{"id":"https://openalex.org/W2933148111","doi":"https://doi.org/10.21437/interspeech.2019-2842","title":"Self-Supervised Speaker Embeddings","display_name":"Self-Supervised Speaker Embeddings","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2933148111","doi":"https://doi.org/10.21437/interspeech.2019-2842","mag":"2933148111"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2842","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2842","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","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/1904.03486","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061939508","display_name":"Themos Stafylakis","orcid":"https://orcid.org/0000-0002-9227-3588"},"institutions":[{"id":"https://openalex.org/I142263535","display_name":"University of Nottingham","ror":"https://ror.org/01ee9ar58","country_code":"GB","type":"education","lineage":["https://openalex.org/I142263535"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Themos Stafylakis","raw_affiliation_strings":["University of Nottingham, Nottingham, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Nottingham, Nottingham, United Kingdom","institution_ids":["https://openalex.org/I142263535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043239262","display_name":"Johan Rohdin","orcid":"https://orcid.org/0000-0003-0978-2064"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Johan Rohdin","raw_affiliation_strings":["Brno University of Technology, Brno, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Brno, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064238041","display_name":"Old\u0159ich Plchot","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Old\u0159ich Plchot","raw_affiliation_strings":["Brno University of Technology;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology;","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040000490","display_name":"Petr Mizera","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Petr Mizera","raw_affiliation_strings":["Brno University of Technology;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology;","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Luk\u00e1\u0161 Burget","raw_affiliation_strings":["Brno University of Technology;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology;","institution_ids":["https://openalex.org/I60587646"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5785,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74874645,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2863","last_page":"2867"},"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":0.9987000226974487,"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":0.9973999857902527,"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/embedding","display_name":"Embedding","score":0.7878105044364929},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7553084492683411},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6924864053726196},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6722503900527954},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6075180768966675},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5560168027877808},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.5281289219856262},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4257206320762634},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3834787607192993},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12626051902770996},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09388762712478638}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7878105044364929},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7553084492683411},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6924864053726196},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6722503900527954},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6075180768966675},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5560168027877808},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.5281289219856262},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4257206320762634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3834787607192993},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12626051902770996},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09388762712478638},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2019-2842","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2842","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1904.03486","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.03486","pdf_url":"https://arxiv.org/pdf/1904.03486","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":"","raw_type":"text"},{"id":"mag:2933148111","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1904.03486.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.1904.03486","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1904.03486","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:1904.03486","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.03486","pdf_url":"https://arxiv.org/pdf/1904.03486","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":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1027409586","display_name":null,"funder_award_id":"665860","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G1985226069","display_name":null,"funder_award_id":"GJ17-23870Y","funder_id":"https://openalex.org/F4320321006","funder_display_name":"Grantov\u00e1 Agentura \u010cesk\u00e9 Republiky"},{"id":"https://openalex.org/G7842005466","display_name":null,"funder_award_id":"Horizon 2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321006","display_name":"Grantov\u00e1 Agentura \u010cesk\u00e9 Republiky","ror":"https://ror.org/01pv73b02"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2933148111.pdf","grobid_xml":"https://content.openalex.org/works/W2933148111.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W2025768430","https://openalex.org/W2107638917","https://openalex.org/W2150769028","https://openalex.org/W2491474862","https://openalex.org/W2516631658","https://openalex.org/W2612434969","https://openalex.org/W2662639535","https://openalex.org/W2747238065","https://openalex.org/W2748466034","https://openalex.org/W2748488820","https://openalex.org/W2769112066","https://openalex.org/W2795132771","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2892620417","https://openalex.org/W2896462747","https://openalex.org/W2898974134","https://openalex.org/W2938358845","https://openalex.org/W2962788262","https://openalex.org/W2963341956","https://openalex.org/W2963395534","https://openalex.org/W2963432880","https://openalex.org/W2963450999","https://openalex.org/W2963465221","https://openalex.org/W2963712897","https://openalex.org/W2964058423","https://openalex.org/W2964121744","https://openalex.org/W2964135029","https://openalex.org/W3099206234"],"related_works":["https://openalex.org/W2963386851","https://openalex.org/W3162424266","https://openalex.org/W2949526695","https://openalex.org/W3046954891","https://openalex.org/W3163929126","https://openalex.org/W2795409001","https://openalex.org/W2952088347","https://openalex.org/W3108855822","https://openalex.org/W2898213692","https://openalex.org/W2892620417","https://openalex.org/W2887894196","https://openalex.org/W3011028252","https://openalex.org/W2936847140","https://openalex.org/W2900161882","https://openalex.org/W2949412037","https://openalex.org/W3158457675","https://openalex.org/W2916104401","https://openalex.org/W3025871231","https://openalex.org/W3164674954","https://openalex.org/W2947896218"],"abstract_inverted_index":{"Contrary":[0],"to":[1,15,31,42,73,134],"i-vectors,":[2],"speaker":[3,44,76,89,120],"embeddings":[4],"such":[5],"as":[6,110,129],"x-vectors":[7],"are":[8,145],"incapable":[9],"of":[10,35,51,60,64,98],"leveraging":[11],"unlabelled":[12,36],"utterances,":[13],"due":[14],"the":[16,33,49,57,65,74,88,94,99,118,124,142,156,159,167,175],"classification":[17,121],"loss":[18,105],"over":[19,174],"training":[20,29],"speakers.":[21],"In":[22,123,139],"this":[23,70],"paper,":[24],"we":[25,83,170],"explore":[26],"an":[27,151],"alternative":[28],"strategy":[30],"enable":[32],"use":[34],"utterances":[37],"in":[38,150,166],"training.":[39,138],"We":[40,68,154],"propose":[41],"train":[43],"embedding":[45,59,77],"extractors":[46],"via":[47],"reconstructing":[48],"frames":[50],"a":[52,79,111,130],"target":[53,100],"speech":[54,62],"segment,":[55],"given":[56],"inferred":[58],"another":[61],"segment":[63],"same":[66],"utterance.":[67],"do":[69],"by":[71],"attaching":[72],"standard":[75,119],"extractor":[78],"decoder":[80],"network,":[81],"which":[82],"feed":[84],"not":[85],"merely":[86],"with":[87,93,117],"embedding,":[90],"but":[91],"also":[92],"estimated":[95],"phone":[96],"sequence":[97],"frame":[101],"sequence.":[102],"The":[103],"reconstruction":[104],"can":[106],"be":[107,115],"used":[108],"either":[109],"single":[112],"objective,":[113],"or":[114],"combined":[116],"loss.":[122],"latter":[125],"case,":[126],"it":[127],"acts":[128],"regularizer,":[131],"encouraging":[132],"generalizability":[133],"speakers":[135],"unseen":[136],"during":[137],"all":[140],"cases,":[141],"proposed":[143,160],"architectures":[144],"trained":[146],"from":[147,158],"scratch":[148],"and":[149,164,169],"end-to-end":[152],"fashion.":[153],"demonstrate":[155],"benefits":[157],"approach":[161],"on":[162],"VoxCeleb":[163],"Speakers":[165],"wild,":[168],"report":[171],"notable":[172],"improvements":[173],"baseline.":[176]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3}],"updated_date":"2026-06-20T22:02:38.213706","created_date":"2025-10-10T00:00:00"}
