{"id":"https://openalex.org/W4392903404","doi":"https://doi.org/10.1109/icassp48485.2024.10447813","title":"Balanced Learning for Multi-Domain Long-Tailed Speaker Recognition","display_name":"Balanced Learning for Multi-Domain Long-Tailed Speaker Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903404","doi":"https://doi.org/10.1109/icassp48485.2024.10447813"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447813","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447813","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/A5077458889","display_name":"Janghoon Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I19268510","display_name":"Qualcomm (United Kingdom)","ror":"https://ror.org/04d3djg48","country_code":"GB","type":"company","lineage":["https://openalex.org/I19268510","https://openalex.org/I4210087596"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Janghoon Cho","raw_affiliation_strings":["Qualcomm AI Research is an Initiative of Qualcomm Technologies, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm AI Research is an Initiative of Qualcomm Technologies, Inc","institution_ids":["https://openalex.org/I19268510"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031869988","display_name":"Sunghyun Park","orcid":null},"institutions":[{"id":"https://openalex.org/I19268510","display_name":"Qualcomm (United Kingdom)","ror":"https://ror.org/04d3djg48","country_code":"GB","type":"company","lineage":["https://openalex.org/I19268510","https://openalex.org/I4210087596"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sunghyun Park","raw_affiliation_strings":["Qualcomm AI Research is an Initiative of Qualcomm Technologies, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm AI Research is an Initiative of Qualcomm Technologies, Inc","institution_ids":["https://openalex.org/I19268510"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010227336","display_name":"Hyunsin Park","orcid":"https://orcid.org/0000-0003-3556-5792"},"institutions":[{"id":"https://openalex.org/I19268510","display_name":"Qualcomm (United Kingdom)","ror":"https://ror.org/04d3djg48","country_code":"GB","type":"company","lineage":["https://openalex.org/I19268510","https://openalex.org/I4210087596"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hyunsin Park","raw_affiliation_strings":["Qualcomm AI Research is an Initiative of Qualcomm Technologies, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm AI Research is an Initiative of Qualcomm Technologies, Inc","institution_ids":["https://openalex.org/I19268510"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069883233","display_name":"Hyung Woo Park","orcid":"https://orcid.org/0000-0002-5341-9249"},"institutions":[{"id":"https://openalex.org/I19268510","display_name":"Qualcomm (United Kingdom)","ror":"https://ror.org/04d3djg48","country_code":"GB","type":"company","lineage":["https://openalex.org/I19268510","https://openalex.org/I4210087596"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hyoungwoo Park","raw_affiliation_strings":["Qualcomm AI Research is an Initiative of Qualcomm Technologies, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm AI Research is an Initiative of Qualcomm Technologies, Inc","institution_ids":["https://openalex.org/I19268510"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012112492","display_name":"Seung-Han Yang","orcid":"https://orcid.org/0000-0001-7842-0492"},"institutions":[{"id":"https://openalex.org/I19268510","display_name":"Qualcomm (United Kingdom)","ror":"https://ror.org/04d3djg48","country_code":"GB","type":"company","lineage":["https://openalex.org/I19268510","https://openalex.org/I4210087596"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Seunghan Yang","raw_affiliation_strings":["Qualcomm AI Research is an Initiative of Qualcomm Technologies, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm AI Research is an Initiative of Qualcomm Technologies, Inc","institution_ids":["https://openalex.org/I19268510"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091430620","display_name":"Sungrack Yun","orcid":"https://orcid.org/0000-0003-2462-3854"},"institutions":[{"id":"https://openalex.org/I19268510","display_name":"Qualcomm (United Kingdom)","ror":"https://ror.org/04d3djg48","country_code":"GB","type":"company","lineage":["https://openalex.org/I19268510","https://openalex.org/I4210087596"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sungrack Yun","raw_affiliation_strings":["Qualcomm AI Research is an Initiative of Qualcomm Technologies, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm AI Research is an Initiative of Qualcomm