{"id":"https://openalex.org/W4224920133","doi":"https://doi.org/10.1109/icassp43922.2022.9747384","title":"Improving Fairness in Speaker Verification via Group-Adapted Fusion Network","display_name":"Improving Fairness in Speaker Verification via Group-Adapted Fusion Network","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224920133","doi":"https://doi.org/10.1109/icassp43922.2022.9747384"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747384","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 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/2202.11323","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067351435","display_name":"Hua Shen","orcid":"https://orcid.org/0009-0007-2837-6914"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hua Shen","raw_affiliation_strings":["The Pennsylvania State University","Amazon Alexa AI"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022888361","display_name":"Yuguang Yang","orcid":"https://orcid.org/0000-0002-9523-9254"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuguang Yang","raw_affiliation_strings":["Amazon Alexa AI"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108642650","display_name":"Guoli Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guoli Sun","raw_affiliation_strings":["Amazon Alexa AI"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040023052","display_name":"Ryan Langman","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryan Langman","raw_affiliation_strings":["Amazon Alexa AI"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005681147","display_name":"Eun\u2010Jung Han","orcid":"https://orcid.org/0000-0002-8385-3775"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eunjung Han","raw_affiliation_strings":["Amazon Alexa AI"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012153296","display_name":"Jasha Droppo","orcid":"https://orcid.org/0000-0001-6097-0090"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jasha Droppo","raw_affiliation_strings":["Amazon Alexa AI"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Stolcke","raw_affiliation_strings":["Amazon Alexa AI"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5067351435"],"corresponding_institution_ids":["https://openalex.org/I130769515","https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":1.2525,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.81136376,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7077","last_page":"7081"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987000226974487,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9916999936103821,"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":0.7419450283050537},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6366613507270813},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6255978345870972},{"id":"https://openalex.org/keywords/skew","display_name":"Skew","score":0.6052619218826294},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5830000042915344},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5643953084945679},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.48119479417800903},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4452381432056427},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43758082389831543},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4223410487174988},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.417763888835907},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41249895095825195},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38636431097984314},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3242742717266083}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7419450283050537},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6366613507270813},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6255978345870972},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.6052619218826294},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5830000042915344},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5643953084945679},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.48119479417800903},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4452381432056427},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43758082389831543},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4223410487174988},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.417763888835907},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41249895095825195},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38636431097984314},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3242742717266083},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747384","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2202.11323","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2202.11323","pdf_url":"https://arxiv.org/pdf/2202.11323","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:2202.11323","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2202.11323","pdf_url":"https://arxiv.org/pdf/2202.11323","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":[{"id":"https://metadata.un.org/sdg/10","score":0.4699999988079071,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1987971958","https://openalex.org/W2025653905","https://openalex.org/W2101234009","https://openalex.org/W2114925438","https://openalex.org/W2119468495","https://openalex.org/W2612434969","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2949879676","https://openalex.org/W2962788625","https://openalex.org/W2963189767","https://openalex.org/W2982232682","https://openalex.org/W3004720752","https://openalex.org/W3012624518","https://openalex.org/W3013020904","https://openalex.org/W3024541814","https://openalex.org/W3024869864","https://openalex.org/W3034312118","https://openalex.org/W3104056985","https://openalex.org/W3126634788","https://openalex.org/W3181414820","https://openalex.org/W3197142615","https://openalex.org/W3197340960","https://openalex.org/W4230428500","https://openalex.org/W4293718192","https://openalex.org/W6675354045","https://openalex.org/W6732520560","https://openalex.org/W6737575990"],"related_works":["https://openalex.org/W112947718","https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W1998549096","https://openalex.org/W3141593045","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W2407001684"],"abstract_inverted_index":{"Modern":[0],"speaker":[1,74,127,188],"verification":[2,75,128],"models":[3,76],"use":[4],"deep":[5],"neural":[6],"networks":[7,21],"to":[8,25,46,153,162,168,174,180],"encode":[9],"utterance":[10],"audio":[11],"into":[12],"discriminative":[13],"embedding":[14,112],"vectors.":[15],"During":[16],"the":[17,33,71,100],"training":[18,184],"process,":[19],"these":[20],"are":[22],"typically":[23],"optimized":[24],"differentiate":[26],"arbitrary":[27],"speakers.":[28],"This":[29,54],"learning":[30,34],"process":[31],"biases":[32],"of":[35,73,151,183],"fine":[36],"voice":[37,64],"characteristics":[38],"towards":[39],"dominant":[40],"demographic":[41,60],"groups,":[42],"which":[43],"can":[44],"lead":[45],"an":[47],"unfair":[48],"performance":[49,89],"disparity":[50,97],"across":[51],"different":[52],"groups.":[53,93,134],"is":[55,178],"observed":[56],"especially":[57],"with":[58,80],"underrepresented":[59,92],"groups":[61],"sharing":[62],"similar":[63],"characteristics.":[65],"In":[66],"this":[67,96],"work,":[68],"we":[69,98],"investigate":[70],"fairness":[72],"on":[77,110],"controlled":[78],"datasets":[79],"imbalanced":[81,136],"gender":[82],"distributions,":[83],"providing":[84],"direct":[85],"evidence":[86],"that":[87,119],"model":[88,123],"suffers":[90],"for":[91,132],"To":[94],"mitigate":[95],"propose":[99],"group-adapted":[101],"fusion":[102],"network":[103],"(GFN)":[104],"architecture,":[105],"a":[106],"modular":[107],"architecture":[108],"based":[109],"group":[111,137,158],"adaptation":[113],"and":[114,131,164],"score":[115],"fusion.":[116],"We":[117],"show":[118],"our":[120,141],"method":[121,143],"alleviates":[122],"unfairness":[124],"by":[125,160],"improving":[126],"both":[129],"overall":[130,145],"individual":[133],"Given":[135],"representation":[138],"in":[139,166,187],"training,":[140],"proposed":[142],"achieves":[144],"equal":[146],"error":[147],"rate":[148],"(EER)":[149],"reduction":[150],"9.6%":[152],"29.0%":[154],"relative,":[155],"reduces":[156],"minority":[157],"EER":[159,171],"13.7%":[161],"18.6%,":[163],"results":[165],"20.0%":[167],"25.4%":[169],"less":[170],"disparity,":[172],"compared":[173],"baselines.":[175],"The":[176],"approach":[177],"applicable":[179],"other":[181],"types":[182],"data":[185],"skew":[186],"recognition":[189],"systems.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2022-04-28T00:00:00"}