{"id":"https://openalex.org/W4392903951","doi":"https://doi.org/10.1109/icassp48485.2024.10446607","title":"Meta Representation Learning Method for Robust Speaker Verification in Unseen Domains","display_name":"Meta Representation Learning Method for Robust Speaker Verification in Unseen Domains","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903951","doi":"https://doi.org/10.1109/icassp48485.2024.10446607"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446607","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446607","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100781674","display_name":"Jiantao Zhang","orcid":"https://orcid.org/0000-0001-8418-9047"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jian-Tao Zhang","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,China","National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381758","display_name":"Yan Song","orcid":"https://orcid.org/0000-0002-5668-9068"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Song","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,China","National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100678192","display_name":"Jin Li","orcid":"https://orcid.org/0000-0001-5737-3594"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Li","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,China","iFLYTEK Research, iFLYTEK Co. Ltd., Hefei, China","National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"iFLYTEK Research, iFLYTEK Co. Ltd., Hefei, China","institution_ids":[]},{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038369085","display_name":"Wu Guo","orcid":"https://orcid.org/0000-0002-3779-7944"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu Guo","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,China","National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108901077","display_name":"Hao-Yu Song","orcid":null},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hao-Yu Song","raw_affiliation_strings":["The Australian National University,Australian","The Australian National University, Australian"],"affiliations":[{"raw_affiliation_string":"The Australian National University,Australian","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"The Australian National University, Australian","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000620878","display_name":"Ian McLoughlin","orcid":"https://orcid.org/0000-0001-7111-2008"},"institutions":[{"id":"https://openalex.org/I168639165","display_name":"Singapore Institute of Technology","ror":"https://ror.org/01v2c2791","country_code":"SG","type":"education","lineage":["https://openalex.org/I168639165"]},{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Ian McLoughlin","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,China","National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","ICT Cluster, Singapore Institute of Technology, Singapore"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"ICT Cluster, Singapore Institute of Technology, Singapore","institution_ids":["https://openalex.org/I168639165"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100781674"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0261224,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":null,"first_page":"11301","last_page":"11305"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9932000041007996,"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/T10860","display_name":"Speech and Audio Processing","score":0.9925000071525574,"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/speaker-verification","display_name":"Speaker verification","score":0.8175452947616577},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.797460675239563},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6972188949584961},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6612075567245483},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5734525918960571},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5480851531028748},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5111461281776428},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.49582967162132263},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4770847260951996},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4694245457649231},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4673880338668823},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.46323344111442566},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.45134657621383667},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43685853481292725},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.2179887592792511},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10074037313461304}],"concepts":[{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.8175452947616577},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.797460675239563},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6972188949584961},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6612075567245483},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5734525918960571},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5480851531028748},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5111461281776428},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.49582967162132263},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4770847260951996},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4694245457649231},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4673880338668823},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.46323344111442566},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.45134657621383667},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43685853481292725},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2179887592792511},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10074037313461304},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446607","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446607","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:figshare.com:article/27336675","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"Conference contribution"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/27336675","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"Conference contribution"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1731081199","https://openalex.org/W2122364000","https://openalex.org/W2183016404","https://openalex.org/W2194775991","https://openalex.org/W2598634450","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2794506738","https://openalex.org/W2807246346","https://openalex.org/W2808631503","https://openalex.org/W2888968865","https://openalex.org/W2890964092","https://openalex.org/W2936028438","https://openalex.org/W2963275094","https://openalex.org/W2963446838","https://openalex.org/W2964288524","https://openalex.org/W2969985801","https://openalex.org/W3024869864","https://openalex.org/W3094665028","https://openalex.org/W3095862185","https://openalex.org/W3097000690","https://openalex.org/W3160646455","https://openalex.org/W4206908380","https://openalex.org/W4224917963","https://openalex.org/W4224919627","https://openalex.org/W4224927738","https://openalex.org/W4296068790","https://openalex.org/W6631362777","https://openalex.org/W6637618735","https://openalex.org/W6639480849","https://openalex.org/W6735531217"],"related_works":["https://openalex.org/W3082848404","https://openalex.org/W2081900870","https://openalex.org/W1979583797","https://openalex.org/W2016864125","https://openalex.org/W2372254676","https://openalex.org/W2080135837","https://openalex.org/W2945706271","https://openalex.org/W1996621592","https://openalex.org/W2114169842","https://openalex.org/W2535808783"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,63,104],"meta":[4],"representation":[5],"learning":[6,23],"method":[7],"for":[8,112,129],"robust":[9],"speaker":[10],"verification":[11],"(SV)":[12],"in":[13,132],"unseen":[14,130],"domains.":[15],"It":[16],"is":[17,69,110],"known":[18],"that":[19],"the":[20,72,99,114],"existing":[21,79],"embedding":[22],"based":[24],"SV":[25],"systems":[26],"may":[27],"suffer":[28],"from":[29,58],"domain":[30,44,54,65,115],"mismatch":[31,45],"issues.":[32],"To":[33],"address":[34],"this,":[35],"we":[36],"propose":[37],"an":[38],"episodic":[39,56,84],"training":[40,85],"procedure":[41],"to":[42,78,97],"compensate":[43],"conditions":[46],"at":[47],"runtime.":[48],"Specifically,":[49],"episodes":[50],"are":[51,91],"constructed":[52],"with":[53,94],"balanced":[55],"sampling":[57],"two":[59],"different":[60,95],"domains,":[61],"and":[62,76,88,122],"new":[64],"alignment":[66,107],"(DA)":[67],"module":[68],"added":[70],"besides":[71],"feature":[73],"extractor":[74],"(FE)":[75],"classifier":[77],"network":[80],"structures.":[81],"In":[82],"each":[83],"iteration,":[86],"FE":[87],"DA":[89],"modules":[90],"optimized":[92],"separately":[93],"objectives":[96],"improve":[98],"robustness":[100],"of":[101],"learning.":[102],"Besides,":[103],"cross-domain":[105],"inter-class":[106],"(CDICA)":[108],"loss":[109],"proposed":[111],"improving":[113],"generalization":[116],"ability.":[117],"Experimental":[118],"results":[119],"on":[120],"CNCeleb":[121],"VoxCeleb":[123],"benchmarks":[124],"demonstrate":[125],"significant":[126],"performance":[127],"gains":[128],"domains":[131],"SV.":[133]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}