{"id":"https://openalex.org/W3094549357","doi":"https://doi.org/10.1145/3427228.3427274","title":"SEEF-ALDR: A Speaker Embedding Enhancement Framework via Adversarial Learning based Disentangled Representation","display_name":"SEEF-ALDR: A Speaker Embedding Enhancement Framework via Adversarial Learning based Disentangled Representation","publication_year":2020,"publication_date":"2020-12-07","ids":{"openalex":"https://openalex.org/W3094549357","doi":"https://doi.org/10.1145/3427228.3427274","mag":"3094549357"},"language":"en","primary_location":{"id":"doi:10.1145/3427228.3427274","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3427228.3427274","pdf_url":null,"source":{"id":"https://openalex.org/S4306417673","display_name":"Annual Computer Security Applications Conference","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":"Annual Computer Security Applications Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1912.02608","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jianwei Tai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jianwei Tai","raw_affiliation_strings":["Key Laboratory of Network Assessment Technology, and Institute of Information Engineering, Chinese Academy of Sciences; Beijing Key Laboratory of Network Security and Protection Technology, and Institute of Information Engineering, Chinese Academy of Sciences; School of Cyber Security, University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Network Assessment Technology, and Institute of Information Engineering, Chinese Academy of Sciences; Beijing Key Laboratory of Network Security and Protection Technology, and Institute of Information Engineering, Chinese Academy of Sciences; School of Cyber Security, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaoqi Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqi Jia","raw_affiliation_strings":["Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qingjia Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingjia Huang","raw_affiliation_strings":["Key Laboratory of Network Assessment Technology, and Institute of Information Engineering, Chinese Academy of Sciences; Beijing Key Laboratory of Network Security and Protection Technology, and Institute of Information Engineering, Chinese Academy of Sciences; School of Cyber Security, University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Network Assessment Technology, and Institute of Information Engineering, Chinese Academy of Sciences; Beijing Key Laboratory of Network Security and Protection Technology, and Institute of Information Engineering, Chinese Academy of Sciences; School of Cyber Security, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Weijuan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weijuan Zhang","raw_affiliation_strings":["Key Laboratory of Network Assessment Technology, and Institute of Information Engineering, Chinese Academy of Sciences; Beijing Key Laboratory of Network Security and Protection Technology, and Institute of Information Engineering, Chinese Academy of Sciences; School of Cyber Security, University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Network Assessment Technology, and Institute of Information Engineering, Chinese Academy of Sciences; Beijing Key Laboratory of Network Security and Protection Technology, and Institute of Information Engineering, Chinese Academy of Sciences; School of Cyber Security, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haichao Du","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haichao Du","raw_affiliation_strings":["Key Laboratory of Network Assessment Technology, and Institute of Information Engineering, Chinese Academy of Sciences; Beijing Key Laboratory of Network Security and Protection Technology, and Institute of Information Engineering, Chinese Academy of Sciences; School of Cyber Security, University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Network Assessment Technology, and Institute of Information Engineering, Chinese Academy of Sciences; Beijing Key Laboratory of Network Security and Protection Technology, and Institute of Information Engineering, Chinese Academy of Sciences; School of Cyber Security, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":null,"display_name":"Shengzhi Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I92609107","display_name":"Metropolitan College of New York","ror":"https://ror.org/012saek46","country_code":"US","type":"education","lineage":["https://openalex.org/I92609107"]},{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shengzhi Zhang","raw_affiliation_strings":["Metropolitan College Boston University, USA"],"affiliations":[{"raw_affiliation_string":"Metropolitan College Boston University, USA","institution_ids":["https://openalex.org/I92609107","https://openalex.org/I111088046"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.2234,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53916652,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"939","last_page":"950"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8337000012397766,"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":0.8337000012397766,"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":0.07280000299215317,"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/T11448","display_name":"Face recognition and analysis","score":0.010499999858438969,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/key","display_name":"Key (lock)","score":0.5679000020027161},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5601000189781189},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5532000064849854},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5483999848365784},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5360000133514404},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.49380001425743103},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.492000013589859},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4763999879360199}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7989000082015991},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5679000020027161},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5601000189781189},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5532000064849854},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5483999848365784},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5360000133514404},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.504800021648407},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.49380001425743103},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.492000013589859},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4763999879360199},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4632999897003174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45719999074935913},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.42829999327659607},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.423799991607666},{"id":"https://openalex.org/C148417208","wikidata":"https://www.wikidata.org/wiki/Q4825882","display_name":"Authentication (law)","level":2,"score":0.4185999929904938},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3619000017642975},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.3084000051021576},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29919999837875366},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2802000045776367},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.2745000123977661},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3427228.3427274","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3427228.3427274","pdf_url":null,"source":{"id":"https://openalex.org/S4306417673","display_name":"Annual Computer Security Applications Conference","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":"Annual Computer Security Applications Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1912.02608","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.02608","pdf_url":"https://arxiv.org/pdf/1912.02608","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:1912.02608","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.02608","pdf_url":"https://arxiv.org/pdf/1912.02608","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":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W16016350","https://openalex.org/W1974821667","https://openalex.org/W2013196554","https://openalex.org/W2025768430","https://openalex.org/W2026158767","https://openalex.org/W2033419168","https://openalex.org/W2097067877","https://openalex.org/W2121812409","https://openalex.org/W2143612262","https://openalex.org/W2160815625","https://openalex.org/W2194775991","https://openalex.org/W2221409856","https://openalex.org/W2354870669","https://openalex.org/W2717402182","https://openalex.org/W2726515241","https://openalex.org/W2737047298","https://openalex.org/W2746742816","https://openalex.org/W2747238065","https://openalex.org/W2748488820","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2889385246","https://openalex.org/W2890704021","https://openalex.org/W2890964092","https://openalex.org/W2901368553","https://openalex.org/W2917756095","https://openalex.org/W2937328535","https://openalex.org/W2962788262","https://openalex.org/W2962788625","https://openalex.org/W2962959915","https://openalex.org/W2963010714","https://openalex.org/W2963371159","https://openalex.org/W2964066126","https://openalex.org/W2964337551","https://openalex.org/W2972403660","https://openalex.org/W2972921407","https://openalex.org/W2972986505","https://openalex.org/W2973099347","https://openalex.org/W2977846024","https://openalex.org/W2981087920"],"related_works":[],"abstract_inverted_index":{"Speaker":[0,81],"verification,":[1],"as":[2,107,112],"a":[3,79],"biometric":[4],"authentication":[5],"mechanism,":[6],"has":[7],"been":[8],"widely":[9],"used":[10],"due":[11,214],"to":[12,54,91,105,184,215],"the":[13,22,32,52,62,65,68,73,93,115,120,126,138,144,172,179,186,199,211,216,220],"pervasiveness":[14],"of":[15,24,38,64,95,122,146,176,188,219],"voice":[16],"control":[17],"on":[18,50,98,125,153,159,166],"smart":[19],"devices.":[20],"However,":[21],"task":[23,129],"\u201cin-the-wild\u201d":[25],"speaker":[26,99,109,127,147],"verification":[27,56,128,148],"is":[28,104,202],"still":[29],"challenging,":[30],"considering":[31],"speech":[33],"samples":[34],"may":[35],"contain":[36],"lots":[37],"identity-unrelated":[39,69,123],"information,":[40],"e.g.,":[41],"background":[42],"noise,":[43],"reverberation,":[44],"emotion,":[45],"etc.":[46],"Previous":[47],"works":[48],"focus":[49],"optimizing":[51],"model":[53,197,212],"improve":[55,143],"accuracy,":[57],"without":[58,170],"taking":[59],"into":[60,198],"account":[61],"elimination":[63],"impact":[66,121],"from":[67,114,210],"information.":[70],"To":[71],"solve":[72],"above":[74],"problem,":[75],"we":[76],"propose":[77],"SEEF-ALDR,":[78],"novel":[80],"Embedding":[82],"Enhancement":[83],"Framework":[84],"via":[85],"Adversarial":[86],"Learning":[87],"based":[88],"Disentangled":[89],"Representation,":[90],"reinforce":[92],"performance":[94,145],"existing":[96,196],"models":[97],"verification.":[100],"The":[101],"key":[102],"idea":[103],"retrieve":[106],"much":[108],"identity":[110],"information":[111,124],"possible":[113],"original":[116],"speech,":[117],"thus":[118],"minimizing":[119],"by":[130,149],"using":[131],"adversarial":[132],"learning.":[133],"Experimental":[134],"results":[135],"demonstrate":[136],"that":[137],"proposed":[139,200],"framework":[140,201],"can":[141],"significantly":[142],"20.3%":[150],"and":[151,162,204],"23.8%":[152],"average":[154],"over":[155],"13":[156],"tested":[157,164],"baselines":[158,165],"dataset":[160,167],"Voxceleb1":[161],"8":[163],"Voxceleb2":[168],"respectively,":[169],"adjusting":[171],"structure":[173],"or":[174],"hyper-parameters":[175],"them.":[177],"Furthermore,":[178],"ablation":[180],"study":[181],"was":[182],"conducted":[183],"evaluate":[185],"contribution":[187],"each":[189],"module":[190],"in":[191],"SEEF-ALDR.":[192],"Finally,":[193],"porting":[194],"an":[195],"straightforward":[203],"cost-efficient,":[205],"with":[206],"very":[207],"little":[208],"effort":[209],"owners":[213],"modular":[217],"design":[218],"framework.":[221]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2020-10-29T00:00:00"}
