{"id":"https://openalex.org/W4285367200","doi":"https://doi.org/10.23919/dafx51585.2021.9768218","title":"Improving Synthesizer Programming From Variational Autoencoders Latent Space","display_name":"Improving Synthesizer Programming From Variational Autoencoders Latent Space","publication_year":2021,"publication_date":"2021-09-08","ids":{"openalex":"https://openalex.org/W4285367200","doi":"https://doi.org/10.23919/dafx51585.2021.9768218"},"language":"en","primary_location":{"id":"doi:10.23919/dafx51585.2021.9768218","is_oa":false,"landing_page_url":"https://doi.org/10.23919/dafx51585.2021.9768218","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 24th International Conference on Digital Audio Effects (DAFx)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://orbi.umons.ac.be/bitstream/20.500.12907/43332/1/DAFx20in21_paper_7.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056151896","display_name":"Gwendal Le Vaillant","orcid":"https://orcid.org/0000-0002-0299-9351"},"institutions":[{"id":"https://openalex.org/I130929987","display_name":"University of Mons","ror":"https://ror.org/02qnnz951","country_code":"BE","type":"education","lineage":["https://openalex.org/I130929987"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Gwendal Le Vaillant","raw_affiliation_strings":["Numediart Institute University of Mons,Mons,Belgium","Numediart Institute University of Mons, Mons, Belgium"],"affiliations":[{"raw_affiliation_string":"Numediart Institute University of Mons,Mons,Belgium","institution_ids":["https://openalex.org/I130929987"]},{"raw_affiliation_string":"Numediart Institute University of Mons, Mons, Belgium","institution_ids":["https://openalex.org/I130929987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042439255","display_name":"Thierry Dutoit","orcid":"https://orcid.org/0000-0001-7024-2150"},"institutions":[{"id":"https://openalex.org/I130929987","display_name":"University of Mons","ror":"https://ror.org/02qnnz951","country_code":"BE","type":"education","lineage":["https://openalex.org/I130929987"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Thierry Dutoit","raw_affiliation_strings":["Numediart Institute University of Mons,Mons,Belgium","Numediart Institute University of Mons, Mons, Belgium"],"affiliations":[{"raw_affiliation_string":"Numediart Institute University of Mons,Mons,Belgium","institution_ids":["https://openalex.org/I130929987"]},{"raw_affiliation_string":"Numediart Institute University of Mons, Mons, Belgium","institution_ids":["https://openalex.org/I130929987"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088277398","display_name":"Sebastien Dekeyser","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115060","display_name":"Haute \u00c9cole Galil\u00e9e","ror":"https://ror.org/028rd3808","country_code":"BE","type":"education","lineage":["https://openalex.org/I4210115060"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Sebastien Dekeyser","raw_affiliation_strings":["ISIB HE2B,Brussels,Belgium","ISIB HE2B, Brussels, Belgium"],"affiliations":[{"raw_affiliation_string":"ISIB HE2B,Brussels,Belgium","institution_ids":["https://openalex.org/I4210115060"]},{"raw_affiliation_string":"ISIB HE2B, Brussels, Belgium","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5056151896"],"corresponding_institution_ids":["https://openalex.org/I130929987"],"apc_list":null,"apc_paid":null,"fwci":2.0004,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.87600698,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"276","last_page":"283"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994999766349792,"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/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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/computer-science","display_name":"Computer science","score":0.7480913996696472},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7147396802902222},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5686219334602356},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5348981618881226},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5012059211730957},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.46040666103363037},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4369293749332428},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4241534173488617},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3706568777561188},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36510246992111206},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3370976150035858}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7480913996696472},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7147396802902222},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5686219334602356},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5348981618881226},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5012059211730957},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.46040666103363037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4369293749332428},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4241534173488617},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3706568777561188},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36510246992111206},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3370976150035858},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/dafx51585.2021.9768218","is_oa":false,"landing_page_url":"https://doi.org/10.23919/dafx51585.2021.9768218","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 