{"id":"https://openalex.org/W4390885010","doi":"https://doi.org/10.1007/s11633-023-1457-1","title":"Exploring Variational Auto-encoder Architectures, Configurations, and Datasets for Generative Music Explainable AI","display_name":"Exploring Variational Auto-encoder Architectures, Configurations, and Datasets for Generative Music Explainable AI","publication_year":2024,"publication_date":"2024-01-15","ids":{"openalex":"https://openalex.org/W4390885010","doi":"https://doi.org/10.1007/s11633-023-1457-1"},"language":"en","primary_location":{"id":"doi:10.1007/s11633-023-1457-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11633-023-1457-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11633-023-1457-1.pdf","source":{"id":"https://openalex.org/S4210224602","display_name":"Machine Intelligence Research","issn_l":"2731-538X","issn":["2731-538X","2731-5398"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Intelligence Research","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11633-023-1457-1.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044409155","display_name":"Nick Bryan\u2013Kinns","orcid":"https://orcid.org/0000-0002-1382-2914"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Nick Bryan-Kinns","raw_affiliation_strings":["School of Electronic Engineering and Computer Science, Queen Mary University of London, London, El 4NS, UK"],"raw_orcid":"https://orcid.org/0000-0002-1382-2914","affiliations":[{"raw_affiliation_string":"School of Electronic Engineering and Computer Science, Queen Mary University of London, London, El 4NS, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102876929","display_name":"Bingyuan Zhang","orcid":"https://orcid.org/0009-0005-7623-836X"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bingyuan Zhang","raw_affiliation_strings":["School of Electronic Engineering and Computer Science, Queen Mary University of London, London, El 4NS, UK"],"raw_orcid":"https://orcid.org/0009-0005-7623-836X","affiliations":[{"raw_affiliation_string":"School of Electronic Engineering and Computer Science, Queen Mary University of London, London, El 4NS, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081093972","display_name":"Songyan Zhao","orcid":"https://orcid.org/0009-0000-6116-5325"},"institutions":[{"id":"https://openalex.org/I188497080","display_name":"Carleton College","ror":"https://ror.org/03jep7677","country_code":"US","type":"education","lineage":["https://openalex.org/I188497080"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Songyan Zhao","raw_affiliation_strings":["Computer Science Department, Carleton College, Northfield, MN, 55057, USA"],"raw_orcid":"https://orcid.org/0009-0000-6116-5325","affiliations":[{"raw_affiliation_string":"Computer Science Department, Carleton College, Northfield, MN, 55057, USA","institution_ids":["https://openalex.org/I188497080"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090034492","display_name":"Berker Banar","orcid":"https://orcid.org/0000-0003-1808-2203"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Berker Banar","raw_affiliation_strings":["School of Electronic Engineering and Computer Science, Queen Mary University of London, London, El 4NS, UK"],"raw_orcid":"https://orcid.org/0000-0003-1808-2203","affiliations":[{"raw_affiliation_string":"School of Electronic Engineering and Computer Science, Queen Mary University of London, London, El 4NS, UK","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5044409155"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":6.0851,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.97054149,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"21","issue":"1","first_page":"29","last_page":"45"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9975000023841858,"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":0.9975000023841858,"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":0.996399998664856,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.989300012588501,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6803731918334961},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6676686406135559},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.6022850275039673},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5454573631286621},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.476481169462204},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3819665014743805},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.23960661888122559}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6803731918334961},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6676686406135559},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.6022850275039673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5454573631286621},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.476481169462204},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3819665014743805},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.23960661888122559}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11633-023-1457-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11633-023-1457-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11633-023-1457-1.pdf","source":{"id":"https://openalex.org/S4210224602","display_name":"Machine Intelligence Research","issn_l":"2731-538X","issn":["2731-538X","2731-5398"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Intelligence