{"id":"https://openalex.org/W4408347299","doi":"https://doi.org/10.1109/icassp49660.2025.10890182","title":"Trainable Adaptive Score Normalization for Automatic Speaker Verification","display_name":"Trainable Adaptive Score Normalization for Automatic Speaker Verification","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408347299","doi":"https://doi.org/10.1109/icassp49660.2025.10890182"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890182","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.04512","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101610186","display_name":"Jeong-Hwan Choi","orcid":"https://orcid.org/0000-0002-3937-2333"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jeong-Hwan Choi","raw_affiliation_strings":["Hanyang University,Department of Electronics Engineering,Seoul,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanyang University,Department of Electronics Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007337599","display_name":"Ju-Seok Seong","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ju-Seok Seong","raw_affiliation_strings":["Hanyang University,Department of Electronics Engineering,Seoul,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanyang University,Department of Electronics Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090642537","display_name":"Ye-Rin Jeoung","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ye-Rin Jeoung","raw_affiliation_strings":["Hanyang University,Department of Electronics Engineering,Seoul,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanyang University,Department of Electronics Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002418613","display_name":"Joon\u2010Hyuk Chang","orcid":"https://orcid.org/0000-0003-2610-2323"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon-Hyuk Chang","raw_affiliation_strings":["Hanyang University,Department of Electronics Engineering,Seoul,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanyang University,Department of Electronics Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4575257"],"apc_list":null,"apc_paid":null,"fwci":2.8948,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.90248864,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"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":0.9929999709129333,"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":0.9929999709129333,"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":0.9746000170707703,"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":0.9071000218391418,"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/normalization","display_name":"Normalization (sociology)","score":0.8841049671173096},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.8617128133773804},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.80161452293396},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5989675521850586},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5548259019851685},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.38823631405830383},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38367128372192383}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8841049671173096},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.8617128133773804},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.80161452293396},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5989675521850586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5548259019851685},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.38823631405830383},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38367128372192383},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890182","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2504.04512","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.04512","pdf_url":"https://arxiv.org/pdf/2504.04512","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.04512","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.04512","pdf_url":"https://arxiv.org/pdf/2504.04512","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321142","display_name":"Hanyang University","ror":"https://ror.org/046865y68"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W5064682","https://openalex.org/W125553504","https://openalex.org/W1481604723","https://openalex.org/W1665214252","https://openalex.org/W1869017930","https://openalex.org/W1987416212","https://openalex.org/W1997873121","https://openalex.org/W2041823554","https://openalex.org/W2044812127","https://openalex.org/W2078953162","https://openalex.org/W2101556109","https://openalex.org/W2157161740","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2747165665","https://openalex.org/W2784163702","https://openalex.org/W2805744305","https://openalex.org/W2808631503","https://openalex.org/W2888807255","https://openalex.org/W2969985801","https://openalex.org/W3008703194","https://openalex.org/W3013020904","https://openalex.org/W3015598461","https://openalex.org/W3024458825","https://openalex.org/W3024869864","https://openalex.org/W3042801391","https://openalex.org/W3109225549","https://openalex.org/W3198508792","https://openalex.org/W3198575874","https://openalex.org/W4206908380","https://openalex.org/W4210631835","https://openalex.org/W4296070379","https://openalex.org/W4297841779","https://openalex.org/W4306867198","https://openalex.org/W4372340947","https://openalex.org/W4385823375","https://openalex.org/W4392903478","https://openalex.org/W4402592714","https://openalex.org/W6631190155","https://openalex.org/W6688816777","https://openalex.org/W6713967443","https://openalex.org/W6786169801","https://openalex.org/W6848916189","https://openalex.org/W6872604002"],"related_works":["https://openalex.org/W1968216131","https://openalex.org/W2355011896","https://openalex.org/W3089964815","https://openalex.org/W1581134722","https://openalex.org/W1491159402","https://openalex.org/W66821593","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W1516392727","https://openalex.org/W2140022733"],"abstract_inverted_index":{"Adaptive":[0],"S-norm":[1],"(AS-norm)":[2],"calibrates":[3],"automatic":[4],"speaker":[5,74],"verification":[6],"(ASV)":[7],"scores":[8,14],"by":[9,87],"normalizing":[10],"them":[11],"utilize":[12,93],"the":[13,21,65,115,148,151],"of":[15,80,150],"impostors":[16],"which":[17,60],"are":[18,61,69,85],"similar":[19],"to":[20,35,63,71,103],"input":[22],"speaker.":[23],"However,":[24],"AS-norm":[25,52,140],"does":[26],"not":[27],"involve":[28],"any":[29],"learning":[30],"process,":[31],"limiting":[32],"its":[33,162],"ability":[34],"provide":[36],"appropriate":[37],"regularization":[38],"strength":[39],"for":[40],"various":[41],"evaluation":[42],"utterances.":[43],"To":[44],"address":[45],"this":[46],"limitation,":[47],"we":[48],"propose":[49],"a":[50,76,94],"trainable":[51],"(TAS-norm)":[53],"that":[54],"leverages":[55],"learnable":[56],"impostor":[57,81],"embeddings":[58],"(LIEs),":[59],"used":[62],"compose":[64],"cohort.":[66],"These":[67],"LIEs":[68,84],"initialized":[70],"represent":[72],"each":[73],"in":[75,101,124],"training":[77],"dataset":[78],"consisting":[79],"speakers.":[82],"Subsequently,":[83],"fine-tuned":[86],"simulating":[88],"an":[89],"ASV":[90,155],"evaluation.":[91],"We":[92,145],"margin":[95],"penalty":[96],"during":[97],"top-scoring":[98],"IEs":[99],"selection":[100],"fine-tuning":[102],"prevent":[104],"non-impostor":[105],"speakers":[106],"from":[107],"being":[108],"selected.":[109],"In":[110],"our":[111],"experiments":[112],"with":[113,138],"ECAPA-TDNN,":[114],"proposed":[116,143],"TAS-norm":[117,152],"observed":[118],"4.11%":[119],"and":[120,128,159],"10.62%":[121],"relative":[122],"improvement":[123],"equal":[125],"error":[126],"rate":[127],"minimum":[129],"detection":[130],"cost":[131],"function,":[132],"respectively,":[133],"on":[134,153],"VoxCeleb1-O":[135],"trial":[136],"compared":[137],"standard":[139],"without":[141],"using":[142],"LIEs.":[144],"further":[146],"validated":[147],"effectiveness":[149],"additional":[154],"datasets":[156],"comprising":[157],"Persian":[158],"Chinese,":[160],"demonstrating":[161],"robustness":[163],"across":[164],"different":[165],"languages.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}