24th International Conference on Digital Audio Effects (DAFx)","raw_type":"proceedings-article"},{"id":"pmh:oai:orbi.umons.ac.be:20.500.12907/43332","is_oa":true,"landing_page_url":"https://orbi.umons.ac.be/handle/20.500.12907/43332","pdf_url":"https://orbi.umons.ac.be/bitstream/20.500.12907/43332/1/DAFx20in21_paper_7.pdf","source":{"id":"https://openalex.org/S7407055454","display_name":"ORBi UMONS","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 24th International Conference on Digital Audio Effects, DAFx 2021 (2021-09-08); 2021 24th International Conference on Digital Audio Effects (DAFx), Vienna, Aut [Aut], 08-09-2021 => 10-09-2021","raw_type":"peer reviewed"}],"best_oa_location":{"id":"pmh:oai:orbi.umons.ac.be:20.500.12907/43332","is_oa":true,"landing_page_url":"https://orbi.umons.ac.be/handle/20.500.12907/43332","pdf_url":"https://orbi.umons.ac.be/bitstream/20.500.12907/43332/1/DAFx20in21_paper_7.pdf","source":{"id":"https://openalex.org/S7407055454","display_name":"ORBi UMONS","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 24th International Conference on Digital Audio Effects, DAFx 2021 (2021-09-08); 2021 24th International Conference on Digital Audio Effects (DAFx), Vienna, Aut [Aut], 08-09-2021 => 10-09-2021","raw_type":"peer reviewed"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285367200.pdf","grobid_xml":"https://content.openalex.org/works/W4285367200.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1561135842","https://openalex.org/W2287082121","https://openalex.org/W2407513162","https://openalex.org/W2587284713","https://openalex.org/W2606176153","https://openalex.org/W2753738274","https://openalex.org/W2791716806","https://openalex.org/W2808492412","https://openalex.org/W2888169323","https://openalex.org/W2903782687","https://openalex.org/W2963090522","https://openalex.org/W2977735357","https://openalex.org/W2998588915","https://openalex.org/W2999890176","https://openalex.org/W3000389243","https://openalex.org/W3017181854","https://openalex.org/W3044645945","https://openalex.org/W3103913581","https://openalex.org/W3150807214","https://openalex.org/W4293849739","https://openalex.org/W4295177495","https://openalex.org/W4391602018","https://openalex.org/W6610566761","https://openalex.org/W6633727632","https://openalex.org/W6640963894","https://openalex.org/W6657159850","https://openalex.org/W6696345064","https://openalex.org/W6733471323","https://openalex.org/W6736723571","https://openalex.org/W6738536549","https://openalex.org/W6744627333","https://openalex.org/W6770847983","https://openalex.org/W6771763809","https://openalex.org/W6773240189","https://openalex.org/W6776208785","https://openalex.org/W6781638033"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W2159052453","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W4386815338","https://openalex.org/W2145836866","https://openalex.org/W2803255133"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"have":[3],"been":[4],"recently":[5],"applied":[6],"to":[7,24,59,63,91,97,110],"the":[8,98],"task":[9],"of":[10,18,46,70,94,102,144,163],"automatic":[11],"synthesizer":[12,164],"programming,":[13],"i.e.,":[14],"finding":[15],"optimal":[16],"values":[17],"sound":[19],"synthesis":[20],"parameters":[21,39,47,71,95,115],"in":[22,89,142],"order":[23,90],"reproduce":[25],"a":[26,79,128],"given":[27],"input":[28,86,103],"sound.":[29],"This":[30],"paper":[31],"focuses":[32],"on":[33],"generative":[34],"models,":[35],"which":[36,132],"can":[37,155],"infer":[38],"as":[40,42,72,114],"well":[41],"generate":[43],"new":[44,57],"sets":[45,162],"or":[48,160],"perform":[49],"smooth":[50],"morphing":[51],"effects":[52],"between":[53],"sounds.":[54,104],"We":[55],"introduce":[56],"models":[58,154],"ensure":[60],"scalability":[61],"and":[62,74,100,118,123,147,150],"increase":[64],"performance":[65,106],"by":[66],"using":[67,127],"heterogeneous":[68],"representations":[69],"numerical":[73],"categorical":[75],"random":[76],"variables.":[77],"Moreover,":[78],"spectral":[80],"variational":[81],"autoencoder":[82],"architecture":[83],"with":[84,135,158],"multi-channel":[85],"is":[87,133],"proposed":[88],"improve":[92],"inference":[93,146],"related":[96],"pitch":[99],"intensity":[101],"Model":[105],"was":[107],"evaluated":[108],"according":[109],"several":[111],"criteria":[112],"such":[113],"estimation":[116],"error":[117],"audio":[119,148],"reconstruction":[120],"accuracy.":[121],"Training":[122],"evaluation":[124],"were":[125],"performed":[126],"30k":[129],"presets":[130],"dataset":[131],"published":[134],"this":[136],"paper.":[137],"They":[138],"demonstrate":[139],"significant":[140],"improvements":[141],"terms":[143],"parameter":[145],"accuracy":[149],"show":[151],"that":[152],"presented":[153],"be":[156],"used":[157],"subsets":[159],"full":[161],"parameters.":[165]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":5}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}