{"id":"https://openalex.org/W4319862271","doi":"https://doi.org/10.1109/slt54892.2023.10022775","title":"An Attention-Based Backend Allowing Efficient Fine-Tuning of Transformer Models for Speaker Verification","display_name":"An Attention-Based Backend Allowing Efficient Fine-Tuning of Transformer Models for Speaker Verification","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862271","doi":"https://doi.org/10.1109/slt54892.2023.10022775"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022775","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022775","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111291634","display_name":"Junyi Peng","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":"Junyi Peng","raw_affiliation_strings":["Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia","Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Faculty of Information Technology, Speech@FIT, Brno University of Technology, 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":"Oldrich Plchot","raw_affiliation_strings":["Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia","Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061939508","display_name":"Themos Stafylakis","orcid":"https://orcid.org/0000-0002-9227-3588"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Themos Stafylakis","raw_affiliation_strings":["Omilia - Conversational Intelligence,Athens,Greece","Omilia - Conversational Intelligence, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Omilia - Conversational Intelligence,Athens,Greece","institution_ids":[]},{"raw_affiliation_string":"Omilia - Conversational Intelligence, Athens, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055201620","display_name":"Ladislav Mo\u0161ner","orcid":"https://orcid.org/0000-0001-8175-2244"},"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":"Ladislav Mosner","raw_affiliation_strings":["Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia","Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","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":"Lukas Burget","raw_affiliation_strings":["Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia","Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045539248","display_name":"Ja\u0148 \u010cernock\u00fd","orcid":"https://orcid.org/0000-0002-8800-0210"},"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":"Jan Cernocky","raw_affiliation_strings":["Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia","Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia","institution_ids":["https://openalex.org/I60587646"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"555","last_page":"562"},"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":0.9993000030517578,"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":0.9987000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.779260516166687},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5767461657524109},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.571722686290741},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.562990128993988},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5602113008499146},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4501955509185791},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43291330337524414},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33486318588256836},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3313823342323303},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3255729079246521},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08983924984931946}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.779260516166687},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5767461657524109},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.571722686290741},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.562990128993988},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5602113008499146},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4501955509185791},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43291330337524414},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33486318588256836},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3313823342323303},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3255729079246521},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08983924984931946},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10022775","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022775","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2039057510","https://openalex.org/W2183016404","https://openalex.org/W2560647685","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2969985801","https://openalex.org/W2972705840","https://openalex.org/W2973049979","https://openalex.org/W2980708516","https://openalex.org/W2999547272","https://openalex.org/W3012310164","https://openalex.org/W3013020904","https://openalex.org/W3024869864","https://openalex.org/W3036601975","https://openalex.org/W3094374485","https://openalex.org/W3163505255","https://openalex.org/W3197580070","https://openalex.org/W3198275944","https://openalex.org/W3198564914","https://openalex.org/W3202370288","https://openalex.org/W3206189675","https://openalex.org/W3206252155","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3211224152","https://openalex.org/W4221161148","https://openalex.org/W4225527248","https://openalex.org/W4385245566","https://openalex.org/W6780218876","https://openalex.org/W6803378298","https://openalex.org/W6810126160"],"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/W3103989898","https://openalex.org/W4287804464","https://openalex.org/W3211292372","https://openalex.org/W803346624"],"abstract_inverted_index":{"In":[0,38],"recent":[1],"years,":[2],"self-supervised":[3],"learning":[4,60,102],"paradigm":[5],"has":[6],"received":[7],"extensive":[8],"attention":[9],"due":[10],"to":[11,28,34,63,78,125],"its":[12],"great":[13],"success":[14],"in":[15],"various":[16],"down-stream":[17],"tasks.":[18],"However,":[19],"the":[20,65,80,92,95,108,122],"fine-tuning":[21,66],"strategies":[22],"for":[23,104],"adapting":[24],"those":[25],"pre-trained":[26,52,96,109],"models":[27],"speaker":[29,83],"verification":[30],"task":[31],"have":[32],"yet":[33],"be":[35],"fully":[36],"explored.":[37],"this":[39],"paper,":[40],"we":[41,99],"analyze":[42],"several":[43],"feature":[44],"extraction":[45],"approaches":[46],"built":[47],"on":[48,137],"top":[49],"of":[50,82,94,107],"a":[51,59],"model,":[53],"as":[54,56],"well":[55],"regularization":[57],"and":[58,68,98,128,134,140],"rate":[61],"scheduler":[62],"stabilize":[64],"process":[67],"further":[69],"boost":[70],"performance:":[71,131],"multi-head":[72],"factorized":[73],"attentive":[74],"pooling":[75],"is":[76,150],"proposed":[77],"factorize":[79],"comparison":[81],"representations":[84],"into":[85],"multiple":[86],"phonetic":[87],"clusters.":[88],"We":[89],"regularize":[90],"towards":[91],"parameters":[93],"model":[97,110],"set":[100],"different":[101],"rates":[103],"each":[105],"layer":[106],"during":[111],"fine-tuning.":[112],"The":[113],"experimental":[114],"results":[115],"show":[116],"our":[117],"method":[118],"can":[119],"significantly":[120],"shorten":[121],"training":[123],"time":[124],"4":[126],"hours":[127],"achieve":[129],"SOTA":[130],"0.59%,":[132],"0.79%":[133],"1.77%":[135],"EER":[136],"Vox1-O,":[138],"Vox1-E":[139],"Vox1-H,":[141],"respectively.":[142],"<sup":[143,146],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[144,147],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[145,148],"Code":[149],"available":[151],"at":[152],"https://github.com/JunyiPeng00/IEEE-SLT22-Pretrained-Model-for-SV.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}