{"id":"https://openalex.org/W2903005299","doi":"https://doi.org/10.5281/zenodo.1492372","title":"Bridging Audio Analysis, Perception and Synthesis with Perceptually-regularized Variational Timbre Spaces","display_name":"Bridging Audio Analysis, Perception and Synthesis with Perceptually-regularized Variational Timbre Spaces","publication_year":2018,"publication_date":"2018-09-23","ids":{"openalex":"https://openalex.org/W2903005299","doi":"https://doi.org/10.5281/zenodo.1492372","mag":"2903005299"},"language":"en","primary_location":{"id":"pmh:oai:zenodo.org:1492373","doi":null,"is_oa":true,"landing_page_url":"https://zenodo.org/record/1492373","pdf_url":"https://zenodo.org/record/1492373","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/1492373","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085170922","display_name":"Philippe Esling","orcid":"https://orcid.org/0000-0002-1655-7909","observed_orcids":["https://orcid.org/0000-0002-1655-7909"]},"institutions":[{"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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Esling, Philippe","raw_affiliation_strings":["Sorbonne Universit\u00e9, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sorbonne Universit\u00e9, Paris, France","institution_ids":["https://openalex.org/I39804081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014174539","display_name":"Axel Chemla--Romeu-Santos","orcid":"https://orcid.org/0000-0001-7329-6533","observed_orcids":["https://orcid.org/0000-0001-7329-6533"]},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Chemla--Romeu-Santos, Axel","raw_affiliation_strings":["University of Milan, Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Milan, Milan, Italy","institution_ids":["https://openalex.org/I189158943"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053447586","display_name":"Adrien Bitton","orcid":null,"observed_orcids":[]},"institutions":[{"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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Bitton, Adrien","raw_affiliation_strings":["Institut de Recherche et Coordination Acoustique Musique, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut de Recherche et Coordination Acoustique Musique, Paris, France","institution_ids":["https://openalex.org/I35345632"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1016,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.9378125,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"175","last_page":"181"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.989300012588501,"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":0.989300012588501,"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":0.00989999994635582,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/timbre","display_name":"timbre","score":0.8500000238418579},{"id":"https://openalex.org/keywords/timbre-space","display_name":"timbre space","score":0.6669999957084656},{"id":"https://openalex.org/keywords/variational-autoencoder","display_name":"variational autoencoder","score":0.8190000057220459},{"id":"https://openalex.org/keywords/latent-space-regularization","display_name":"latent space regularization","score":0.847000002861023},{"id":"https://openalex.org/keywords/perceptual-similarity","display_name":"perceptual similarity","score":0.8230000138282776},{"id":"https://openalex.org/keywords/sound-synthesis","display_name":"sound synthesis","score":0.5440000295639038},{"id":"https://openalex.org/keywords/audio-classification","display_name":"audio classification","score":0.871999979019165},{"id":"https://openalex.org/keywords/audio-descriptors","display_name":"audio descriptors","score":0.8109999895095825},{"id":"https://openalex.org/keywords/music-perception","display_name":"music perception","score":0.48399999737739563},{"id":"https://openalex.org/keywords/generative-models","display_name":"generative models","score":0.6589999794960022}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.856106162071228},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6180415749549866},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6175056099891663},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.6081757545471191},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5615597367286682},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09319469332695007},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.06495961546897888},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:zenodo.org:1492373","doi":null,"is_oa":true,"landing_page_url":"https://zenodo.org/record/1492373","pdf_url":"https://zenodo.org/record/1492373","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"},{"id":"doi:10.5281/zenodo.1492372","doi":"https://doi.org/10.5281/zenodo.1492372","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.1492372","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.5281/zenodo.1492373","doi":"https://doi.org/10.5281/zenodo.1492373","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.1492373","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},{"id":"mag:2903005299","doi":null,"is_oa":false,"landing_page_url":"http://ismir2018.ircam.fr/doc/pdfs/219_Paper.