{"id":"https://openalex.org/W3163829335","doi":"https://doi.org/10.1109/icassp39728.2021.9413403","title":"DEAAN: Disentangled Embedding and Adversarial Adaptation Network for Robust Speaker Representation Learning","display_name":"DEAAN: Disentangled Embedding and Adversarial Adaptation Network for Robust Speaker Representation Learning","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163829335","doi":"https://doi.org/10.1109/icassp39728.2021.9413403","mag":"3163829335"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413403","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413403","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005211900","display_name":"Mufan Sang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mufan Sang","raw_affiliation_strings":["The University of Texas,Center for Robust Speech Systems,Dallas,TX,USA","Center for Robust Speech Systems, The University of Texas, Dallas, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas,Center for Robust Speech Systems,Dallas,TX,USA","institution_ids":[]},{"raw_affiliation_string":"Center for Robust Speech Systems, The University of Texas, Dallas, TX, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101861591","display_name":"Wei Xia","orcid":"https://orcid.org/0009-0009-4734-6256"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Xia","raw_affiliation_strings":["The University of Texas,Center for Robust Speech Systems,Dallas,TX,USA","Center for Robust Speech Systems, The University of Texas, Dallas, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas,Center for Robust Speech Systems,Dallas,TX,USA","institution_ids":[]},{"raw_affiliation_string":"Center for Robust Speech Systems, The University of Texas, Dallas, TX, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John H.L. Hansen","raw_affiliation_strings":["The University of Texas,Center for Robust Speech Systems,Dallas,TX,USA","Center for Robust Speech Systems, The University of Texas, Dallas, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas,Center for Robust Speech Systems,Dallas,TX,USA","institution_ids":[]},{"raw_affiliation_string":"Center for Robust Speech Systems, The University of Texas, Dallas, TX, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3445,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.90724203,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6169","last_page":"6173"},"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":0.9873999953269958,"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":0.9836999773979187,"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/discriminative-model","display_name":"Discriminative model","score":0.7550598382949829},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7436073422431946},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5719041228294373},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5610243082046509},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5362955927848816},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.534137487411499},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5234931707382202},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5081408023834229},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.46706777811050415},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45159125328063965},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4209122061729431},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1254577338695526}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7550598382949829},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7436073422431946},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5719041228294373},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5610243082046509},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5362955927848816},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.534137487411499},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5234931707382202},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5081408023834229},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46706777811050415},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45159125328063965},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4209122061729431},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1254577338695526},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413403","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413403","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1731081199","https://openalex.org/W1936725236","https://openalex.org/W2136144249","https://openalex.org/W2165698076","https://openalex.org/W2173520492","https://openalex.org/W2419501139","https://openalex.org/W2726515241","https://openalex.org/W2747238065","https://openalex.org/W2796485741","https://openalex.org/W2801581493","https://openalex.org/W2803832867","https://openalex.org/W2808631503","https://openalex.org/W2885192629","https://openalex.org/W2890964092","https://openalex.org/W2901368553","https://openalex.org/W2936780106","https://openalex.org/W2937328535","https://openalex.org/W2952056941","https://openalex.org/W2962788625","https://openalex.org/W2963040451","https://openalex.org/W2963371159","https://openalex.org/W2963684088","https://openalex.org/W2963800509","https://openalex.org/W2972961496","https://openalex.org/W3008883495","https://openalex.org/W3012767853","https://openalex.org/W3015231328","https://openalex.org/W3015555484","https://openalex.org/W3015964387","https://openalex.org/W3025783616","https://openalex.org/W3096529494","https://openalex.org/W3096730275","https://openalex.org/W3097256596","https://openalex.org/W3097459123","https://openalex.org/W4232613155","https://openalex.org/W6637618735","https://openalex.org/W6685352114","https://openalex.org/W6717434760","https://openalex.org/W6752051073","https://openalex.org/W6775957535"],"related_works":["https://openalex.org/W3208297503","https://openalex.org/W3119773509","https://openalex.org/W2889153461","https://openalex.org/W2964117661","https://openalex.org/W4388405611","https://openalex.org/W2619127353","https://openalex.org/W2786094008","https://openalex.org/W3131501806","https://openalex.org/W2799683370","https://openalex.org/W2807745940"],"abstract_inverted_index":{"Despite":[0],"speaker":[1,147],"verification":[2],"has":[3],"achieved":[4],"significant":[5],"performance":[6],"improvement":[7],"with":[8,149],"the":[9,44,56,80,100,107,114,127,132,158],"development":[10],"of":[11,50,109,154],"deep":[12],"neural":[13],"networks,":[14],"do-main":[15],"mismatch":[16],"is":[17,62,85,97],"still":[18],"a":[19,30,150],"challenging":[20],"problem":[21],"in":[22],"this":[23,26],"field.":[24],"In":[25],"study,":[27],"we":[28,112],"propose":[29],"novel":[31],"framework":[32,139],"to":[33,105,125,157],"disentangle":[34],"speaker-related":[35,45,102,118],"and":[36,39,82,119,145],"domain-specific":[37,120],"features":[38,121],"apply":[40],"domain":[41,52,60,95],"adaptation":[42,53,70,96],"on":[43,55,99,131],"feature":[46,57,91,103],"space":[47,58,104],"solely.":[48],"Instead":[49],"performing":[51],"directly":[54],"where":[59],"information":[61,116],"not":[63],"removed,":[64],"using":[65],"disentanglement":[66],"can":[67,140],"efficiently":[68],"boost":[69],"performance.":[71],"To":[72],"be":[73],"specific,":[74],"our":[75,137],"model\u2019s":[76],"input":[77],"speech":[78],"from":[79],"source":[81],"target":[83],"domains":[84],"first":[86],"encoded":[87],"into":[88],"different":[89],"latent":[90],"spaces.":[92],"The":[93],"adversarial":[94],"conducted":[98],"shared":[101],"encourage":[106],"property":[108],"domain-invariance.":[110],"Further,":[111],"minimize":[113],"mutual":[115],"between":[117],"for":[122],"both":[123],"do-mains":[124],"enforce":[126],"disentanglement.":[128],"Experimental":[129],"results":[130],"VOiCES":[133],"dataset":[134],"demonstrate":[135],"that":[136],"proposed":[138],"effectively":[141],"generate":[142],"more":[143],"speaker-discriminative":[144],"domain-invariant":[146],"representations":[148],"relative":[151],"20.3%":[152],"reduction":[153],"EER":[155],"com-pared":[156],"original":[159],"ResNet-based":[160],"system.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":9}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}