{"id":"https://openalex.org/W4372266902","doi":"https://doi.org/10.1109/icassp49357.2023.10094795","title":"Parameter-Efficient Transfer Learning of Pre-Trained Transformer Models for Speaker Verification Using Adapters","display_name":"Parameter-Efficient Transfer Learning of Pre-Trained Transformer Models for Speaker Verification Using Adapters","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266902","doi":"https://doi.org/10.1109/icassp49357.2023.10094795"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094795","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094795","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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/A5038895203","display_name":"Rongzhi Gu","orcid":"https://orcid.org/0000-0003-1861-9170"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongzhi Gu","raw_affiliation_strings":["Tencent AI Lab,Shenzhen,China","Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"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,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/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 Mo\u0161ner","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":"Luk\u00e1\u0161 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 \u010cernock\u00fd","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":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9994999766349792,"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":0.9980000257492065,"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/transformer","display_name":"Transformer","score":0.8203408718109131},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7947396039962769},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6538328528404236},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46446695923805237},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"Fine-tuning","score":0.4614478647708893},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3988531827926636},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38998138904571533},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.184727281332016},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12645357847213745}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.8203408718109131},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7947396039962769},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6538328528404236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46446695923805237},{"id":"https://openalex.org/C157524613","wikidata":"https://www.wikidata.org/wiki/Q2828883","display_name":"Fine-tuning","level":2,"score":0.4614478647708893},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3988531827926636},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38998138904571533},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.184727281332016},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12645357847213745},{"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},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094795","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094795","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321408","display_name":"Ministry of Education","ror":"https://ror.org/01p262204"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1682403713","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2963850025","https://openalex.org/W2964303773","https://openalex.org/W2969985801","https://openalex.org/W3015598461","https://openalex.org/W3024869864","https://openalex.org/W3036601975","https://openalex.org/W3094374485","https://openalex.org/W3142516134","https://openalex.org/W3152426975","https://openalex.org/W3160646455","https://openalex.org/W3163505255","https://openalex.org/W3172698324","https://openalex.org/W3174770825","https://openalex.org/W3205949070","https://openalex.org/W3206189675","https://openalex.org/W3206252155","https://openalex.org/W3206886023","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4206908380","https://openalex.org/W4221161148","https://openalex.org/W4225274946","https://openalex.org/W4297841748","https://openalex.org/W4311000453","https://openalex.org/W4319862271","https://openalex.org/W6752048366","https://openalex.org/W6759579507","https://openalex.org/W6780218876","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W4360603156","https://openalex.org/W3126778358","https://openalex.org/W4287207696","https://openalex.org/W2735783528","https://openalex.org/W4385567133","https://openalex.org/W2882981877","https://openalex.org/W3208244077","https://openalex.org/W4307785608","https://openalex.org/W4319049505","https://openalex.org/W4372266902"],"abstract_inverted_index":{"Recently,":[0],"the":[1,11,31,34,41,70,82,85,109,116],"pre-trained":[2,35,86],"Transformer":[3,97,117],"models":[4,87],"have":[5],"received":[6],"a":[7,58,112,123,132],"rising":[8],"interest":[9],"in":[10,21,48,95,111],"field":[12],"of":[13,33,61,140],"speech":[14],"processing":[15],"thanks":[16],"to":[17,68,76,107],"their":[18],"great":[19],"success":[20],"various":[22],"downstream":[23],"tasks.":[24,79],"However,":[25],"most":[26],"fine-tuning":[27,83,129,151],"approaches":[28],"update":[29],"all":[30],"parameters":[32,73],"model,":[36],"which":[37],"becomes":[38],"prohibitive":[39],"as":[40,104],"model":[42,118],"size":[43],"grows":[44],"and":[45,90],"sometimes":[46],"results":[47],"over-fitting":[49],"on":[50,122,131],"small":[51,133],"datasets.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56],"conduct":[57],"comprehensive":[59],"analysis":[60],"applying":[62],"parameter-efficient":[63],"transfer":[64],"learning":[65],"(PETL)":[66],"methods":[67,145,152],"reduce":[69],"required":[71],"learnable":[72],"for":[74],"adapting":[75],"speaker":[77],"verification":[78],"Specifically,":[80],"during":[81],"process,":[84],"are":[88,99],"frozen,":[89],"only":[91],"lightweight":[92],"modules":[93],"inserted":[94],"each":[96],"block":[98],"trainable":[100],"(a":[101],"method":[102],"known":[103],"adapters).":[105],"Moreover,":[106],"boost":[108],"performance":[110],"cross-language":[113],"low-resource":[114],"scenario,":[115],"is":[119],"further":[120],"tuned":[121],"large":[124],"intermediate":[125],"dataset":[126],"before":[127],"directly":[128],"it":[130],"dataset.":[134],"With":[135],"updating":[136],"fewer":[137],"than":[138],"4%":[139],"parameters,":[141],"(our":[142],"proposed)":[143],"PETL-based":[144],"achieve":[146],"comparable":[147],"performances":[148],"with":[149],"full":[150],"(Vox1-O:":[153],"0.55%,":[154],"Vox1-E:":[155],"0.82%,":[156],"Vox1-H:1.73%).":[157]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}