{"id":"https://openalex.org/W4392931137","doi":"https://doi.org/10.1109/icassp48485.2024.10448178","title":"An Investigation of Distribution Alignment in Multi-Genre Speaker Recognition","display_name":"An Investigation of Distribution Alignment in Multi-Genre Speaker Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392931137","doi":"https://doi.org/10.1109/icassp48485.2024.10448178"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448178","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448178","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039042766","display_name":"Zhenyu Zhou","orcid":"https://orcid.org/0000-0002-3344-4463"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhenyu Zhou","raw_affiliation_strings":["Tsinghua University,Center for Speech and Language Technologies, BNRist,China","Center for Speech and Language Technologies, BNRist, Tsinghua University, China","Beijing University of Posts and Telecommunications, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Center for Speech and Language Technologies, BNRist,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Center for Speech and Language Technologies, BNRist, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100713230","display_name":"Junhui Chen","orcid":"https://orcid.org/0000-0002-3507-3942"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhui Chen","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China","Beijing University of Posts and Telecommunications, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020246512","display_name":"Namin Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210146936","display_name":"Huawei Technologies (United States)","ror":"https://ror.org/03jyqk712","country_code":"US","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210146936"]},{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Namin Wang","raw_affiliation_strings":["Huawei Cloud,China","Huawei Cloud, China"],"affiliations":[{"raw_affiliation_string":"Huawei Cloud,China","institution_ids":["https://openalex.org/I2250955327","https://openalex.org/I4210146936"]},{"raw_affiliation_string":"Huawei Cloud, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050701255","display_name":"Lantian Li","orcid":"https://orcid.org/0000-0003-4274-7930"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lantian Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China","Beijing University of Posts and Telecommunications, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035406686","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0001-9454-3126"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Tsinghua University,Center for Speech and Language Technologies, BNRist,China","Center for Speech and Language Technologies, BNRist, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Center for Speech and Language Technologies, BNRist,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Center for Speech and Language Technologies, BNRist, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5039042766"],"corresponding_institution_ids":["https://openalex.org/I139759216","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.0107,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.78621126,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"11596","last_page":"11600"},"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":0.9986000061035156,"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":0.9979000091552734,"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":0.7822495102882385},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6231639385223389},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5600461363792419},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4973774254322052},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.48493340611457825},{"id":"https://openalex.org/keywords/mainstream","display_name":"Mainstream","score":0.43828386068344116},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43125224113464355},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39789339900016785},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3526753783226013},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1021433174610138}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7822495102882385},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6231639385223389},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5600461363792419},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4973774254322052},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.48493340611457825},{"id":"https://openalex.org/C2777617010","wikidata":"https://www.wikidata.org/wiki/Q18957","display_name":"Mainstream","level":2,"score":0.43828386068344116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43125224113464355},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39789339900016785},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3526753783226013},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1021433174610138},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448178","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448178","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4173487881","display_name":null,"funder_award_id":"2022061","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4491952354","display_name":null,"funder_award_id":"62171250","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8126170492","display_name":null,"funder_award_id":"202206","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2110097068","https://openalex.org/W2125865219","https://openalex.org/W2164943005","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2520774990","https://openalex.org/W2752782242","https://openalex.org/W2794506738","https://openalex.org/W2801581493","https://openalex.org/W2888897023","https://openalex.org/W2890964092","https://openalex.org/W2938358845","https://openalex.org/W2963275094","https://openalex.org/W2963446838","https://openalex.org/W2964288524","https://openalex.org/W2973032144","https://openalex.org/W3010925296","https://openalex.org/W3015598461","https://openalex.org/W3015964387","https://openalex.org/W3133917823","https://openalex.org/W3160646455","https://openalex.org/W3217778739","https://openalex.org/W4206908380","https://openalex.org/W4224919627","https://openalex.org/W4283014282","https://openalex.org/W4296068790","https://openalex.org/W4321524405","https://openalex.org/W4372340947","https://openalex.org/W6639480849","https://openalex.org/W6676663998","https://openalex.org/W6849840340"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2368768466","https://openalex.org/W2757081366","https://openalex.org/W3197877226"],"abstract_inverted_index":{"Multi-genre":[0],"speaker":[1,31,137,148],"recognition":[2],"is":[3,23,39,67,152],"becoming":[4],"increasingly":[5],"popular":[6],"due":[7],"to":[8,11,43,86,154],"its":[9],"ability":[10],"better":[12],"represent":[13],"the":[14,24,28,62,100,119,134,143],"complexities":[15],"of":[16,30,64,74,118,136],"real-world":[17],"applications.":[18],"However,":[19,112],"a":[20,40,54,58,71,156],"major":[21],"challenge":[22],"significant":[25],"shift":[26],"in":[27,125],"distribution":[29,37,76,106],"vectors":[32,138],"across":[33],"different":[34],"genres.":[35],"While":[36],"alignment":[38,77,107],"common":[41],"approach":[42],"address":[44,142],"this":[45],"challenge,":[46],"previous":[47],"studies":[48],"have":[49],"mainly":[50],"focused":[51],"on":[52,79,99],"aligning":[53,133],"source":[55],"domain":[56],"with":[57],"target":[59],"domain,":[60],"and":[61,95],"performance":[63,124],"multi-genre":[65,80,147],"data":[66],"unknown.This":[68],"paper":[69],"presents":[70],"comprehensive":[72,158],"study":[73],"mainstream":[75],"methods":[78,92,121],"data,":[81],"where":[82],"multiple":[83],"distributions":[84,135],"need":[85],"be":[87],"aligned.":[88],"We":[89],"analyze":[90],"various":[91],"both":[93],"qualitatively":[94],"quantitatively.":[96],"Our":[97],"experiments":[98],"CN-Celeb":[101],"dataset":[102],"show":[103],"that":[104,116,131],"within-between":[105],"(WBDA)":[108],"performs":[109],"relatively":[110],"better.":[111],"we":[113],"also":[114],"found":[115],"none":[117],"investigated":[120],"consistently":[122],"improved":[123],"all":[126],"test":[127],"cases.":[128],"This":[129],"suggests":[130],"solely":[132],"may":[139],"not":[140],"fully":[141],"challenges":[144],"posed":[145],"by":[146],"recognition.":[149],"Further":[150],"investigation":[151],"necessary":[153],"develop":[155],"more":[157],"solution.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}