{"id":"https://openalex.org/W3094247854","doi":"https://doi.org/10.21437/interspeech.2021-1936","title":"Unsupervised Learning of Disentangled Speech Content and Style Representation","display_name":"Unsupervised Learning of Disentangled Speech Content and Style Representation","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3094247854","doi":"https://doi.org/10.21437/interspeech.2021-1936","mag":"3094247854"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1936","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1936","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.12973","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038296765","display_name":"Andros Tjandra","orcid":"https://orcid.org/0000-0003-1246-5908"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Andros Tjandra","raw_affiliation_strings":["Nara Institute of Science and Technology, Ikoma, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Ikoma, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112901893","display_name":"Ruoming Pang","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruoming Pang","raw_affiliation_strings":["Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433648","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0002-9505-1833"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036532214","display_name":"Shigeki Karita","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shigeki Karita","raw_affiliation_strings":["Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5038296765"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":0.14,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.51211974,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4089","last_page":"4093"},"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/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"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":0.9961000084877014,"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":0.7166032195091248},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6910108923912048},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6517032384872437},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.6382068395614624},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6381180882453918},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6288246512413025},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.6236600875854492},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5235628485679626},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.46041280031204224},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4501962661743164},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4395497739315033}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7166032195091248},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6910108923912048},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6517032384872437},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6382068395614624},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6381180882453918},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6288246512413025},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.6236600875854492},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5235628485679626},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.46041280031204224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4501962661743164},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4395497739315033},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-1936","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1936","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2010.12973","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.12973","pdf_url":"https://arxiv.org/pdf/2010.12973","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3094247854","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2010.12973","pdf_url":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2010.12973","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.12973","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.12973","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.12973","pdf_url":"https://arxiv.org/pdf/2010.12973","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3094247854.pdf","grobid_xml":"https://content.openalex.org/works/W3094247854.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1959608418","https://openalex.org/W2099471712","https://openalex.org/W2792263949","https://openalex.org/W2803832867","https://openalex.org/W2842511635","https://openalex.org/W2902070858","https://openalex.org/W2946006146","https://openalex.org/W2962793481","https://openalex.org/W2963272440","https://openalex.org/W2963341956","https://openalex.org/W2963568578","https://openalex.org/W2963618559","https://openalex.org/W2963799213","https://openalex.org/W2963873275","https://openalex.org/W2964307104","https://openalex.org/W2973049979","https://openalex.org/W3015212100","https://openalex.org/W3043747271","https://openalex.org/W3096216486","https://openalex.org/W3097777922","https://openalex.org/W3099782249","https://openalex.org/W3125709657","https://openalex.org/W3140968660"],"related_works":["https://openalex.org/W3197103763","https://openalex.org/W2983539408","https://openalex.org/W2291725357","https://openalex.org/W2118860825","https://openalex.org/W3049360585","https://openalex.org/W2788991015","https://openalex.org/W134006180","https://openalex.org/W3131643166","https://openalex.org/W3023996010","https://openalex.org/W1942713348","https://openalex.org/W2949510815","https://openalex.org/W3208516011","https://openalex.org/W1981883218","https://openalex.org/W2603213385","https://openalex.org/W2897548994","https://openalex.org/W3096474940","https://openalex.org/W2890704021","https://openalex.org/W2037536661","https://openalex.org/W3047003947","https://openalex.org/W3125709657"],"abstract_inverted_index":{"We":[0],"present":[1],"an":[2,105],"approach":[3],"for":[4],"unsupervised":[5],"learning":[6],"of":[7,98],"speech":[8,41,58,62,90],"representation":[9],"disentangling":[10],"contents":[11],"and":[12,34,44,125],"styles.":[13],"Our":[14,48],"model":[15,119],"consists":[16],"of:":[17],"(1)":[18,52],"a":[19,27,36,76,116],"local":[20,43,54],"encoder":[21,29],"that":[22,30,39,51],"captures":[23,31],"per-frame":[24],"information;":[25,33],"(2)":[26,80],"global":[28,45,78,82,100,122],"per-utterance":[32],"(3)":[35],"conditional":[37],"decoder":[38],"reconstructs":[40],"given":[42],"latent":[46,55,83,123],"variables.":[47],"experiments":[49],"show":[50],"the":[53,81,95,99,121],"variables":[56,84,124],"encode":[57,85],"contents,":[59],"as":[60,88,132,135],"reconstructed":[61,89],"can":[63,114],"be":[64],"recognized":[65],"by":[66,129],"ASR":[67],"with":[68,75,94,131],"low":[69],"word":[70],"error":[71],"rates":[72],"(WER),":[73],"even":[74],"different":[77],"encoding;":[79],"speaker":[86,92,117],"style,":[87],"shares":[91],"identity":[93],"source":[96],"utterance":[97],"encoding.":[101],"Additionally,":[102],"we":[103,113],"demonstrate":[104],"useful":[106],"application":[107],"from":[108,120],"our":[109],"pre-trained":[110],"model,":[111],"where":[112],"train":[115],"recognition":[118],"achieve":[126],"high":[127],"accuracy":[128],"fine-tuning":[130],"few":[133],"data":[134],"one":[136],"label":[137],"per":[138],"speaker.":[139]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}