{"id":"https://openalex.org/W3024869864","doi":"https://doi.org/10.21437/interspeech.2020-2650","title":"ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification","display_name":"ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3024869864","doi":"https://doi.org/10.21437/interspeech.2020-2650","mag":"3024869864"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2650","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2650","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/2005.07143","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":["Department of Electronics and Information Systems, imec -Ghent University, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Systems, imec -Ghent University, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"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/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":"Jenthe Thienpondt","raw_affiliation_strings":["Department of Electronics and Information Systems, imec -Ghent University, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Systems, imec -Ghent University, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046536366","display_name":"Kris Demuynck","orcid":"https://orcid.org/0000-0001-8525-7160"},"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":"Kris Demuynck","raw_affiliation_strings":["Department of Electronics and Information Systems, imec -Ghent University, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Systems, imec -Ghent University, Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I32597200"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1445,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3830","last_page":"3834"},"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":0.9997000098228455,"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":0.9976000189781189,"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":0.8109618425369263},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6216539740562439},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5941953063011169},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.568656325340271},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.5158552527427673},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5115564465522766},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5086241960525513},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.49497050046920776},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.49058690667152405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4800754189491272},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4397678077220917},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09705409407615662}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8109618425369263},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6216539740562439},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5941953063011169},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.568656325340271},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.5158552527427673},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5115564465522766},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5086241960525513},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.49497050046920776},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.49058690667152405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4800754189491272},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4397678077220917},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09705409407615662},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2020-2650","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2650","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2005.07143","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.07143","pdf_url":"https://arxiv.org/pdf/2005.07143","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:8680078","is_oa":true,"landing_page_url":"https://biblio.ugent.be/publication/8680078","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:2005.07143","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.07143","pdf_url":"https://arxiv.org/pdf/2005.07143","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":[{"id":"https://metadata.un.org/sdg/4","score":0.5099999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W125553504","https://openalex.org/W1522301498","https://openalex.org/W1589137271","https://openalex.org/W1836465849","https://openalex.org/W2157161740","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2696967604","https://openalex.org/W2713263280","https://openalex.org/W2726515241","https://openalex.org/W2747165665","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2888867175","https://openalex.org/W2889519245","https://openalex.org/W2890964092","https://openalex.org/W2928165649","https://openalex.org/W2936774411","https://openalex.org/W2938358845","https://openalex.org/W2951534110","https://openalex.org/W2963420686","https://openalex.org/W2964054038","https://openalex.org/W2964121744","https://openalex.org/W2969985801","https://openalex.org/W2972441390","https://openalex.org/W2972552635","https://openalex.org/W2981461916","https://openalex.org/W2991951409","https://openalex.org/W2996132597","https://openalex.org/W3010925296","https://openalex.org/W3015368919","https://openalex.org/W3027908062","https://openalex.org/W3042801391","https://openalex.org/W4288091954","https://openalex.org/W4300685083","https://openalex.org/W4309845474"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W147410782","https://openalex.org/W3022252430","https://openalex.org/W3081952170","https://openalex.org/W4385719553","https://openalex.org/W2349696592","https://openalex.org/W1985270221"],"abstract_inverted_index":{"Current":[0],"speaker":[1,11,34],"verification":[2,57],"techniques":[3],"rely":[4],"on":[5,48,127,164,186],"a":[6,18,128],"neural":[7,115],"network":[8,161],"to":[9,28,44,78,87,108,119,162],"extract":[10],"representations.":[12],"The":[13,92,176],"successful":[14],"x-vector":[15],"architecture":[16,46,179],"is":[17],"Time":[19],"Delay":[20],"Neural":[21],"Network":[22],"(TDNN)":[23],"that":[24],"applies":[25],"statistics":[26,151,174],"pooling":[27,152],"project":[29],"variable-length":[30],"utterances":[31],"into":[32,69],"fixed-length":[33],"characterizing":[35],"embeddings.":[36],"In":[37],"this":[38,45,135],"paper,":[39],"we":[40,80,138,148],"propose":[41],"multiple":[42],"enhancements":[43],"based":[47,184],"recent":[49],"trends":[50],"in":[51,84],"the":[52,62,96,100,105,112,150,160,172,187,192],"related":[53],"fields":[54],"of":[55,99,111,131,143,167,171],"face":[56],"and":[58,140,191],"computer":[59],"vision.":[60],"Firstly,":[61],"initial":[63],"frame":[64,101,156],"layers":[65],"can":[66],"be":[67],"restructured":[68],"1-dimensional":[70],"Res2Net":[71],"modules":[72,86],"with":[73,123,154],"impactful":[74],"skip":[75],"connections.":[76],"Similarly":[77],"SE-ResNet,":[79],"introduce":[81],"Squeeze-and-Excitation":[82],"blocks":[83],"these":[85],"explicitly":[88],"model":[89],"channel":[90],"interdependencies.":[91],"SE":[93],"block":[94],"expands":[95],"temporal":[97],"context":[98],"layer":[102,125],"by":[103],"rescaling":[104],"channels":[106],"according":[107],"global":[109],"properties":[110],"recording.":[113],"Secondly,":[114],"networks":[116],"are":[117],"known":[118],"learn":[120],"hierarchical":[121,145],"features,":[122],"each":[124,170],"operating":[126],"different":[129,144,165],"level":[130],"complexity.":[132],"To":[133],"leverage":[134],"complementary":[136],"information,":[137],"aggregate":[139],"propagate":[141],"features":[142],"levels.":[146],"Finally,":[147],"improve":[149],"module":[153],"channel-dependent":[155],"attention.":[157],"This":[158],"enables":[159],"focus":[163],"subsets":[166],"frames":[168],"during":[169],"channel's":[173],"estimation.":[175],"proposed":[177],"ECAPA-TDNN":[178],"significantly":[180],"outperforms":[181],"state-of-the-art":[182],"TDNN":[183],"systems":[185],"VoxCeleb":[188,194],"test":[189],"sets":[190],"2019":[193],"Speaker":[195],"Recognition":[196],"Challenge.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":147},{"year":2025,"cited_by_count":378},{"year":2024,"cited_by_count":355},{"year":2023,"cited_by_count":312},{"year":2022,"cited_by_count":169},{"year":2021,"cited_by_count":74},{"year":2020,"cited_by_count":10}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}