{"id":"https://openalex.org/W4392904027","doi":"https://doi.org/10.1109/icassp48485.2024.10446686","title":"Efficient Adapter Tuning of Pre-Trained Speech Models for Automatic Speaker Verification","display_name":"Efficient Adapter Tuning of Pre-Trained Speech Models for Automatic Speaker Verification","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904027","doi":"https://doi.org/10.1109/icassp48485.2024.10446686"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446686","doi":"https://doi.org/10.1109/icassp48485.2024.10446686","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446686","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"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":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2403.00293","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005211900","display_name":"Mufan Sang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mufan Sang","raw_affiliation_strings":["University of Texas at Dallas,Center for Robust Speech Systems (CRSS),TX,USA","Center for Robust Speech Systems (CRSS), University of Texas at Dallas, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas,Center for Robust Speech Systems (CRSS),TX,USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas at Dallas, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929","observed_orcids":["https://orcid.org/0000-0003-1382-9929"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H.L. Hansen","raw_affiliation_strings":["University of Texas at Dallas,Center for Robust Speech Systems (CRSS),TX,USA","Center for Robust Speech Systems (CRSS), University of Texas at Dallas, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas,Center for Robust Speech Systems (CRSS),TX,USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas at Dallas, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":2.5985,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.91109282,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"12131","last_page":"12135"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9961000084877014,"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":0.9961000084877014,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.002099999925121665,"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":0.0007999999797903001,"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/adapters","display_name":"adapters","score":0.5860000252723694},{"id":"https://openalex.org/keywords/parameter-efficient-fine-tuning","display_name":"parameter-efficient fine-tuning","score":0.8610000014305115},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"speaker verification","score":0.8820000290870667},{"id":"https://openalex.org/keywords/self-supervised-speech-models","display_name":"self-supervised speech models","score":0.972000002861023},{"id":"https://openalex.org/keywords/transformer-layers","display_name":"transformer layers","score":0.6309999823570251},{"id":"https://openalex.org/keywords/voxceleb1","display_name":"VoxCeleb1","score":0.7080000042915344},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.5550000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8314870595932007},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7673012018203735},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7442882657051086},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.5933499336242676},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.50541090965271},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.454163134098053},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.44312289357185364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43890380859375},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4328887462615967},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3994041681289673},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1794438660144806},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.14074808359146118},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09114569425582886},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07675746083259583},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446686","doi":"https://doi.org/10.1109/icassp48485.2024.10446686","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446686","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"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":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2403.00293","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.00293","pdf_url":"https://arxiv.org/pdf/2403.00293","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"doi:10.48550/arxiv.2403.00293","doi":"https://doi.org/10.48550/arxiv.2403.00293","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2403.00293","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2403.00293","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.00293","pdf_url":"https://arxiv.org/pdf/2403.00293","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392904027.pdf","grobid_xml":"https://content.openalex.org/works/W4392904027.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2726515241","https://openalex.org/W2890964092","https://openalex.org/W2896457183","https://openalex.org/W2913946806","https://openalex.org/W2939710050","https://openalex.org/W2971840980","https://openalex.org/W2972552635","https://openalex.org/W2981461916","https://openalex.org/W3024869864","https://openalex.org/W3036601975","https://openalex.org/W3096730275","https://openalex.org/W3110524561","https://openalex.org/W3160397447","https://openalex.org/W3165404421","https://openalex.org/W3169320628","https://openalex.org/W3197580070","https://openalex.org/W3205949070","https://openalex.org/W3206252155","https://openalex.org/W3209984917","https://openalex.org/W4200629441","https://openalex.org/W4200633018","https://openalex.org/W4221154745","https://openalex.org/W4225274946","https://openalex.org/W4283073456","https://openalex.org/W4372266902","https://openalex.org/W4372270069","https://openalex.org/W4375869415","https://openalex.org/W4385484947","https://openalex.org/W4389520150","https://openalex.org/W4393156634","https://openalex.org/W6769178842","https://openalex.org/W6780218876","https://openalex.org/W7133219196"],"related_works":["https://openalex.org/W4372266902","https://openalex.org/W4407169754","https://openalex.org/W7223032420","https://openalex.org/W4392902886","https://openalex.org/W4319862271","https://openalex.org/W4390494801","https://openalex.org/W4385823373","https://openalex.org/W4401016696","https://openalex.org/W4319862642","https://openalex.org/W7169712892"],"abstract_inverted_index":{"With":[0,80],"excellent":[1],"generalization":[2],"ability,":[3],"self-supervised":[4,72],"speech":[5,14,73],"models":[6,55,74],"have":[7],"shown":[8],"impressive":[9],"performance":[10,149],"on":[11,130],"various":[12],"downstream":[13],"tasks":[15],"in":[16],"the":[17,24,44,76,94,98,120,125,131,136,155],"pre-training":[18],"and":[19,38,107,122,141],"fine-tuning":[20,30,140],"paradigm.":[21],"However,":[22],"as":[23,41,43],"growing":[25],"size":[26],"of":[27,46,91,100,124,154],"pre-trained":[28,54,95],"models,":[29],"becomes":[31],"practically":[32],"unfeasible":[33],"due":[34],"to":[35,56,75,118],"heavy":[36],"computation":[37],"storage":[39],"overhead,":[40],"well":[42],"risk":[45],"overfitting.":[47],"Adapters":[48],"are":[49],"lightweight":[50],"modules":[51],"inserted":[52],"into":[53,93],"facilitate":[57],"parameter-efficient":[58,143],"adaptation.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63],"propose":[64],"an":[65],"effective":[66],"adapter":[67,83],"framework":[68,87],"designed":[69],"for":[70],"adapting":[71],"speaker":[77],"verification":[78],"task.":[79],"a":[81],"parallel":[82],"design,":[84],"our":[85],"proposed":[86,126,137],"inserts":[88],"two":[89],"types":[90],"adapters":[92,138],"model,":[96],"allowing":[97],"adaptation":[99],"latent":[101],"features":[102],"within":[103],"intermediate":[104],"Transformer":[105,112],"layers":[106],"output":[108],"embeddings":[109],"from":[110],"all":[111],"layers.":[113],"We":[114],"conduct":[115],"comprehensive":[116],"experiments":[117],"validate":[119],"efficiency":[121],"effectiveness":[123],"framework.":[127],"Experimental":[128],"results":[129],"VoxCeleb1":[132],"dataset":[133],"demonstrate":[134],"that":[135],"surpass":[139],"other":[142],"transfer":[144],"learning":[145],"methods,":[146],"achieving":[147],"superior":[148],"while":[150],"updating":[151],"only":[152],"5%":[153],"parameters.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2024-03-19T00:00:00"}