{"id":"https://openalex.org/W3134889661","doi":"https://doi.org/10.1109/icassp39728.2021.9414487","title":"Contrastive Predictive Coding Supported Factorized Variational Autoencoder For Unsupervised Learning Of Disentangled Speech Representations","display_name":"Contrastive Predictive Coding Supported Factorized Variational Autoencoder For Unsupervised Learning Of Disentangled Speech Representations","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3134889661","doi":"https://doi.org/10.1109/icassp39728.2021.9414487","mag":"3134889661"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414487","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414487","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/2005.12963","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055580486","display_name":"Janek Ebbers","orcid":null},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Janek Ebbers","raw_affiliation_strings":["Paderborn University, Paderborn, Germany","Paderborn Univ"],"affiliations":[{"raw_affiliation_string":"Paderborn University, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]},{"raw_affiliation_string":"Paderborn Univ","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009710583","display_name":"Michael Kuhlmann","orcid":"https://orcid.org/0000-0003-3664-6922"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Kuhlmann","raw_affiliation_strings":["Paderborn University, Paderborn, Germany","Paderborn Univ"],"affiliations":[{"raw_affiliation_string":"Paderborn University, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]},{"raw_affiliation_string":"Paderborn Univ","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029591169","display_name":"Tobias Cord-Landwehr","orcid":null},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tobias Cord-Landwehr","raw_affiliation_strings":["Paderborn University, Paderborn, Germany","Paderborn Univ"],"affiliations":[{"raw_affiliation_string":"Paderborn University, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]},{"raw_affiliation_string":"Paderborn Univ","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082075598","display_name":"Reinhold Haeb\u2010Umbach","orcid":"https://orcid.org/0000-0001-9468-7330"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Reinhold Haeb-Umbach","raw_affiliation_strings":["Paderborn University, Paderborn, Germany","Paderborn Univ"],"affiliations":[{"raw_affiliation_string":"Paderborn University, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]},{"raw_affiliation_string":"Paderborn Univ","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5055580486"],"corresponding_institution_ids":["https://openalex.org/I206945453"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0326234,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"3860","last_page":"3864"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9980000257492065,"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/T11309","display_name":"Music and Audio Processing","score":0.9970999956130981,"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":0.9471198916435242},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7918635010719299},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7241486310958862},{"id":"https://openalex.org/keywords/predictive-coding","display_name":"Predictive coding","score":0.6808191537857056},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6035969257354736},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5649474263191223},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5404869318008423},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5171374678611755},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.472973495721817},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4241345524787903},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4182566702365875},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3857964873313904},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.2974661588668823},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1305852234363556}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.9471198916435242},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7918635010719299},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7241486310958862},{"id":"https://openalex.org/C2778061373","wikidata":"https://www.wikidata.org/wiki/Q1315146","display_name":"Predictive coding","level":3,"score":0.6808191537857056},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6035969257354736},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5649474263191223},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5404869318008423},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5171374678611755},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.472973495721817},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4241345524787903},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4182566702365875},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3857964873313904},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2974661588668823},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1305852234363556},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414487","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414487","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2005.12963","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.12963","pdf_url":"https://arxiv.org/pdf/2005.12963","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:3134889661","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2005.12963.pdf","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.2005.12963","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2005.12963","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"},{"id":"doi:10.17023/c5db-ev97","is_oa":true,"landing_page_url":"https://doi.org/10.17023/c5db-ev97","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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:2005.12963","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.12963","pdf_url":"https://arxiv.org/pdf/2005.12963","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":[{"display_name":"Reduced inequalities","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3134889661.pdf","grobid_xml":"https://content.openalex.org/works/W3134889661.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1959608418","https://openalex.org/W2099621636","https://openalex.org/W2150769028","https://openalex.org/W2502312327","https://openalex.org/W2532494225","https://openalex.org/W2603777577","https://openalex.org/W2752796333","https://openalex.org/W2753738274","https://openalex.org/W2799121188","https://openalex.org/W2842511635","https://openalex.org/W2939131199","https://openalex.org/W2946555236","https://openalex.org/W2949281321","https://openalex.org/W2962752582","https://openalex.org/W2963104724","https://openalex.org/W2963618559","https://openalex.org/W2963799213","https://openalex.org/W2963830550","https://openalex.org/W2964121744","https://openalex.org/W2964127395","https://openalex.org/W2972659941","https://openalex.org/W3015434413","https://openalex.org/W3020570669","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6640963894","https://openalex.org/W6675409298","https://openalex.org/W6724804524","https://openalex.org/W6739139180","https://openalex.org/W6744627333","https://openalex.org/W6745117592","https://openalex.org/W6748223763","https://openalex.org/W6748391871","https://openalex.org/W6762533536","https://openalex.org/W6776390925","https://openalex.org/W6955712162"],"related_works":["https://openalex.org/W3162390194","https://openalex.org/W3160567113","https://openalex.org/W3125709657","https://openalex.org/W3166174815","https://openalex.org/W2949510815","https://openalex.org/W3121737235","https://openalex.org/W3096474940","https://openalex.org/W3094247854","https://openalex.org/W3016175755","https://openalex.org/W3163187953","https://openalex.org/W2950523597","https://openalex.org/W2899069432","https://openalex.org/W3131643166","https://openalex.org/W2788991015","https://openalex.org/W2801581493","https://openalex.org/W1796128977","https://openalex.org/W1595761392","https://openalex.org/W3027324582","https://openalex.org/W2964307722","https://openalex.org/W2467417825"],"abstract_inverted_index":{"In":[0],"this":[1],"work":[2],"we":[3,33],"address":[4],"disentanglement":[5,41,74],"of":[6,59,87],"style":[7,28],"and":[8,26,62,70],"content":[9,24,63,89],"in":[10],"speech":[11],"signals.":[12],"We":[13,51,81],"propose":[14,34],"a":[15,23,27,92],"fully":[16],"convolutional":[17],"variational":[18],"autoencoder":[19],"employing":[20],"two":[21,67],"encoders:":[22],"encoder":[25],"encoder.":[29],"To":[30],"foster":[31],"disentanglement,":[32],"adversarial":[35],"contrastive":[36],"predictive":[37],"coding.":[38],"This":[39],"new":[40],"method":[42],"does":[43],"neither":[44],"need":[45],"parallel":[46],"data":[47],"nor":[48],"any":[49],"supervision.":[50],"show":[52,71],"that":[53],"the":[54,66,88],"proposed":[55],"technique":[56],"is":[57],"capable":[58],"separating":[60],"speaker":[61],"traits":[64],"into":[65],"different":[68],"representations":[69],"competitive":[72],"speaker-content":[73],"performance":[75],"compared":[76,95],"to":[77,96],"other":[78],"unsupervised":[79],"approaches.":[80],"further":[82],"demonstrate":[83],"an":[84],"increased":[85],"robustness":[86],"representation":[90],"against":[91],"train-test":[93],"mismatch":[94],"spectral":[97],"features,":[98],"when":[99],"used":[100],"for":[101],"phone":[102],"recognition.":[103]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}