{"id":"https://openalex.org/W4388118623","doi":"https://doi.org/10.23919/eusipco58844.2023.10289926","title":"Improved Disentangled Speech Representations Using Contrastive Learning in Factorized Hierarchical Variational Autoencoder","display_name":"Improved Disentangled Speech Representations Using Contrastive Learning in Factorized Hierarchical Variational Autoencoder","publication_year":2023,"publication_date":"2023-09-04","ids":{"openalex":"https://openalex.org/W4388118623","doi":"https://doi.org/10.23919/eusipco58844.2023.10289926"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco58844.2023.10289926","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/eusipco58844.2023.10289926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2211.08191","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069800152","display_name":"Yuying Xie","orcid":"https://orcid.org/0000-0002-4804-2176"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Yuying Xie","raw_affiliation_strings":["Aalborg University,Department of Electronic Systems,Denmark","Department of Electronic Systems, Aalborg University, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University,Department of Electronic Systems,Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001695391","display_name":"Thomas Arildsen","orcid":"https://orcid.org/0000-0003-3254-3790"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Thomas Arildsen","raw_affiliation_strings":["Aalborg University,Department of Electronic Systems,Denmark","Department of Electronic Systems, Aalborg University, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University,Department of Electronic Systems,Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090108098","display_name":"Zheng\u2010Hua Tan","orcid":"https://orcid.org/0000-0001-6856-8928"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Zheng-Hua Tan","raw_affiliation_strings":["Aalborg University,Department of Electronic Systems,Denmark","Department of Electronic Systems, Aalborg University, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University,Department of Electronic Systems,Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I891191580"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1330","last_page":"1334"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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/T11309","display_name":"Music and Audio Processing","score":0.9979000091552734,"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/latent-variable","display_name":"Latent variable","score":0.7368301749229431},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.708133339881897},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6267474889755249},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6146124601364136},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.570233166217804},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5620070099830627},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5346670746803284},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48862940073013306},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.477719783782959},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.47217458486557007},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.45348095893859863},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4137459397315979},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3380472660064697},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3275689482688904},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2580421268939972},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.22497665882110596},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.14991572499275208}],"concepts":[{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.7368301749229431},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.708133339881897},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6267474889755249},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6146124601364136},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.570233166217804},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5620070099830627},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5346670746803284},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48862940073013306},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.477719783782959},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.47217458486557007},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.45348095893859863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4137459397315979},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3380472660064697},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3275689482688904},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2580421268939972},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.22497665882110596},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.14991572499275208},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/eusipco58844.2023.10289926","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/eusipco58844.2023.10289926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/a1f703af-4424-4079-9317-3826606c217f","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/a1f703af-4424-4079-9317-3826606c217f","pdf_url":"https://arxiv.org/pdf/2211.08191","source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Xie, Y, Arildsen, T & Tan, Z H 2023, Improved Disentangled Speech Representations Using Contrastive Learning in Factorized Hierarchical Variational Autoencoder. in 31st European Signal Processing Conference, EUSIPCO 2023 - Proceedings. IEEE (Institute of Electrical and Electronics Engineers), European Signal Processing Conference, pp. 1330-1334, 31st European Signal Processing Conference, EUSIPCO 2023, Helsinki, Finland, 04/09/2023. https://doi.org/10.23919/EUSIPCO58844.2023.10289926","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:publications/a1f703af-4424-4079-9317-3826606c217f","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/a1f703af-4424-4079-9317-3826606c217f","pdf_url":"https://arxiv.org/pdf/2211.08191","source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Xie, Y, Arildsen, T & Tan, Z H 2023, Improved Disentangled Speech Representations Using Contrastive Learning in Factorized Hierarchical Variational Autoencoder. in 31st European Signal Processing Conference, EUSIPCO 2023 - Proceedings. IEEE (Institute of Electrical and Electronics Engineers), European Signal Processing Conference, pp. 1330-1334, 31st European Signal Processing Conference, EUSIPCO 2023, Helsinki, Finland, 04/09/2023. https://doi.org/10.23919/EUSIPCO58844.2023.10289926","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388118623.pdf","grobid_xml":"https://content.openalex.org/works/W4388118623.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W2138621090","https://openalex.org/W2163922914","https://openalex.org/W2187089797","https://openalex.org/W2758785877","https://openalex.org/W2949811029","https://openalex.org/W2962788625","https://openalex.org/W3035524453","https://openalex.org/W3045886598","https://openalex.org/W3092028330","https://openalex.org/W3098439673","https://openalex.org/W3099631870","https://openalex.org/W3140429000","https://openalex.org/W3162390194","https://openalex.org/W3200754814","https://openalex.org/W4221141917","https://openalex.org/W4225322394","https://openalex.org/W4225329057","https://openalex.org/W4225939199","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6745117592","https://openalex.org/W6756663807","https://openalex.org/W6762533536","https://openalex.org/W6783867762"],"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/W2803255133","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W4386815338","https://openalex.org/W2988134182"],"abstract_inverted_index":{"Leveraging":[0],"the":[1,39,44,72,84,96,99,110,115,122,149,166,180,188,199,209],"fact":[2],"that":[3,208],"speaker":[4,47,116,175,181,214],"identity":[5,48,76,117,182,215],"and":[6,62,177,184,216,223],"content":[7,189,217],"vary":[8],"on":[9,198,229],"different":[10,19,35],"time":[11],"scales,":[12],"factorized":[13],"hierarchical":[14],"variational":[15],"autoencoder":[16],"(FHVAE)":[17],"uses":[18],"latent":[20,41],"variables":[21,77,118],"to":[22,83,113,221],"symbolize":[23],"these":[24,29],"two":[25],"attributes.":[26],"Disentanglement":[27],"of":[28,38,46,86,98,134,193,201],"attributes":[30],"is":[31,53,92,156],"carried":[32],"out":[33],"by":[34],"prior":[36,45,100],"settings":[37],"corresponding":[40],"variables.":[42],"For":[43],"variable,":[49,183],"FHVAE":[50,111],"assumes":[51],"it":[52],"a":[54,63,68],"Gaussian":[55],"distribution":[56],"with":[57],"an":[58],"utterance-scale":[59],"varying":[60],"mean":[61,85,97],"fixed":[64,70],"variance.":[65],"By":[66],"setting":[67],"small":[69],"variance,":[71],"training":[73,150],"process":[74],"promotes":[75],"within":[78],"one":[79],"utterance":[80],"gathering":[81,119],"close":[82],"their":[87],"prior.":[88],"However,":[89],"this":[90,145,169],"constraint":[91],"relatively":[93],"weak,":[94],"as":[95,128,130,165],"changes":[101],"between":[102],"utterances.":[103],"Therefore,":[104],"we":[105],"introduce":[106],"contrastive":[107],"learning":[108],"into":[109],"framework,":[112],"make":[114],"when":[120],"representing":[121],"same":[123],"speaker,":[124],"while":[125],"distancing":[126],"themselves":[127],"far":[129],"possible":[131],"from":[132],"those":[133],"other":[135],"speakers.":[136],"The":[137],"model":[138],"structure":[139],"has":[140,162,224],"not":[141],"been":[142,163],"changed":[143],"in":[144,168],"work":[146],"but":[147],"only":[148],"process,":[151],"thus":[152],"no":[153],"additional":[154],"cost":[155],"needed":[157],"during":[158],"testing.":[159],"Voice":[160],"conversion":[161,195],"chosen":[164],"application":[167],"paper.":[170],"Latent":[171],"variable":[172],"evaluations":[173],"include":[174],"verification":[176],"identification":[178],"for":[179,187],"speech":[185,203],"recognition":[186],"variable.":[190],"Furthermore,":[191],"assessments":[192],"voice":[194],"performance":[196,226],"are":[197],"grounds":[200],"fake":[202],"detection":[204],"experiments.":[205],"Results":[206],"show":[207],"proposed":[210],"method":[211],"improves":[212],"both":[213],"feature":[218],"extraction":[219],"compared":[220],"FHVAE,":[222],"better":[225],"than":[227],"baseline":[228],"conversion.":[230]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}