{"id":"https://openalex.org/W4226254439","doi":"https://doi.org/10.1109/taslp.2022.3169977","title":"When Speaker Recognition Meets Noisy Labels: Optimizations for Front-Ends and Back-Ends","display_name":"When Speaker Recognition Meets Noisy Labels: Optimizations for Front-Ends and Back-Ends","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4226254439","doi":"https://doi.org/10.1109/taslp.2022.3169977"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3169977","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3169977","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9657755/09763412.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/9657755/09763412.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103050255","display_name":"Lin Li","orcid":"https://orcid.org/0000-0002-5021-2648"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":["XMU Speech Lab and the School of Electronic Science and Engineering, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-5021-2648","affiliations":[{"raw_affiliation_string":"XMU Speech Lab and the School of Electronic Science and Engineering, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090944758","display_name":"Fuchuan Tong","orcid":"https://orcid.org/0000-0001-5123-1843"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuchuan Tong","raw_affiliation_strings":["XMU Speech Lab and the School of Electronic Science and Engineering, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0001-5123-1843","affiliations":[{"raw_affiliation_string":"XMU Speech Lab and the School of Electronic Science and Engineering, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011997254","display_name":"Qingyang Hong","orcid":"https://orcid.org/0000-0001-7380-8690"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyang Hong","raw_affiliation_strings":["XMU Speech Lab and the School of Informatics, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0001-7380-8690","affiliations":[{"raw_affiliation_string":"XMU Speech Lab and the School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":1.1809,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.8160144,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"30","issue":null,"first_page":"1586","last_page":"1599"},"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":0.9997000098228455,"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/speech-recognition","display_name":"Speech recognition","score":0.6209024786949158},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.567914605140686},{"id":"https://openalex.org/keywords/front","display_name":"Front (military)","score":0.4959352910518646},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.42460116744041443},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4089522361755371},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3310587406158447},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1762203872203827},{"id":"https://openalex.org/keywords/mechanical-engineering","display_name":"Mechanical engineering","score":0.05820390582084656}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6209024786949158},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.567914605140686},{"id":"https://openalex.org/C2777551076","wikidata":"https://www.wikidata.org/wiki/Q842332","display_name":"Front (military)","level":2,"score":0.4959352910518646},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.42460116744041443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4089522361755371},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3310587406158447},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1762203872203827},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.05820390582084656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2022.3169977","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3169977","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9657755/09763412.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2022.3169977","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3169977","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9657755/09763412.