Research","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11633-023-1457-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11633-023-1457-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11633-023-1457-1.pdf","source":{"id":"https://openalex.org/S4210224602","display_name":"Machine Intelligence Research","issn_l":"2731-538X","issn":["2731-538X","2731-5398"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Intelligence Research","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8793594538","display_name":null,"funder_award_id":"EP/S022694/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"}],"funders":[{"id":"https://openalex.org/F4320309083","display_name":"Carleton College","ror":"https://ror.org/03jep7677"},{"id":"https://openalex.org/F4320311061","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846"},{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390885010.pdf"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W181426284","https://openalex.org/W2067621398","https://openalex.org/W2079172465","https://openalex.org/W2282821441","https://openalex.org/W2406433429","https://openalex.org/W2463338764","https://openalex.org/W2491611869","https://openalex.org/W2560316200","https://openalex.org/W2569330962","https://openalex.org/W2621350877","https://openalex.org/W2758804652","https://openalex.org/W2775487773","https://openalex.org/W2792210438","https://openalex.org/W2803390034","https://openalex.org/W2809621972","https://openalex.org/W2891794946","https://openalex.org/W2909608214","https://openalex.org/W2913668833","https://openalex.org/W2919624000","https://openalex.org/W2946112597","https://openalex.org/W2948574791","https://openalex.org/W2954957095","https://openalex.org/W2962772482","https://openalex.org/W2963253162","https://openalex.org/W2964105398","https://openalex.org/W2999765337","https://openalex.org/W3005441616","https://openalex.org/W3014731244","https://openalex.org/W3041122017","https://openalex.org/W3045523713","https://openalex.org/W3046218710","https://openalex.org/W3048062783","https://openalex.org/W3048713063","https://openalex.org/W3049174246","https://openalex.org/W3080764280","https://openalex.org/W3096831136","https://openalex.org/W3099425575","https://openalex.org/W3101039626","https://openalex.org/W3104847483","https://openalex.org/W3152124863","https://openalex.org/W3165134144","https://openalex.org/W3186465535","https://openalex.org/W3195758981","https://openalex.org/W4205550663","https://openalex.org/W4226065182","https://openalex.org/W4226360574","https://openalex.org/W4298053324","https://openalex.org/W4313527987","https://openalex.org/W4377081716","https://openalex.org/W4382318729","https://openalex.org/W4400940563","https://openalex.org/W6631190155","https://openalex.org/W6640963894","https://openalex.org/W6789449647"],"related_works":["https://openalex.org/W4220775285","https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4365211920","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4313488044","https://openalex.org/W3209574120"],"abstract_inverted_index":{"Abstract":[0],"Generative":[1],"AI":[2,22,30,45,61,88,224,237],"models":[3,31,46,78,134,225],"for":[4,200,226,243],"music":[5,108,166,168,182,209,227],"and":[6,14,28,80,96,104,176,186,228,235,241],"the":[7,70,87,121,215],"arts":[8],"in":[9,86],"general":[10],"are":[11,118,214],"increasingly":[12],"complex":[13,27],"hard":[15],"to":[16,25,38,42,50,92,164,207,232],"understand.":[17],"The":[18],"field":[19],"of":[20,55,69,75,83,132,138,174,219,221,247],"explainable":[21],"(XAI)":[23],"seeks":[24],"make":[26],"opaque":[29],"such":[32,133,183],"as":[33,184],"neural":[34],"networks":[35],"more":[36,47,244],"understandable":[37,48,245],"people.":[39],"One":[40],"approach":[41],"making":[43],"generative":[44,60,122,223],"is":[49,198],"impose":[51],"a":[52,66,191],"small":[53],"number":[54],"semantically":[56],"meaningful":[57,115],"attributes":[58,117],"on":[59,107,120],"models.":[62],"This":[63],"paper":[64],"contributes":[65],"systematic":[67,130],"examination":[68],"impact":[71],"that":[72,144,160,190],"different":[73],"combinations":[74],"variational":[76],"auto-encoder":[77],"(measureVAE":[79],"adversarialVAE),":[81],"configurations":[82,220],"latent":[84,94,195],"space":[85,197],"model":[89],"(from":[90],"4":[91,114,201],"256":[93],"dimensions),":[95],"training":[97],"datasets":[98,242],"(Irish":[99],"folk,":[100,102],"Turkish":[101],"classical,":[103],"pop)":[105],"have":[106,127],"generation":[109,246],"performance":[110,149],"when":[111,204],"2":[112],"or":[113,193],"musical":[116,155,172,239],"imposed":[119],"model.":[123],"To":[124],"date,":[125],"there":[126],"been":[128],"no":[129],"comparisons":[131,218],"at":[135],"this":[136],"level":[137],"combinatorial":[139],"detail.":[140],"Our":[141,212],"findings":[142],"show":[143],"measureVAE":[145,161,206],"has":[146,153],"better":[147,154],"reconstruction":[148],"than":[150],"adversarialVAE":[151],"which":[152],"attribute":[156],"independence.":[157],"Results":[158],"demonstrate":[159],"was":[162],"able":[163],"generate":[165,208],"across":[167,210],"genres":[169],"with":[170,179],"interpretable":[171],"dimensions":[173,203],"control,":[175],"performs":[177],"best":[178],"low":[180],"complexity":[181],"pop":[185],"rock.":[187],"We":[188],"recommend":[189],"32":[192],"64":[194],"dimensional":[196],"optimal":[199],"regularised":[202],"using":[205],"genres.":[211],"results":[213],"first":[216],"detailed":[217],"state-of-the-art":[222],"can":[229],"be":[230],"used":[231],"help":[233],"select":[234],"configure":[236],"models,":[238],"features,":[240],"music.":[248]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}