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306420076","display_name":"International Symposium/Conference on Music Information Retrieval","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Symposium/Conference on Music Information Retrieval","raw_type":null}],"best_oa_location":{"id":"pmh:oai:zenodo.org:1492373","doi":null,"is_oa":true,"landing_page_url":"https://zenodo.org/record/1492373","pdf_url":"https://zenodo.org/record/1492373","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2903005299.pdf","grobid_xml":"https://content.openalex.org/works/W2903005299.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1501437548","https://openalex.org/W1663973292","https://openalex.org/W1959608418","https://openalex.org/W1986595194","https://openalex.org/W2043317581","https://openalex.org/W2074075027","https://openalex.org/W2164767140","https://openalex.org/W2399306074","https://openalex.org/W2519091744","https://openalex.org/W2584032004","https://openalex.org/W2605762339","https://openalex.org/W2606176153","https://openalex.org/W2964121744"],"related_works":["https://openalex.org/W2810655876","https://openalex.org/W6888632738","https://openalex.org/W7139088309","https://openalex.org/W3047431472","https://openalex.org/W3160669408","https://openalex.org/W2804722844","https://openalex.org/W4312120655","https://openalex.org/W2952523162","https://openalex.org/W4387830621","https://openalex.org/W3040787347"],"abstract_inverted_index":{"Generative":[0],"models":[1],"aim":[2],"to":[3,32,42,52,66,101,121,185,192],"understand":[4,43],"the":[5,10,22,26,98,153,168,202],"properties":[6,129],"of":[7,12,90,114,196,205,216],"data,":[8],"through":[9],"construction":[11],"latent":[13,27,99,154],"spaces":[14,54,100,122,137],"that":[15,82,118,123,135,158,208],"allow":[16],"classification":[17],"and":[18,69,92,116,130,156],"generation.":[19],"However,":[20,61],"as":[21,181],"learning":[23],"is":[24],"unsupervised,":[25],"dimensions":[28,155],"are":[29,124,150],"not":[30,64,71],"related":[31],"perceptual":[33,57,103,131,194],"properties.":[34],"In":[35],"parallel,":[36],"music":[37],"perception":[38],"research":[39,91],"has":[40],"aimed":[41],"timbre":[44,53,107,217],"based":[45],"on":[46],"human":[47],"dissimilarity":[48],"ratings.":[49],"These":[50],"lead":[51,120],"which":[55],"exhibit":[56,172,201],"similarities":[58,195],"between":[59],"sounds.":[60],"they":[62,119,170],"do":[63,70],"generalize":[65],"novel":[67,186,197],"examples":[68],"provide":[72],"an":[73],"invertible":[74],"mapping,":[75],"preventing":[76],"audio":[77,143,148],"synthesis.":[78],"Here,":[79],"we":[80,110,200],"show":[81,117,134,157,179],"Variational":[83],"Auto-Encoders":[84],"(VAE)":[85],"can":[86,138,189,209],"bridge":[87],"these":[88,136],"lines":[89],"alleviate":[93],"their":[94],"weaknesses":[95],"by":[96],"regularizing":[97],"match":[102],"distances":[104],"collected":[105],"from":[106],"studies.":[108],"Hence,":[109],"propose":[111],"three":[112],"types":[113],"regularization":[115],"simultaneously":[125],"coherent":[126],"with":[127,213],"signal":[128],"similarities.":[132],"We":[133,145,177],"be":[139,190],"used":[140,191],"for":[141],"efficient":[142],"classification.":[144],"study":[146],"how":[147],"descriptors":[149,161],"organized":[151],"along":[152],"even":[159],"though":[160],"behave":[162],"in":[163],"a":[164,173],"non-linear":[165],"way":[166],"across":[167],"space,":[169],"still":[171],"locally":[174],"smooth":[175],"evolution.":[176],"also":[178],"that,":[180],"this":[182],"space":[183],"generalizes":[184],"samples,":[187],"it":[188],"predict":[193],"instruments.":[198],"Finally,":[199],"generative":[203],"capabilities":[204],"our":[206],"spaces,":[207],"directly":[210],"synthesize":[211],"sounds":[212],"continuous":[214],"evolution":[215],"perception.":[218]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2018-12-11T00:00:00"}
