{"id":"https://openalex.org/W3205635414","doi":"https://doi.org/10.1109/icassp43922.2022.9747162","title":"Self-Supervised Speaker Recognition with Loss-Gated Learning","display_name":"Self-Supervised Speaker Recognition with Loss-Gated Learning","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3205635414","doi":"https://doi.org/10.1109/icassp43922.2022.9747162","mag":"3205635414"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747162","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"ICASSP 2022 - 2022 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/A5026034735","display_name":"Ruijie Tao","orcid":"https://orcid.org/0000-0003-0021-5661"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Ruijie Tao","raw_affiliation_strings":["National University of Singapore,Department of Electrical and Computer Engineering,Singapore","Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004287909","display_name":"Kong Aik Lee","orcid":"https://orcid.org/0000-0001-9133-3000"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kong Aik Lee","raw_affiliation_strings":["A*STAR,Institute for Infocomm Research,Singapore","Institute for Infocomm Research, A*STAR, Singapore"],"affiliations":[{"raw_affiliation_string":"A*STAR,Institute for Infocomm Research,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029637694","display_name":"Rohan Kumar Das","orcid":"https://orcid.org/0000-0002-1332-3357"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rohan Kumar Das","raw_affiliation_strings":["Fortemedia Singapore,Singapore","Fortemedia Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Fortemedia Singapore,Singapore","institution_ids":[]},{"raw_affiliation_string":"Fortemedia Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037259225","display_name":"Ville Hautam\u00e4ki","orcid":"https://orcid.org/0000-0002-5885-0003"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I4210107997","display_name":"Finland University","ror":"https://ror.org/014rks409","country_code":"FI","type":"education","lineage":["https://openalex.org/I4210107997"]},{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]}],"countries":["FI","SG"],"is_corresponding":false,"raw_author_name":"Ville Hautamaki","raw_affiliation_strings":["National University of Singapore,Department of Electrical and Computer Engineering,Singapore","Department of Electrical and Computer Engineering, National University of Singapore, Singapore","University of Eastern Finland, Finland"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"University of Eastern Finland, Finland","institution_ids":["https://openalex.org/I4210107997","https://openalex.org/I175532246"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["National University of Singapore,Department of Electrical and Computer Engineering,Singapore","The Chinese University of Hong Kong, Shenzhen, China","Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5026034735"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":5.8207,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":{"value":0.9704805,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6142","last_page":"6146"},"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":0.9990000128746033,"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":0.9980999827384949,"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":0.7968913912773132},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7843056321144104},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7553743124008179},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5834951996803284},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5490877032279968},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.533764123916626},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5286626815795898},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5248793959617615},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5048988461494446},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.46273526549339294},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.42090269923210144}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7968913912773132},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7843056321144104},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7553743124008179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5834951996803284},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5490877032279968},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.533764123916626},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5286626815795898},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5248793959617615},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5048988461494446},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.46273526549339294},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.42090269923210144},{"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/icassp43922.2022.9747162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747162","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2150593711","https://openalex.org/W2154278880","https://openalex.org/W2219249508","https://openalex.org/W2222512263","https://openalex.org/W2295590090","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2883725317","https://openalex.org/W2890964092","https://openalex.org/W2916104401","https://openalex.org/W2921475306","https://openalex.org/W2964121744","https://openalex.org/W2969985801","https://openalex.org/W2972705840","https://openalex.org/W2981873476","https://openalex.org/W2998845736","https://openalex.org/W2999514914","https://openalex.org/W3005680577","https://openalex.org/W3013020904","https://openalex.org/W3015734344","https://openalex.org/W3023351797","https://openalex.org/W3024869864","https://openalex.org/W3033783364","https://openalex.org/W3034978746","https://openalex.org/W3035524453","https://openalex.org/W3044308976","https://openalex.org/W3093674315","https://openalex.org/W3126089204","https://openalex.org/W3131146638","https://openalex.org/W3160397447","https://openalex.org/W3161606033","https://openalex.org/W3163187953","https://openalex.org/W3196649213","https://openalex.org/W3211358952","https://openalex.org/W4205654098","https://openalex.org/W4221154746","https://openalex.org/W4286981691","https://openalex.org/W4287388854","https://openalex.org/W4287635082","https://openalex.org/W6631190155","https://openalex.org/W6688816777","https://openalex.org/W6697535213","https://openalex.org/W6772905751","https://openalex.org/W6773803412","https://openalex.org/W6774314701","https://openalex.org/W6779230768","https://openalex.org/W6781368565","https://openalex.org/W6784330115","https://openalex.org/W6784400926","https://openalex.org/W6788329692","https://openalex.org/W6800698692"],"related_works":["https://openalex.org/W2499802997","https://openalex.org/W4296594783","https://openalex.org/W2342291550","https://openalex.org/W2914064142","https://openalex.org/W2093392830","https://openalex.org/W3202053206","https://openalex.org/W2143693287","https://openalex.org/W1995148513","https://openalex.org/W78370326","https://openalex.org/W3205635414"],"abstract_inverted_index":{"In":[0,34],"self-supervised":[1,104],"learning":[2,65],"for":[3],"speaker":[4,21,41,88,105],"recognition,":[5],"pseudo":[6,28],"labels":[7,29,51,72,116],"are":[8],"useful":[9],"as":[10],"the":[11,47,70,74,78,84,97,102,111,125],"supervision":[12],"signals.":[13],"It":[14],"is":[15],"a":[16,20,40,63,92],"known":[17],"fact":[18],"that":[19,39],"recognition":[22,42,89,106],"model":[23,46,90],"doesn\u2019t":[24],"always":[25],"benefit":[26],"from":[27],"due":[30],"to":[31,45,61],"their":[32],"unreliability.":[33],"this":[35],"work,":[36],"we":[37],"observe":[38],"network":[43,80],"tends":[44],"data":[48],"with":[49,55,107],"reliable":[50,71],"faster":[52],"than":[53],"those":[54],"unreliable":[56],"labels.":[57],"This":[58],"motivates":[59],"us":[60],"study":[62],"loss-gated":[64],"(LGL)":[66],"strategy,":[67],"which":[68],"extracts":[69],"through":[73],"fitting":[75],"ability":[76],"of":[77,122],"neural":[79],"during":[81],"training.":[82],"With":[83],"proposed":[85,103],"LGL,":[86],"our":[87],"obtains":[91],"46.3%":[93],"performance":[94],"gain":[95],"over":[96],"system":[98],"without":[99,114],"it.":[100],"Further,":[101],"LGL":[108],"trained":[109],"on":[110,124],"VoxCeleb2":[112],"dataset":[113],"any":[115],"achieves":[117],"an":[118],"equal":[119],"error":[120],"rate":[121],"1.66%":[123],"VoxCeleb1":[126],"original":[127],"test":[128],"set.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}