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1141457816","display_name":null,"funder_award_id":"20720210087","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2299475589","display_name":null,"funder_award_id":"62001405","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3698338998","display_name":null,"funder_award_id":"61876160","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"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4226254439.pdf","grobid_xml":"https://content.openalex.org/works/W4226254439.grobid-xml"},"referenced_works_count":64,"referenced_works":["https://openalex.org/W577640895","https://openalex.org/W1589137271","https://openalex.org/W2121056381","https://openalex.org/W2121812409","https://openalex.org/W2135148572","https://openalex.org/W2147147599","https://openalex.org/W2150769028","https://openalex.org/W2360384684","https://openalex.org/W2395750323","https://openalex.org/W2402146185","https://openalex.org/W2404617565","https://openalex.org/W2566079294","https://openalex.org/W2589177632","https://openalex.org/W2730167212","https://openalex.org/W2784163702","https://openalex.org/W2890964092","https://openalex.org/W2891244534","https://openalex.org/W2938358845","https://openalex.org/W2949811029","https://openalex.org/W2962898354","https://openalex.org/W2963446838","https://openalex.org/W2963509340","https://openalex.org/W2964155802","https://openalex.org/W2964274690","https://openalex.org/W2969985801","https://openalex.org/W2972405707","https://openalex.org/W2972712416","https://openalex.org/W2972986505","https://openalex.org/W2979302305","https://openalex.org/W2979593053","https://openalex.org/W2981087920","https://openalex.org/W2985817549","https://openalex.org/W2987269219","https://openalex.org/W3010925296","https://openalex.org/W3011185790","https://openalex.org/W3015488554","https://openalex.org/W3024869864","https://openalex.org/W3038083940","https://openalex.org/W3042609801","https://openalex.org/W3049278490","https://openalex.org/W3094813571","https://openalex.org/W3095130383","https://openalex.org/W3099631870","https://openalex.org/W3103152812","https://openalex.org/W3107727058","https://openalex.org/W3109225549","https://openalex.org/W3111759753","https://openalex.org/W3118826713","https://openalex.org/W3137249133","https://openalex.org/W3163421828","https://openalex.org/W3194763370","https://openalex.org/W3197627775","https://openalex.org/W3198483183","https://openalex.org/W3206287456","https://openalex.org/W3215704891","https://openalex.org/W6678280073","https://openalex.org/W6713727690","https://openalex.org/W6734376636","https://openalex.org/W6740005241","https://openalex.org/W6758930985","https://openalex.org/W6762161020","https://openalex.org/W6762903502","https://openalex.org/W6768848008","https://openalex.org/W6800175519"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W4313854686","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":{"A":[0],"typical":[1],"speaker":[2,15,48,63],"recognition":[3,49,64],"system":[4,130],"often":[5],"involves":[6],"two":[7,140],"modules:":[8],"a":[9,14,94,168],"feature":[10],"extractor":[11],"front-end":[12,53,88],"and":[13,54,89,100,127,158,180],"identification":[16],"back-end.":[17,90],"Despite":[18],"the":[19,29,35,52,80,87,109,117,128,144,159,172,176,193],"superior":[20],"performance":[21],"that":[22,189],"deep":[23],"neural":[24],"networks":[25],"have":[26],"achieved":[27],"for":[28,124],"front-end,":[30],"their":[31],"success":[32],"benefits":[33],"from":[34],"availability":[36],"of":[37,79,82,122,143,192,200],"large-scale,":[38],"correctly":[39],"labeled":[40],"datasets.":[41],"While":[42],"label":[43,59,83,106,135,201],"noise":[44,84,107],"is":[45,197],"unavoidable":[46],"in":[47,108],"datasets,":[50],"both":[51,86],"back-end":[55],"are":[56],"affected":[57],"by":[58,184],"noise,":[60],"which":[61],"degrades":[62],"performance.":[65],"In":[66],"this":[67],"paper,":[68],"we":[69,92,138,187],"first":[70],"conduct":[71],"comprehensive":[72],"experiments":[73],"to":[74,104,134,175],"help":[75],"improve":[76],"our":[77,113],"understanding":[78],"effects":[81],"on":[85,153],"Then,":[91],"propose":[93],"simple":[95],"yet":[96],"effective":[97],"training":[98],"paradigm":[99],"loss":[101],"correction":[102],"method":[103,115],"handle":[105],"front-end.":[110],"We":[111],"combine":[112],"proposed":[114,119],"with":[116],"recently":[118],"Bayesian":[120],"estimation":[121],"PLDA":[123],"noisy":[125,150,165],"labels,":[126],"whole":[129],"shows":[131],"strong":[132],"robustness":[133],"noise.":[136],"Furthermore,":[137],"show":[139],"practical":[141],"applications":[142],"improved":[145],"system:":[146],"one":[147],"application":[148,174],"corrects":[149],"labels":[151],"based":[152],"an":[154],"utterance\u2019s":[155],"chunk-level":[156],"predictions,":[157],"other":[160],"algorithmically":[161],"filters":[162],"out":[163],"high-confidence":[164],"samples":[166],"within":[167],"dataset.":[169],"By":[170],"applying":[171],"second":[173],"NIST":[177,194],"SRE04\u201310":[178,195],"dataset":[179,196],"verifying":[181],"filtered":[182],"utterances":[183],"human":[185],"validation,":[186],"identify":[188],"approximately":[190],"1%":[191],"made":[198],"up":[199],"errors.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}