{"id":"https://openalex.org/W3143367551","doi":"https://doi.org/10.21437/interspeech.2021-941","title":"ECAPA-TDNN Embeddings for Speaker Diarization","display_name":"ECAPA-TDNN Embeddings for Speaker Diarization","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3143367551","doi":"https://doi.org/10.21437/interspeech.2021-941","mag":"3143367551"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-941","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-941","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":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.01466","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067313233","display_name":"Nauman Dawalatabad","orcid":"https://orcid.org/0000-0003-1592-6300"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]},{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]}],"countries":["CA","IN"],"is_corresponding":false,"raw_author_name":"Nauman Dawalatabad","raw_affiliation_strings":["Mila -Quebec Artificial Intelligence Institute, Canada","Indian Institute of Technology Madras, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mila -Quebec Artificial Intelligence Institute, Canada","institution_ids":["https://openalex.org/I4210164802"]},{"raw_affiliation_string":"Indian Institute of Technology Madras, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040811098","display_name":"Mirco Ravanelli","orcid":"https://orcid.org/0000-0002-3929-5526"},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mirco Ravanelli","raw_affiliation_strings":["Mila -Quebec Artificial Intelligence Institute, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mila -Quebec Artificial Intelligence Institute, Canada","institution_ids":["https://openalex.org/I4210164802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045901453","display_name":"Fran\u00e7ois Grondin","orcid":"https://orcid.org/0000-0002-0563-4251"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fran\u00e7ois Grondin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022199264","display_name":"Jenthe Thienpondt","orcid":"https://orcid.org/0000-0001-5990-722X"},"institutions":[{"id":"https://openalex.org/I135117807","display_name":"Universit\u00e9 de Sherbrooke","ror":"https://ror.org/00kybxq39","country_code":"CA","type":"education","lineage":["https://openalex.org/I135117807"]},{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE","CA"],"is_corresponding":false,"raw_author_name":"Jenthe Thienpondt","raw_affiliation_strings":["Universit\u00e9 de Sherbrooke, Canada","IDLab, Ghent University -imec, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Sherbrooke, Canada","institution_ids":["https://openalex.org/I135117807"]},{"raw_affiliation_string":"IDLab, Ghent University -imec, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032699386","display_name":"Brecht Desplanques","orcid":null},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Brecht Desplanques","raw_affiliation_strings":["IDLab, Ghent University -imec, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDLab, Ghent University -imec, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027377615","display_name":"Hwidong Na","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hwidong Na","raw_affiliation_strings":["Samsung Advanced Institute of Technology, Suwon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Advanced Institute of Technology, Suwon, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":95,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3560","last_page":"3564"},"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":0.9972000122070312,"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":0.9958000183105469,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.8305954933166504},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8148945569992065},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7540077567100525},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7457258105278015},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7054169178009033},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6457430124282837},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6313896775245667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5042918920516968},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.42820048332214355},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3870152235031128}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8305954933166504},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8148945569992065},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7540077567100525},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7457258105278015},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7054169178009033},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6457430124282837},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6313896775245667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5042918920516968},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.42820048332214355},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3870152235031128},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2021-941","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-941","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:2104.01466","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.01466","pdf_url":"https://arxiv.org/pdf/2104.01466","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":null,"raw_type":"text"},{"id":"pmh:oai:archive.ugent.be:8720784","is_oa":true,"landing_page_url":"https://biblio.ugent.be/publication/8720784","pdf_url":null,"source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISSN: 2308-457X","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.01466","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.01466","pdf_url":"https://arxiv.org/pdf/2104.01466","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":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1589137271","https://openalex.org/W2081074144","https://openalex.org/W2125336414","https://openalex.org/W2132914434","https://openalex.org/W2148613904","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2889418727","https://openalex.org/W2890964092","https://openalex.org/W2914611487","https://openalex.org/W2928165649","https://openalex.org/W2936774411","https://openalex.org/W2962788625","https://openalex.org/W2963420686","https://openalex.org/W2963962398","https://openalex.org/W2964054038","https://openalex.org/W2964121744","https://openalex.org/W2969985801","https://openalex.org/W2972441390","https://openalex.org/W2972449503","https://openalex.org/W2972680151","https://openalex.org/W2981461916","https://openalex.org/W2981615245","https://openalex.org/W3015778863","https://openalex.org/W3024541814","https://openalex.org/W3024869864","https://openalex.org/W3042801391","https://openalex.org/W3043471679","https://openalex.org/W3095129427","https://openalex.org/W3096029132","https://openalex.org/W3105031100","https://openalex.org/W3111481301","https://openalex.org/W3115133930","https://openalex.org/W3125596972","https://openalex.org/W3134299941","https://openalex.org/W3145204487","https://openalex.org/W3167533889","https://openalex.org/W3178462146","https://openalex.org/W3212886388","https://openalex.org/W4288091954","https://openalex.org/W4309845474"],"related_works":["https://openalex.org/W4384929466","https://openalex.org/W2206035908","https://openalex.org/W3148366653","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138"],"abstract_inverted_index":{"Learning":[0],"robust":[1,120],"speaker":[2,9,17,61,87,121],"embeddings":[3,23,122],"is":[4],"a":[5,29,66,95],"crucial":[6],"step":[7],"in":[8,59],"diarization.":[10,88],"Deep":[11],"neural":[12,69],"networks":[13],"can":[14],"accurately":[15],"capture":[16],"discriminative":[18],"characteristics":[19],"and":[20,126],"popular":[21,133],"deep":[22],"such":[24],"as":[25],"x-vectors":[26,46],"are":[27],"nowadays":[28],"fundamental":[30],"component":[31],"of":[32,82,104],"modern":[33],"diarization":[34],"systems.":[35],"Recently,":[36],"some":[37],"improvements":[38],"over":[39],"the":[40,60,77,80,83,105,109,132],"standard":[41],"TDNN":[42],"architecture":[43],"used":[44],"for":[45,53,76],"have":[47],"been":[48],"proposed.":[49],"The":[50,113],"ECAPA-TDNN":[51,84,114],"model,":[52],"instance,":[54],"has":[55],"shown":[56],"impressive":[57],"performance":[58],"verification":[62],"domain,":[63],"thanks":[64],"to":[65,86,118],"carefully":[67],"designed":[68],"model.":[70],"In":[71],"this":[72],"work,":[73],"we":[74,90],"extend,":[75],"first":[78],"time,":[79],"use":[81],"model":[85,115],"Moreover,":[89],"improved":[91],"its":[92],"robustness":[93],"with":[94],"powerful":[96],"augmentation":[97],"scheme":[98],"that":[99,138],"concatenates":[100],"several":[101],"contaminated":[102],"versions":[103],"same":[106,110],"signal":[107],"within":[108],"training":[111],"batch.":[112],"turned":[116],"out":[117],"provide":[119],"under":[123],"both":[124],"close-talking":[125],"distant-talking":[127],"conditions.":[128],"Our":[129],"results":[130],"on":[131],"AMI":[134],"meeting":[135],"corpus":[136],"show":[137],"our":[139],"system":[140],"significantly":[141],"outperforms":[142],"recently":[143],"proposed":[144],"approaches.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":12},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":28},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}