAE)":[69],"learn":[71],"generate":[73,85],"music,":[74],"seeded":[75],"by":[76,89,216,239],"musician.":[79],"In":[80],"learned":[82],"model,":[83],"novel":[86],"musical":[87,159,225],"sequences":[88],"interpolation":[90],"latent":[92,106,129,153,208],"space.":[93,145],"Standard":[94],"VAEs":[95],"however":[96],"do":[97],"not":[98],"guarantee":[99],"any":[100],"form":[101],"smoothness":[103],"their":[105],"representation.":[107],"This":[108],"translates":[109],"into":[110],"abrupt":[111],"changes":[112,160],"generated":[115],"sequences.":[117],"overcome":[119],"these":[120],"limitations,":[121],"regularise":[123],"decoder":[125],"endow":[127],"space":[130,154],"with":[131,196,244],"flat":[133],"Riemannian":[134],"manifold,":[135],"i.e.,":[136],"manifold":[138],"that":[139,161,206],"isometric":[141],"Euclidean":[144],"As":[146],"result,":[148],"linearly":[149],"interpolating":[150],"yields":[155],"realistic":[156],"smooth":[158],"fit":[162],"type":[164],"machine--musician":[166],"interactions":[167],"aim":[169],"for.":[170],"provide":[172],"empirical":[173],"evidence":[174,205],"our":[176,189,227],"method":[177],"via":[178],"set":[180],"experiments":[182],"on":[183],"datasets":[185],"deploy":[188],"model":[190],"an":[192,230],"interactive":[193],"jam":[194],"session":[195],"professional":[198],"drummer.":[199],"live":[201],"performance":[202],"provides":[203],"qualitative":[204],"representation":[209],"can":[210],"be":[211],"intuitively":[212],"interpreted":[213],"exploited":[215],"drummer":[218],"drive":[220],"interplay.":[222],"Beyond":[223],"application,":[226],"approach":[228],"showcases":[229],"instance":[231],"human-centred":[233],"design":[234],"machine-learning":[236],"models,":[237],"driven":[238],"interpretability":[240],"interaction":[243],"end":[246],"user.":[247]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2022-07-26T00:00:00"}