{"id":"https://openalex.org/W4401110548","doi":"https://doi.org/10.1109/cai59869.2024.00186","title":"On the influence of metric learning loss functions for robust self-supervised speaker verification to label noise","display_name":"On the influence of metric learning loss functions for robust self-supervised speaker verification to label noise","publication_year":2024,"publication_date":"2024-06-25","ids":{"openalex":"https://openalex.org/W4401110548","doi":"https://doi.org/10.1109/cai59869.2024.00186"},"language":"en","primary_location":{"id":"doi:10.1109/cai59869.2024.00186","doi":"https://doi.org/10.1109/cai59869.2024.00186","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cai59869.2024.00186","pdf_url":null,"source":{"id":"https://openalex.org/S7407087030","display_name":"IEEE Conference on Artificial Intelligence (CAI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Conference on Artificial Intelligence (CAI)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5066980762","display_name":"Abderrahim Fathan","orcid":"https://orcid.org/0000-0002-5749-1643","observed_orcids":["https://orcid.org/0000-0002-5749-1643"]},"institutions":[{"id":"https://openalex.org/I4210111842","display_name":"Computer Research Institute of Montr\u00e9al","ror":"https://ror.org/0279d5115","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210111842"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Abderrahim Fathan","raw_affiliation_strings":["Computer Research Institute of Montreal (CRIM),Montreal,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Research Institute of Montreal (CRIM),Montreal,Canada","institution_ids":["https://openalex.org/I4210111842"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaolin Zhu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210111842","display_name":"Computer Research Institute of Montr\u00e9al","ror":"https://ror.org/0279d5115","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210111842"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xiaolin Zhu","raw_affiliation_strings":["Computer Research Institute of Montreal (CRIM),Montreal,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Research Institute of Montreal (CRIM),Montreal,Canada","institution_ids":["https://openalex.org/I4210111842"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055570520","display_name":"Jahangir Alam","orcid":"https://orcid.org/0000-0003-1081-3665","observed_orcids":["https://orcid.org/0000-0003-1081-3665"]},"institutions":[{"id":"https://openalex.org/I4210111842","display_name":"Computer Research Institute of Montr\u00e9al","ror":"https://ror.org/0279d5115","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210111842"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jahangir Alam","raw_affiliation_strings":["Computer Research Institute of Montreal (CRIM),Montreal,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Research Institute of Montreal (CRIM),Montreal,Canada","institution_ids":["https://openalex.org/I4210111842"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210111842"],"apc_list":null,"apc_paid":null,"fwci":0.1527,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.33019144,"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":"1024","last_page":"1031"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9897000193595886,"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":0.9897000193595886,"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":0.004600000102072954,"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/T10828","display_name":"Biometric Identification and Security","score":0.000699999975040555,"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/label-noise-robustness","display_name":"label noise robustness","score":0.9179999828338623},{"id":"https://openalex.org/keywords/pseudo-labeling","display_name":"pseudo-labeling","score":0.7549999952316284},{"id":"https://openalex.org/keywords/loss-function-selection","display_name":"loss function selection","score":0.5189999938011169}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.748798668384552},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.684175431728363},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5985035300254822},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5522676110267639},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5372374653816223},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.49400097131729126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45745790004730225},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4196772277355194},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3541359305381775},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07736533880233765},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cai59869.2024.00186","doi":"https://doi.org/10.1109/cai59869.2024.00186","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cai59869.2024.00186","pdf_url":null,"source":{"id":"https://openalex.org/S7407087030","display_name":"IEEE