Technologies, Inc","institution_ids":["https://openalex.org/I19268510"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3057,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.46059675,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"7465","last_page":"7469"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9976000189781189,"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":0.8125530481338501},{"id":"https://openalex.org/keywords/orthogonality","display_name":"Orthogonality","score":0.7701144218444824},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7680792808532715},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.751130223274231},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6321750283241272},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6093682050704956},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5734722018241882},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5175368189811707},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42781034111976624},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.41137734055519104},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33677226305007935},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1096433699131012}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8125530481338501},{"id":"https://openalex.org/C17137986","wikidata":"https://www.wikidata.org/wiki/Q215067","display_name":"Orthogonality","level":2,"score":0.7701144218444824},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7680792808532715},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.751130223274231},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6321750283241272},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6093682050704956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5734722018241882},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5175368189811707},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42781034111976624},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.41137734055519104},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33677226305007935},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1096433699131012},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447813","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447813","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1731081199","https://openalex.org/W2012210378","https://openalex.org/W2748488820","https://openalex.org/W2953300268","https://openalex.org/W2962898354","https://openalex.org/W2963691377","https://openalex.org/W2964052309","https://openalex.org/W2964124968","https://openalex.org/W2969985801","https://openalex.org/W2970941190","https://openalex.org/W2981087920","https://openalex.org/W3013020904","https://openalex.org/W3030437843","https://openalex.org/W3152426975","https://openalex.org/W4206908380","https://openalex.org/W4312321233","https://openalex.org/W4312769845","https://openalex.org/W6637618735","https://openalex.org/W6758038952","https://openalex.org/W6764733053","https://openalex.org/W6768920361","https://openalex.org/W6771467084","https://openalex.org/W6802669646"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W2095582735","https://openalex.org/W4389116644","https://openalex.org/W2059318893","https://openalex.org/W1965698851","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W834942123"],"abstract_inverted_index":{"This":[0],"paper":[1],"considers":[2],"two":[3,56],"types":[4],"of":[5,86,123],"imbalance":[6,19],"problems":[7],"commonly":[8],"inherent":[9],"in":[10,34],"large-scale":[11],"datasets:":[12],"multiple":[13],"domain":[14,81],"and":[15,30,62,80,88,94,138],"class":[16,74],"imbalance.":[17],"Class":[18],"causes":[20],"the":[21,27,84,103,121],"algorithm":[22],"to":[23,116],"be":[24],"biased":[25],"toward":[26],"majority":[28],"classes,":[29],"multiple-domain":[31],"data":[32],"results":[33],"significant":[35],"performance":[36],"disparities":[37],"for":[38,51,91],"different":[39],"domains.":[40],"To":[41],"tackle":[42],"these":[43],"challenges,":[44],"we":[45],"propose":[46],"a":[47],"novel":[48],"learning":[49,98],"approach":[50,125],"multi-domain":[52],"imbalanced":[53],"datasets,":[54,135],"featuring":[55],"techniques:":[57],"(i)":[58],"distribution-aware":[59,69],"partial":[60,70],"mask":[61,71],"(ii)":[63],"domain-wise":[64,104],"interprototype":[65,105],"loss":[66,106],"function.":[67],"The":[68],"selects":[72],"negative":[73,89],"centers":[75],"based":[76],"on":[77,130],"class-level":[78],"distribution":[79],"labels,":[82],"adjusting":[83],"ratio":[85],"positive":[87],"updates":[90],"prototype":[92,110],"vectors":[93,111],"enhancing":[95],"discriminative":[96],"feature":[97],"within":[99,112],"each":[100,113],"domain.":[101],"Additionally,":[102],"enforces":[107],"orthogonality":[108],"among":[109],"domain,":[114],"leading":[115],"increased":[117],"discriminativeness.":[118],"We":[119],"demonstrate":[120],"superiority":[122],"our":[124],"over":[126],"baselines":[127],"through":[128],"experiments":[129],"publicly":[131],"available":[132],"speaker":[133],"recognition":[134],"including":[136],"CN-Celeb":[137],"Mozilla":[139],"Common":[140],"Voice.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}