{"id":"https://openalex.org/W4372341266","doi":"https://doi.org/10.1109/icassp49357.2023.10094954","title":"Exploring Binary Classification Loss for Speaker Verification","display_name":"Exploring Binary Classification Loss for Speaker Verification","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372341266","doi":"https://doi.org/10.1109/icassp49357.2023.10094954"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094954","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094954","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":"conference-paper","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/A5100690517","display_name":"Bing Han","orcid":"https://orcid.org/0000-0002-6319-6755"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Han","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101416769","display_name":"Zhengyang Chen","orcid":"https://orcid.org/0000-0003-1293-8146"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengyang Chen","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9994999766349792,"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/computer-science","display_name":"Computer science","score":0.8023875951766968},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7515092492103577},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6565092206001282},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.6357861757278442},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6095913648605347},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5477206707000732},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5244163274765015},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.5196155905723572},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4935113191604614},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4929494857788086},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4801035225391388},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.47266826033592224},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3838544487953186},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37994688749313354},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3258095979690552},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.28793126344680786}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8023875951766968},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7515092492103577},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6565092206001282},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.6357861757278442},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6095913648605347},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5477206707000732},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5244163274765015},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5196155905723572},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4935113191604614},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4929494857788086},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4801035225391388},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.47266826033592224},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3838544487953186},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37994688749313354},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3258095979690552},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.28793126344680786},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094954","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094954","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":[{"score":0.6100000143051147,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W125553504","https://openalex.org/W2150769028","https://openalex.org/W2219249508","https://openalex.org/W2601450892","https://openalex.org/W2726515241","https://openalex.org/W2784163702","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2963466847","https://openalex.org/W2969985801","https://openalex.org/W2972986505","https://openalex.org/W3010925296","https://openalex.org/W3013020904","https://openalex.org/W3034303554","https://openalex.org/W3094374485","https://openalex.org/W3103152812","https://openalex.org/W3135006803","https://openalex.org/W3190626620","https://openalex.org/W3198161435","https://openalex.org/W3205310163","https://openalex.org/W4286981691","https://openalex.org/W4288091954","https://openalex.org/W4296068762","https://openalex.org/W4297841827","https://openalex.org/W6682600690","https://openalex.org/W6735236233","https://openalex.org/W6769178842","https://openalex.org/W6784400926","https://openalex.org/W6799764170"],"related_works":["https://openalex.org/W4235705411","https://openalex.org/W1521299571","https://openalex.org/W2134501921","https://openalex.org/W204267554","https://openalex.org/W2147062549","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W3094374485","https://openalex.org/W4317103504","https://openalex.org/W3096066489"],"abstract_inverted_index":{"The":[0],"mismatch":[1],"between":[2,86],"close-set":[3],"training":[4,87,143],"and":[5,88],"open-set":[6],"testing":[7],"usually":[8,41],"leads":[9],"to":[10,62,114,129,137],"significant":[11],"performance":[12],"degradation":[13,44],"for":[14,119],"speaker":[15,65],"verification":[16],"task.":[17],"For":[18],"existing":[19,100],"loss":[20,101],"functions,":[21,102],"metric":[22],"learning-based":[23],"objectives":[24],"depend":[25],"strongly":[26],"on":[27,47,92,104],"searching":[28],"effective":[29],"pairs":[30],"which":[31,57,133],"might":[32],"hinder":[33],"further":[34,120],"improvements.":[35,121],"And":[36],"popular":[37],"multi-classification":[38],"methods":[39],"are":[40],"observed":[42],"with":[43,117,145],"when":[45],"evaluated":[46],"unseen":[48],"speakers.":[49],"In":[50],"this":[51,77],"work,":[52],"we":[53],"introduce":[54],"SphereFace2":[55,97,123],"framework":[56],"uses":[58],"several":[59],"binary":[60],"classifiers":[61],"train":[63],"the":[64,84,96,135,141],"model":[66],"in":[67,140],"a":[68],"pair-wise":[69],"manner":[70],"instead":[71],"of":[72],"performing":[73],"multi-classification.":[74],"Benefiting":[75],"from":[76],"learning":[78],"paradigm,":[79],"it":[80,118],"can":[81],"efficiently":[82],"alleviate":[83],"gap":[85],"evaluation.":[89],"Experiments":[90],"conducted":[91],"Voxceleb":[93],"show":[94],"that":[95],"outperforms":[98],"other":[99],"especially":[103],"hard":[105],"trials.":[106],"Besides,":[107],"large":[108],"margin":[109],"fine-tuning":[110],"strategy":[111],"is":[112],"proven":[113],"be":[115,138],"compatible":[116],"Finally,":[122],"also":[124],"shows":[125],"its":[126],"strong":[127],"robustness":[128],"class-wise":[130],"noisy":[131],"labels":[132],"has":[134],"potential":[136],"applied":[139],"semi-supervised":[142],"scenario":[144],"inaccurate":[146],"estimated":[147],"pseudo":[148],"labels.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}