{"id":"https://openalex.org/W2937328535","doi":"https://doi.org/10.1109/icassp.2019.8682488","title":"Adversarial Speaker Verification","display_name":"Adversarial Speaker Verification","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2937328535","doi":"https://doi.org/10.1109/icassp.2019.8682488","mag":"2937328535"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1904.12406","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101749753","display_name":"Zhong Meng","orcid":"https://orcid.org/0000-0001-7814-5929"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhong Meng","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100702071","display_name":"Yong Zhao","orcid":"https://orcid.org/0000-0003-2644-952X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yong Zhao","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101928537","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0002-3912-097X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Gong","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101749753"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":7.3778,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.97660087,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6216","last_page":"6220"},"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":0.994700014591217,"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":0.9866999983787537,"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":0.7472623586654663},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7366607785224915},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.7016635537147522},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.6590675115585327},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6195247769355774},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6080539226531982},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5965958833694458},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5641669631004333},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5272753834724426},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5153610110282898},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.45780301094055176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43463635444641113},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38743433356285095},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.25651103258132935},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13222923874855042}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7472623586654663},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7366607785224915},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.7016635537147522},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.6590675115585327},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6195247769355774},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6080539226531982},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5965958833694458},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5641669631004333},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5272753834724426},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5153610110282898},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.45780301094055176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43463635444641113},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38743433356285095},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25651103258132935},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13222923874855042},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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":2,"locations":[{"id":"doi:10.1109/icassp.2019.8682488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1904.12406","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.12406","pdf_url":"https://arxiv.org/pdf/1904.12406","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:1904.12406","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.12406","pdf_url":"https://arxiv.org/pdf/1904.12406","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":[{"display_name":"Quality Education","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1882958252","https://openalex.org/W1992475611","https://openalex.org/W2046056978","https://openalex.org/W2078169166","https://openalex.org/W2099471712","https://openalex.org/W2114925438","https://openalex.org/W2150769028","https://openalex.org/W2289394825","https://openalex.org/W2510867321","https://openalex.org/W2584329820","https://openalex.org/W2584667682","https://openalex.org/W2587088898","https://openalex.org/W2587150483","https://openalex.org/W2612434969","https://openalex.org/W2769025471","https://openalex.org/W2774848319","https://openalex.org/W2795867901","https://openalex.org/W2796339975","https://openalex.org/W2801581493","https://openalex.org/W2888858245","https://openalex.org/W2889500840","https://openalex.org/W2890964092","https://openalex.org/W2939164678","https://openalex.org/W2963266252","https://openalex.org/W2963321191","https://openalex.org/W2963341071","https://openalex.org/W2963826681","https://openalex.org/W4302765731","https://openalex.org/W4320013936","https://openalex.org/W6639480849","https://openalex.org/W6732862412","https://openalex.org/W6735429107","https://openalex.org/W6737575990","https://openalex.org/W6745822563","https://openalex.org/W6745924425","https://openalex.org/W6746801104"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W4312095835","https://openalex.org/W4235705411","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W4317103504","https://openalex.org/W3096066489"],"abstract_inverted_index":{"The":[0,80],"use":[1],"of":[2,83],"deep":[3,48],"networks":[4],"to":[5,19,23,44,68,101],"extract":[6],"embeddings":[7,16],"for":[8,133],"speaker":[9,40,57,71,117],"recognition":[10],"has":[11],"proven":[12],"successfully.":[13],"However,":[14],"such":[15],"are":[17,65],"susceptible":[18],"performance":[20],"degradation":[21],"due":[22],"the":[24,27,46,70,77,84,108,120],"mismatches":[25],"among":[26],"training,":[28],"enrollment,":[29],"and":[30,60,74,92,124,135],"test":[31],"conditions.":[32],"In":[33,54],"this":[34],"work,":[35],"we":[36],"propose":[37,98],"an":[38],"adversarial":[39,51],"verification":[41,118],"(ASV)":[42],"scheme":[43],"learn":[45],"condition-invariant":[47],"embedding":[49],"via":[50],"multi-task":[52],"training.":[53],"ASV,":[55],"a":[56,61,113],"classification":[58,72],"network":[59,64,86],"condition":[62,78,85,109],"identification":[63],"jointly":[66],"optimized":[67],"minimize":[69],"loss":[73],"simultaneously":[75,102],"mini-maximize":[76],"loss.":[79],"target":[81],"labels":[82],"can":[87],"be":[88],"categorical":[89],"(environment":[90],"types)":[91],"continuous":[93],"(SNR":[94],"values).":[95],"We":[96],"further":[97],"multi-factorial":[99],"ASV":[100,121],"suppress":[103],"multiple":[104],"factors":[105],"that":[106],"constitute":[107],"variability.":[110],"Evaluated":[111],"on":[112],"Microsoft":[114],"Cortana":[115],"text-dependent":[116],"task,":[119],"achieves":[122],"8.8%":[123],"14.5%":[125],"relative":[126],"improvements":[127],"in":[128],"equal":[129],"error":[130],"rates":[131],"(EER)":[132],"known":[134],"unknown":[136],"conditions,":[137],"respectively.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":25},{"year":2019,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}