{"id":"https://openalex.org/W4391021719","doi":"https://doi.org/10.1109/asru57964.2023.10389750","title":"ECAPA2: A Hybrid Neural Network Architecture and Training Strategy for Robust Speaker Embeddings","display_name":"ECAPA2: A Hybrid Neural Network Architecture and Training Strategy for Robust Speaker Embeddings","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021719","doi":"https://doi.org/10.1109/asru57964.2023.10389750"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://biblio.ugent.be/publication/01J1SX77QNVTSSRM0Y7FX0XTZY/file/01J1SX9R4ZDW58W502R9ZZK9TF.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":["Ghent University - imec,IDLab,Department of Electronics and Information Systems,Belgium","Department of Electronics and Information Systems, IDLab, Ghent University - imec, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University - imec,IDLab,Department of Electronics and Information Systems,Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"Department of Electronics and Information Systems, IDLab, Ghent University - imec, 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":["Ghent University - imec,IDLab,Department of Electronics and Information Systems,Belgium","Department of Electronics and Information Systems, IDLab, Ghent University - imec, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University - imec,IDLab,Department of Electronics and Information Systems,Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"Department of Electronics and Information Systems, IDLab, Ghent University - imec, 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":true,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9984999895095825,"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":0.9962999820709229,"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":0.8458881378173828},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7157838344573975},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6208158135414124},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5692639350891113},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5536186695098877},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4840080440044403},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4814964532852173},{"id":"https://openalex.org/keywords/network-architecture","display_name":"Network architecture","score":0.45029282569885254},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43287748098373413},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.41775739192962646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3896111845970154},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.056524187326431274}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8458881378173828},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7157838344573975},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6208158135414124},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5692639350891113},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5536186695098877},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4840080440044403},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4814964532852173},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.45029282569885254},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43287748098373413},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.41775739192962646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3896111845970154},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.056524187326431274},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asru57964.2023.10389750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:archive.ugent.be:01J1SX77QNVTSSRM0Y7FX0XTZY","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01J1SX77QNVTSSRM0Y7FX0XTZY","pdf_url":"https://biblio.ugent.be/publication/01J1SX77QNVTSSRM0Y7FX0XTZY/file/01J1SX9R4ZDW58W502R9ZZK9TF.pdf","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":"ISBN: 9798350306897","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:archive.ugent.be:01J1SX77QNVTSSRM0Y7FX0XTZY","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01J1SX77QNVTSSRM0Y7FX0XTZY","pdf_url":"https://biblio.ugent.be/publication/01J1SX77QNVTSSRM0Y7FX0XTZY/file/01J1SX9R4ZDW58W502R9ZZK9TF.pdf","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":"ISBN: 9798350306897","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391021719.pdf","grobid_xml":"https://content.openalex.org/works/W4391021719.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2219249508","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2747165665","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2913668833","https://openalex.org/W2928165649","https://openalex.org/W2936774411","https://openalex.org/W2949846184","https://openalex.org/W2964054038","https://openalex.org/W2969985801","https://openalex.org/W2973190269","https://openalex.org/W2986661129","https://openalex.org/W3008104819","https://openalex.org/W3024869864","https://openalex.org/W3094374485","https://openalex.org/W3109225549","https://openalex.org/W3141035251","https://openalex.org/W3198698812","https://openalex.org/W3205335446","https://openalex.org/W4283072473","https://openalex.org/W4372269848","https://openalex.org/W6631190155","https://openalex.org/W6688816777","https://openalex.org/W6729983426","https://openalex.org/W6734194636","https://openalex.org/W6751739117","https://openalex.org/W6801723603"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W1998549096","https://openalex.org/W2767892728","https://openalex.org/W4235705411","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W3096066489"],"abstract_inverted_index":{"In":[0,79],"this":[1,69],"paper,":[2],"we":[3,81,123],"present":[4],"ECAPA2,":[5],"a":[6,83,125],"novel":[7],"hybrid":[8],"neural":[9],"network":[10],"architecture":[11,103],"and":[12,96,104],"training":[13,84,105],"strategy":[14,85,106],"to":[15,58,130],"produce":[16],"robust":[17,92],"speaker":[18,21,76,89],"embeddings.":[19],"Most":[20],"verification":[22,77],"models":[23,44],"are":[24,45],"based":[25],"on":[26,110,133],"either":[27],"the":[28,64,88,111],"1D-":[29],"or":[30,40],"2D-convolutional":[31],"operation,":[32],"often":[33],"manifested":[34],"as":[35],"Time":[36],"Delay":[37],"Neural":[38],"Networks":[39],"ResNets,":[41],"respectively.":[42],"Hybrid":[43],"relatively":[46],"unexplored":[47],"without":[48],"an":[49,72],"intuitive":[50],"explanation":[51],"what":[52],"constitutes":[53],"best":[54],"practices":[55],"in":[56,68],"regard":[57],"its":[59],"architectural":[60],"choices.":[61],"We":[62],"motivate":[63],"proposed":[65],"ECAPA2":[66,102],"model":[67,127],"paper":[70],"with":[71,115],"analysis":[73],"of":[74],"current":[75,120],"architectures.":[78],"addition,":[80],"propose":[82],"which":[86],"makes":[87],"embeddings":[90],"more":[91],"against":[93],"overlapping":[94],"speech":[95],"short":[97],"utterance":[98],"lengths.":[99],"The":[100],"presented":[101],"attains":[107],"state-of-the-art":[108],"performance":[109],"VoxCeleb1":[112],"test":[113],"sets":[114],"significantly":[116],"less":[117],"parameters":[118],"than":[119],"models.":[121],"Finally,":[122],"make":[124],"pre-trained":[126],"publicly":[128],"available":[129],"promote":[131],"research":[132],"downstream":[134],"tasks.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}