{"id":"https://openalex.org/W3015893497","doi":"https://doi.org/10.1109/icassp40776.2020.9053674","title":"Partial AUC Optimization Based Deep Speaker Embeddings with Class-Center Learning for Text-Independent Speaker Verification","display_name":"Partial AUC Optimization Based Deep Speaker Embeddings with Class-Center Learning for Text-Independent Speaker Verification","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015893497","doi":"https://doi.org/10.1109/icassp40776.2020.9053674","mag":"3015893497"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053674","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053674","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5041350492","display_name":"Zhongxin Bai","orcid":"https://orcid.org/0000-0003-3575-7014"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhongxin Bai","raw_affiliation_strings":["Center of Intelligent Acoustics and Immersive Communications and School of Marine Science and Technology, Northwestern Polytechnical University"],"affiliations":[{"raw_affiliation_string":"Center of Intelligent Acoustics and Immersive Communications and School of Marine Science and Technology, Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450091","display_name":"Xiao-Lei Zhang","orcid":"https://orcid.org/0000-0001-7694-193X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-Lei Zhang","raw_affiliation_strings":["Center of Intelligent Acoustics and Immersive Communications and School of Marine Science and Technology, Northwestern Polytechnical University"],"affiliations":[{"raw_affiliation_string":"Center of Intelligent Acoustics and Immersive Communications and School of Marine Science and Technology, Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056129529","display_name":"Jingdong Chen","orcid":"https://orcid.org/0000-0003-0083-9247"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingdong Chen","raw_affiliation_strings":["Center of Intelligent Acoustics and Immersive Communications and School of Marine Science and Technology, Northwestern Polytechnical University"],"affiliations":[{"raw_affiliation_string":"Center of Intelligent Acoustics and Immersive Communications and School of Marine Science and Technology, Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041350492"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":4.2419,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.95080577,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6819","last_page":"6823"},"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":0.9997000098228455,"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":0.9983999729156494,"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/softmax-function","display_name":"Softmax function","score":0.9321556091308594},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7239203453063965},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.7084549069404602},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5942891240119934},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5879461169242859},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5425733327865601},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5424304008483887},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5261330604553223},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.49875402450561523},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.46955400705337524},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4619444012641907},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.455496609210968},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43219491839408875}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.9321556091308594},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7239203453063965},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7084549069404602},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5942891240119934},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5879461169242859},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5425733327865601},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5424304008483887},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5261330604553223},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.49875402450561523},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.46955400705337524},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4619444012641907},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.455496609210968},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43219491839408875},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053674","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053674","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W2114925438","https://openalex.org/W2516764878","https://openalex.org/W2612434969","https://openalex.org/W2726515241","https://openalex.org/W2746742816","https://openalex.org/W2802488037","https://openalex.org/W2802973008","https://openalex.org/W2808631503","https://openalex.org/W2889045432","https://openalex.org/W2889519245","https://openalex.org/W2890964092","https://openalex.org/W2916104401","https://openalex.org/W2916301830","https://openalex.org/W2938358845","https://openalex.org/W2939634425","https://openalex.org/W2956925952","https://openalex.org/W2962788625","https://openalex.org/W2962832278","https://openalex.org/W2963371159","https://openalex.org/W2972441390","https://openalex.org/W2972606715","https://openalex.org/W2972961496","https://openalex.org/W2972986505","https://openalex.org/W3006478128","https://openalex.org/W3024039722","https://openalex.org/W6631362777","https://openalex.org/W6737575990","https://openalex.org/W6759166234","https://openalex.org/W6777399054"],"related_works":["https://openalex.org/W4306178031","https://openalex.org/W2118039276","https://openalex.org/W2051274299","https://openalex.org/W468945283","https://openalex.org/W4235705411","https://openalex.org/W1521299571","https://openalex.org/W1996621592","https://openalex.org/W2134501921","https://openalex.org/W204267554","https://openalex.org/W2147062549"],"abstract_inverted_index":{"Deep":[0],"embedding":[1,50,87],"based":[2,88,97],"text-independent":[3,89],"speaker":[4,39,90],"verification":[5,28,32,70],"has":[6],"demonstrated":[7],"superior":[8],"performance":[9],"to":[10,102,115,118],"traditional":[11],"methods":[12,51],"in":[13,122,128],"many":[14],"challenging":[15],"scenarios.":[16],"Its":[17],"loss":[18,33,55,71,113,121,142,151],"functions":[19,34,56],"can":[20],"be":[21,116],"generally":[22],"categorized":[23],"into":[24],"two":[25],"classes,":[26],"i.e.,":[27],"and":[29,132],"identification.":[30],"The":[31],"match":[35],"the":[36,53,74,80,104,111,119,126,129,139,148],"pipeline":[37],"of":[38,76],"verification,":[40],"but":[41],"their":[42,62],"implementations":[43],"are":[44],"difficult.":[45],"Thus,":[46],"most":[47],"state-of-the-art":[48,149],"deep":[49,86],"use":[52],"identification":[54,120,150],"with":[57,147],"softmax":[58],"output":[59],"units":[60],"or":[61],"variants.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67],"propose":[68,94],"a":[69,95],"function,":[72],"named":[73],"maximization":[75],"partial":[77],"area":[78],"under":[79],"Receiver-operating-characteristic":[81],"(ROC)":[82],"curve":[83],"(pAUC),":[84],"for":[85,110],"verification.":[91],"We":[92],"also":[93],"class-center":[96],"training":[98,105],"trial":[99],"construction":[100],"method":[101],"improve":[103],"efficiency,":[106],"which":[107],"is":[108,144],"critical":[109],"proposed":[112,140],"function":[114,143],"comparable":[117],"performance.":[123],"Experiments":[124],"on":[125],"Speaker":[127],"Wild":[130],"(SITW)":[131],"NIST":[133],"SRE":[134],"2016":[135],"datasets":[136],"show":[137],"that":[138],"pAUC":[141],"highly":[145],"competitive":[146],"functions.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":10},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}