Conference on Artificial Intelligence (CAI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Conference on Artificial Intelligence (CAI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320319880","display_name":"Government of Canada","ror":"https://ror.org/010q4q527"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1666942233","https://openalex.org/W1866072925","https://openalex.org/W1936725236","https://openalex.org/W2035890032","https://openalex.org/W2100031962","https://openalex.org/W2146849125","https://openalex.org/W2150769028","https://openalex.org/W2156483112","https://openalex.org/W2338753184","https://openalex.org/W2404874347","https://openalex.org/W2577784528","https://openalex.org/W2593814746","https://openalex.org/W2594407953","https://openalex.org/W2618574054","https://openalex.org/W2682189153","https://openalex.org/W2726515241","https://openalex.org/W2784163702","https://openalex.org/W2784874046","https://openalex.org/W2793731154","https://openalex.org/W2803187616","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2936774411","https://openalex.org/W2944141891","https://openalex.org/W2962898354","https://openalex.org/W2963697299","https://openalex.org/W2963772355","https://openalex.org/W2964159205","https://openalex.org/W2981873476","https://openalex.org/W2992232939","https://openalex.org/W3005680577","https://openalex.org/W3018378048","https://openalex.org/W3024869864","https://openalex.org/W3035429562","https://openalex.org/W3087124270","https://openalex.org/W3109225549","https://openalex.org/W3127781933","https://openalex.org/W3137249133","https://openalex.org/W3161606033","https://openalex.org/W3176579584","https://openalex.org/W3202801947","https://openalex.org/W3205635414","https://openalex.org/W4283032551","https://openalex.org/W4289792473","https://openalex.org/W4292692470","https://openalex.org/W4296068770","https://openalex.org/W4297808394","https://openalex.org/W4312402191","https://openalex.org/W4312904577","https://openalex.org/W4382053191","https://openalex.org/W4388579618","https://openalex.org/W4388878572","https://openalex.org/W4390873661","https://openalex.org/W4391021767","https://openalex.org/W6801362334","https://openalex.org/W7133187193"],"related_works":["https://openalex.org/W4404238744","https://openalex.org/W4382053191","https://openalex.org/W4391326347","https://openalex.org/W4385489013","https://openalex.org/W4388854325","https://openalex.org/W4312904577","https://openalex.org/W4411990369","https://openalex.org/W4402115996","https://openalex.org/W4296068770","https://openalex.org/W4401110697"],"abstract_inverted_index":{"While":[0],"clustering-driven":[1],"Pseudo-Labels":[2],"(PLs)":[3],"are":[4],"commonly":[5],"employed":[6],"to":[7,121,140,147],"optimize":[8],"Speaker":[9,18],"Embedding":[10],"(SE)":[11],"networks":[12],"and":[13,105,119],"facilitate":[14],"training":[15,27],"of":[16,24,32,45,49,58,68,74,93,96,103,111,154],"self-supervised":[17,26,59,76,150],"Verification":[19],"(SV)":[20],"systems,":[21],"the":[22,30,66,72,75,94,134],"efficacy":[23],"PL-based":[25],"hinges":[28],"on":[29,71],"accuracy":[31],"these":[33,69,97],"generated":[34],"labels.":[35],"In":[36,62],"this":[37],"paper,":[38],"we":[39,64],"perform":[40],"a":[41,46],"large-scale":[42],"comparative":[43,91],"study":[44],"wide":[47],"range":[48],"recent":[50],"metric":[51],"learning":[52],"loss":[53,98,112],"functions":[54,99,113],"for":[55],"better":[56],"generalization":[57],"SV":[60,77,125,151],"systems.":[61],"particular,":[63],"investigate":[65],"effect":[67],"losses":[70,131],"robustness":[73],"task":[78],"against":[79,116],"label":[80,117],"noise":[81,118],"using":[82,100,128],"various":[83],"real-life":[84],"clustering-based":[85],"PLs.":[86],"We":[87],"present":[88],"an":[89],"extensive":[90],"evaluation":[92],"performance":[95],"different":[101],"numbers":[102],"clusters":[104],"show":[106],"that":[107],"our":[108,129,142,155],"proposed":[109],"selection":[110],"is":[114],"effective":[115],"leads":[120],"considerable":[122],"improvements":[123],"in":[124],"performance.":[126,152],"Moreover,":[127],"selected":[130],"combined":[132],"with":[133],"adopted":[135],"CAMSAT":[136],"clustering":[137],"algorithm-based":[138],"PLs":[139],"train":[141],"SE":[143],"system":[144],"allows":[145],"us":[146],"achieve":[148],"state-of-the-art":[149],"Code":[153],"experiments":[156],"will":[157],"be":[158],"made":[159],"publicly":[160],"available.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2024-07-31T00:00:00"}