{"id":"https://openalex.org/W4372349064","doi":"https://doi.org/10.1109/icassp49357.2023.10095876","title":"Optimal Transport with a Diversified Memory Bank for Cross-Domain Speaker Verification","display_name":"Optimal Transport with a Diversified Memory Bank for Cross-Domain Speaker Verification","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372349064","doi":"https://doi.org/10.1109/icassp49357.2023.10095876"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095876","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5059846834","display_name":"Ruiteng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ruiteng Zhang","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,Tianjin,China","College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027428789","display_name":"Jianguo Wei","orcid":"https://orcid.org/0000-0002-8964-9759"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]},{"id":"https://openalex.org/I290007724","display_name":"Qinghai University for Nationalities","ror":"https://ror.org/01e7csr82","country_code":"CN","type":"education","lineage":["https://openalex.org/I290007724"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianguo Wei","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,Tianjin,China","College of Intelligence and Computing, Tianjin University, Tianjin, China","Computer College, Qinghai Nationalities University, Xining, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Computer College, Qinghai Nationalities University, Xining, China","institution_ids":["https://openalex.org/I290007724"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034792613","display_name":"Xugang Lu","orcid":"https://orcid.org/0000-0001-7075-448X"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xugang Lu","raw_affiliation_strings":["National Institute of Information and Communications Technology,Kyoto,Japan","National Institute of Information and Communications Technology, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology,Kyoto,Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082286929","display_name":"Wenhuan Lu","orcid":"https://orcid.org/0000-0002-7951-8907"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhuan Lu","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,Tianjin,China","College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012455357","display_name":"Di Jin","orcid":"https://orcid.org/0000-0002-7445-9936"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Jin","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,Tianjin,China","College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100351795","display_name":"Lin Zhang","orcid":"https://orcid.org/0000-0001-7826-2850"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Lin Zhang","raw_affiliation_strings":["National Institute of Informatics,Tokyo,Japan","National Institute of Informatics, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Tokyo,Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006839468","display_name":"Junhai Xu","orcid":"https://orcid.org/0000-0002-4289-647X"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhai Xu","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,Tianjin,China","College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5059846834"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":1.2205,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82816976,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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":0.9975000023841858,"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":0.8041256666183472},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7897448539733887},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6386704444885254},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.6314609050750732},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5896840691566467},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5275996327400208},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45065638422966003},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4320886731147766},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4292590618133545},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.42725831270217896},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4269754886627197},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32419365644454956},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.307535320520401},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07036998867988586}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8041256666183472},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7897448539733887},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6386704444885254},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.6314609050750732},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5896840691566467},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5275996327400208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45065638422966003},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4320886731147766},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4292590618133545},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.42725831270217896},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4269754886627197},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32419365644454956},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.307535320520401},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07036998867988586},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095876","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1594039573","https://openalex.org/W1882958252","https://openalex.org/W2100913937","https://openalex.org/W2121812409","https://openalex.org/W2132984949","https://openalex.org/W2187089797","https://openalex.org/W2219249508","https://openalex.org/W2748488820","https://openalex.org/W2801581493","https://openalex.org/W2889048668","https://openalex.org/W2901368553","https://openalex.org/W2936780106","https://openalex.org/W2962997028","https://openalex.org/W2963187488","https://openalex.org/W2963242190","https://openalex.org/W2969985801","https://openalex.org/W2972743990","https://openalex.org/W3024869864","https://openalex.org/W3096831136","https://openalex.org/W3097244734","https://openalex.org/W3160646455","https://openalex.org/W3162130072","https://openalex.org/W3163150275","https://openalex.org/W3208777959","https://openalex.org/W3212125355","https://openalex.org/W4221154746","https://openalex.org/W4226329757","https://openalex.org/W4298333447","https://openalex.org/W6631362777","https://openalex.org/W6639480849","https://openalex.org/W6675038308","https://openalex.org/W6679390333","https://openalex.org/W6688816777","https://openalex.org/W6737976933","https://openalex.org/W6754473786","https://openalex.org/W6795356967","https://openalex.org/W6803559545","https://openalex.org/W6810752947"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W2053159670","https://openalex.org/W3148366653","https://openalex.org/W1521299571","https://openalex.org/W4312246223","https://openalex.org/W3095180122","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W2886606195","https://openalex.org/W4252590334"],"abstract_inverted_index":{"Optimal":[0],"transport":[1,109],"(OT)":[2],"can":[3],"be":[4],"applied":[5],"to":[6,20,84],"cross-domain":[7],"adaptation":[8,52],"in":[9,24,33,115],"speaker":[10,93],"verification":[11],"(SV)":[12],"by":[13,71],"converting":[14],"speakers'":[15],"probability":[16],"distributions":[17],"from":[18,90,107],"source":[19],"target":[21,124],"domains.":[22],"However,":[23],"scenarios":[25],"involving":[26],"over-massive":[27],"categories":[28],"(speakers)":[29],"or":[30],"difficult":[31],"samples":[32,89,114],"discrimination,":[34],"OT":[35,57,106],"often":[36],"has":[37],"difficulty":[38],"computing":[39],"effective":[40],"transports.":[41],"To":[42],"address":[43],"this":[44],"challenge,":[45],"we":[46],"propose":[47],"an":[48],"OT-based":[49,137],"unsupervised":[50,129],"domain":[51],"(UDA)":[53],"framework":[54],"for":[55],"SV,":[56],"with":[58,94],"a":[59,100],"diversified":[60],"memory":[61],"bank,":[62],"called":[63],"DMB-OT,":[64],"which":[65,82],"ensures":[66],"the":[67,77,91,116,134,143,146],"accuracy":[68],"of":[69,80,119,136,145],"transfers":[70],"two":[72],"strategies:":[73],"(1)":[74],"It":[75],"regularizes":[76],"solution":[78],"space":[79],"OT,":[81],"attempts":[83],"plan":[85],"transformations":[86],"between":[87],"audio":[88],"same":[92],"high":[95],"confidence;":[96],"(2)":[97],"it":[98],"integrates":[99],"dynamic":[101],"curriculum":[102],"learning":[103],"algorithm,":[104],"preventing":[105],"calculating":[108],"couplings":[110],"based":[111],"on":[112],"hard-discriminative":[113],"early":[117],"stage":[118],"UDA.":[120],"Experiments":[121],"under":[122],"different":[123],"domains":[125],"showed":[126],"that":[127],"our":[128],"DMB-OT":[130],"could":[131,140],"significantly":[132],"improve":[133],"performance":[135,144],"UDA":[138],"and":[139],"even":[141],"match":[142],"supervised":[147],"PLDA-based":[148],"adaptation.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":6}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}