{"id":"https://openalex.org/W3200754814","doi":"https://doi.org/10.1109/mlsp52302.2021.9596320","title":"Disentangled Speech Representation Learning Based on Factorized Hierarchical Variational Autoencoder with Self-Supervised Objective","display_name":"Disentangled Speech Representation Learning Based on Factorized Hierarchical Variational Autoencoder with Self-Supervised Objective","publication_year":2021,"publication_date":"2021-10-25","ids":{"openalex":"https://openalex.org/W3200754814","doi":"https://doi.org/10.1109/mlsp52302.2021.9596320","mag":"3200754814"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp52302.2021.9596320","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp52302.2021.9596320","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2204.02166","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University","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":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9980999827384949,"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/T10860","display_name":"Speech and Audio Processing","score":0.9943000078201294,"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/autoencoder","display_name":"Autoencoder","score":0.8126662969589233},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8010474443435669},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.6438151597976685},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.607153058052063},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5830572843551636},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5475623607635498},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47309592366218567},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4430122971534729},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4274214506149292},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.41408392786979675},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.41261544823646545},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3941973149776459},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.32658851146698},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.14513948559761047}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8126662969589233},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8010474443435669},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.6438151597976685},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.607153058052063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5830572843551636},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5475623607635498},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47309592366218567},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4430122971534729},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4274214506149292},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.41408392786979675},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.41261544823646545},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3941973149776459},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32658851146698},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.14513948559761047},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/mlsp52302.2021.9596320","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp52302.2021.9596320","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2204.02166","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.02166","pdf_url":"https://arxiv.org/pdf/2204.02166","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:pure.atira.dk:publications/0dd427a9-492f-4bac-a320-160a83ea6aab","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/0dd427a9-492f-4bac-a320-160a83ea6aab","pdf_url":"https://arxiv.org/pdf/2204.02166.pdf","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":null,"raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.atira.dk:publications/0dd427a9-492f-4bac-a320-160a83ea6aab","is_oa":false,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85122805866&partnerID=8YFLogxK","pdf_url":null,"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":null,"raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2204.02166","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.02166","pdf_url":"https://arxiv.org/pdf/2204.02166","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1635512741","https://openalex.org/W1959608418","https://openalex.org/W2163922914","https://openalex.org/W2264800663","https://openalex.org/W2290689761","https://openalex.org/W2758785877","https://openalex.org/W2963618559","https://openalex.org/W2963659646","https://openalex.org/W2972530081","https://openalex.org/W2972943112","https://openalex.org/W2997079913","https://openalex.org/W3015419784","https://openalex.org/W3015699566","https://openalex.org/W3016011332","https://openalex.org/W3016243847","https://openalex.org/W3107942086","https://openalex.org/W3126776772","https://openalex.org/W3157923770","https://openalex.org/W3162390194","https://openalex.org/W3197580070","https://openalex.org/W6631362777","https://openalex.org/W6640963894","https://openalex.org/W6745117592","https://openalex.org/W6772199901","https://openalex.org/W6772384842"],"related_works":["https://openalex.org/W2983142544","https://openalex.org/W2891059443","https://openalex.org/W4281663961","https://openalex.org/W3208888551","https://openalex.org/W4313561566","https://openalex.org/W3208386644","https://openalex.org/W4220682630","https://openalex.org/W4389832810","https://openalex.org/W3163146846","https://openalex.org/W3133533225"],"abstract_inverted_index":{"Disentangled":[0],"representation":[1,74,163],"learning":[2,75],"aims":[3],"to":[4,22,80,141,175],"extract":[5],"explanatory":[6],"features":[7,62,143],"or":[8],"factors":[9],"and":[10,29,36,59,152,168],"retain":[11],"salient":[12],"information.":[13],"Factorized":[14],"hierarchical":[15],"variational":[16],"autoencoder":[17],"(FHVAE)":[18],"presents":[19],"a":[20,24,42],"way":[21],"disentangle":[23],"speech":[25,37,61,150],"signal":[26],"into":[27,85],"sequential-level":[28],"segmental-level":[30],"features,":[31],"which":[32],"represent":[33],"speaker":[34,153],"identity":[35],"content":[38],"information,":[39],"respectively.":[40],"As":[41],"self-supervised":[43,137],"objective,":[44],"autoregressive":[45],"predictive":[46],"coding":[47],"(APC),":[48],"on":[49,125,181],"the":[50,69,82,86,93,126,135,178],"other":[51],"hand,":[52],"has":[53,165],"been":[54,166],"used":[55],"in":[56],"extracting":[57],"meaningful":[58,116],"transferable":[60],"for":[63,147],"multiple":[64],"downstream":[65],"tasks.":[66],"Inspired":[67],"by":[68],"success":[70],"of":[71,161,177],"these":[72],"two":[73],"methods,":[76],"this":[77],"paper":[78],"proposes":[79],"integrate":[81],"APC":[83],"objective":[84,138],"FHVAE":[87,132],"framework":[88,180],"aiming":[89],"at":[90,110],"benefiting":[91],"from":[92],"additional":[94,136],"self-supervision":[95],"target.":[96],"The":[97,121,170],"main":[98],"proposed":[99],"method":[100],"requires":[101],"neither":[102],"more":[103,107],"training":[104],"data":[105],"nor":[106],"computational":[108],"cost":[109],"test":[111],"time,":[112],"but":[113],"obtains":[114],"improved":[115],"representations":[117],"while":[118],"maintaining":[119],"disentanglement.":[120],"experiments":[122],"were":[123],"conducted":[124],"TIMIT":[127],"dataset.":[128],"Results":[129],"demonstrate":[130],"that":[131],"equipped":[133],"with":[134],"is":[139],"able":[140],"learn":[142],"providing":[144],"superior":[145],"performance":[146,173],"tasks":[148],"including":[149],"recognition":[151],"recognition.":[154],"Furthermore,":[155],"voice":[156,182],"conversion,":[157],"as":[158],"one":[159],"application":[160],"disentangled":[162],"learning,":[164],"applied":[167],"evaluated.":[169],"results":[171],"show":[172],"similar":[174],"baseline":[176],"new":[179],"conversion.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}