{"id":"https://openalex.org/W3040752496","doi":"https://doi.org/10.24963/ijcai.2020/767","title":"FlowSynth: Simplifying Complex Audio Generation Through Explorable Latent Spaces with Normalizing Flows","display_name":"FlowSynth: Simplifying Complex Audio Generation Through Explorable Latent Spaces with Normalizing Flows","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3040752496","doi":"https://doi.org/10.24963/ijcai.2020/767","mag":"3040752496"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/767","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/767","pdf_url":"https://www.ijcai.org/proceedings/2020/0767.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0767.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085170922","display_name":"Philippe Esling","orcid":"https://orcid.org/0000-0002-1655-7909"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4389425508","display_name":"Sciences et Technologies de la Musique et du Son","ror":"https://ror.org/025xvn046","country_code":null,"type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I2802818602","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4210102700","https://openalex.org/I4389425508"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Philippe Esling","raw_affiliation_strings":["IRCAM - CNRS UMR 9912, Sorbonne Universit\u00e9"],"affiliations":[{"raw_affiliation_string":"IRCAM - CNRS UMR 9912, Sorbonne Universit\u00e9","institution_ids":["https://openalex.org/I4389425508","https://openalex.org/I35345632","https://openalex.org/I1294671590","https://openalex.org/I39804081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086267956","display_name":"Naotake Masuda","orcid":"https://orcid.org/0000-0001-8064-3038"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Naotake Masuda","raw_affiliation_strings":["University of Tokyo","University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tokyo","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014174539","display_name":"Axel Chemla--Romeu-Santos","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4389425508","display_name":"Sciences et Technologies de la Musique et du Son","ror":"https://ror.org/025xvn046","country_code":null,"type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I2802818602","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4210102700","https://openalex.org/I4389425508"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Axel Chemla--Romeu-Santos","raw_affiliation_strings":["IRCAM - CNRS UMR 9912, Sorbonne Universit\u00e9"],"affiliations":[{"raw_affiliation_string":"IRCAM - CNRS UMR 9912, Sorbonne Universit\u00e9","institution_ids":["https://openalex.org/I4389425508","https://openalex.org/I35345632","https://openalex.org/I1294671590","https://openalex.org/I39804081"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5086267956"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.2944,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.56345523,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5273","last_page":"5275"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9983999729156494,"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":0.982200026512146,"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/computer-science","display_name":"Computer science","score":0.7863937616348267},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5580137372016907},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5575302839279175},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5069582462310791},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.49807190895080566},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.48593631386756897},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4790550470352173},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4061928987503052},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3939773440361023},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33774131536483765},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.29381412267684937}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7863937616348267},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5580137372016907},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5575302839279175},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5069582462310791},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.49807190895080566},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48593631386756897},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4790550470352173},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4061928987503052},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3939773440361023},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33774131536483765},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.29381412267684937},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2020/767","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/767","pdf_url":"https://www.ijcai.org/proceedings/2020/0767.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/767","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/767","pdf_url":"https://www.ijcai.org/proceedings/2020/0767.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3040752496.pdf","grobid_xml":"https://content.openalex.org/works/W3040752496.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W1524247719","https://openalex.org/W1959608418","https://openalex.org/W2170699275","https://openalex.org/W2287082121","https://openalex.org/W2791716806","https://openalex.org/W2955263139","https://openalex.org/W2963090522","https://openalex.org/W2998588915"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4315836293","https://openalex.org/W4243888788","https://openalex.org/W2769884427","https://openalex.org/W2088690926","https://openalex.org/W2157165686","https://openalex.org/W2371215329","https://openalex.org/W1975359510"],"abstract_inverted_index":{"Audio":[0],"synthesizers":[1],"are":[2],"pervasive":[3],"in":[4,157],"modern":[5],"music":[6],"production.":[7],"These":[8],"highly":[9],"complex":[10],"audio":[11,67,73],"generation":[12],"functions":[13],"provide":[14],"a":[15,51,76,93,108,136],"unique":[16],"diversity":[17],"through":[18],"their":[19],"large":[20],"sets":[21],"of":[22,54,57,102,125,172,174],"parameters.":[23],"However,":[24],"this":[25],"feature":[26],"also":[27,106,164],"can":[28,153],"make":[29],"them":[30],"extremely":[31],"hard":[32],"and":[33,75,117,139,150,159,193],"obfuscated":[34],"to":[35,91,97,130,168,183,190],"use,":[36],"especially":[37],"for":[38,111],"non-expert":[39],"users":[40],"with":[41,198],"no":[42],"formal":[43],"knowledge":[44],"on":[45],"signal":[46],"processing.":[47],"We":[48],"recently":[49],"introduced":[50],"novel":[52],"formalization":[53],"the":[55,72,83,99,103,123,140,170,185,195,199],"problem":[56],"synthesizer":[58],"control":[59,116,171],"as":[60],"learning":[61],"an":[62,66],"invertible":[63],"mapping":[64],"between":[65,135],"latent":[68,79,187],"space,":[69,80,188],"extracted":[70,81],"from":[71,82,145],"signal,":[74],"target":[77],"parameter":[78,113],"synthesizer's":[84],"presets,":[85],"using":[86],"normalizing":[87],"flows.":[88],"In":[89],"addition":[90],"model":[92],"continuous":[94],"representation":[95],"allowing":[96,189],"ease":[98],"intuitive":[100],"exploration":[101],"synthesizer,":[104],"it":[105],"provides":[107],"ground-breaking":[109],"method":[110],"audio-based":[112],"inference,":[114],"vocal":[115],"macro-control":[118],"learning.":[119],"Here,":[120],"we":[121,163],"discuss":[122],"details":[124],"integrating":[126],"these":[127],"high-level":[128,147],"features":[129],"develop":[131],"new":[132],"interaction":[133,197],"schemes":[134],"human":[137],"user":[138],"generating":[141],"device:":[142],"parameters":[143,175],"inference":[144],"audio,":[146],"preset":[148],"visualization":[149],"interpolation,":[151],"that":[152],"be":[154],"used":[155],"both":[156,191],"off-time":[158],"real-time":[160],"situations.":[161],"Moreover,":[162],"leverage":[165],"LeapMotion":[166],"devices":[167],"allow":[169],"hundreds":[173],"simply":[176],"by":[177],"moving":[178],"one":[179],"hand":[180],"across":[181],"space":[182],"explore":[184],"low-dimensional":[186],"empower":[192],"facilitate":[194],"user's":[196],"synthesizer.":[200]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}