{"id":"https://openalex.org/W4319862473","doi":"https://doi.org/10.1109/slt54892.2023.10022470","title":"A Comprehensive Study on Self-Supervised Distillation for Speaker Representation Learning","display_name":"A Comprehensive Study on Self-Supervised Distillation for Speaker Representation Learning","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862473","doi":"https://doi.org/10.1109/slt54892.2023.10022470"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022470","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022470","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/A5101416769","display_name":"Zhengyang Chen","orcid":"https://orcid.org/0000-0003-1293-8146"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"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"]},{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA","CN","US"],"is_corresponding":false,"raw_author_name":"Zhengyang Chen","raw_affiliation_strings":["AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab,Department of Computer Science and Engineering","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, X-LANCE Lab, AI Institute, Shanghai Jiao Tong University","Microsoft Cognitive Services Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I4210164862"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, X-LANCE Lab, AI Institute, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Microsoft Cognitive Services Research, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342006","display_name":"Yao Qian","orcid":"https://orcid.org/0000-0003-1855-9630"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Yao Qian","raw_affiliation_strings":["AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab,Department of Computer Science and Engineering","Microsoft Cognitive Services Research,USA","Microsoft Cognitive Services Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I4210164862"]},{"raw_affiliation_string":"Microsoft Cognitive Services Research,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Cognitive Services Research, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","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"]},{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA","CN"],"is_corresponding":false,"raw_author_name":"Bing Han","raw_affiliation_strings":["AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab,Department of Computer Science and Engineering","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, X-LANCE Lab, AI Institute, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I4210164862"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, X-LANCE Lab, AI Institute, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"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"]},{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA","CN","US"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab,Department of Computer Science and Engineering","Microsoft Cognitive Services Research,USA","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, X-LANCE Lab, AI Institute, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I4210164862"]},{"raw_affiliation_string":"Microsoft Cognitive Services Research,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, X-LANCE Lab, AI Institute, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089195158","display_name":"Michael Zeng","orcid":"https://orcid.org/0000-0001-5302-5883"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Zeng","raw_affiliation_strings":["Microsoft Cognitive Services Research,USA","Microsoft Cognitive Services Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Cognitive Services Research,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Cognitive Services Research, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"599","last_page":"604"},"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":0.9994999766349792,"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":0.9993000030517578,"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":0.7236424088478088},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6397367119789124},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5580981373786926},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5460054278373718},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5186628103256226},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5040077567100525},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4998586177825928},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4726509153842926},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4236522316932678},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37071138620376587}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7236424088478088},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6397367119789124},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5580981373786926},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5460054278373718},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5186628103256226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5040077567100525},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4998586177825928},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4726509153842926},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4236522316932678},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37071138620376587},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10022470","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022470","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1006777433","https://openalex.org/W2082257952","https://openalex.org/W2219249508","https://openalex.org/W2284050935","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2962788625","https://openalex.org/W2969985801","https://openalex.org/W2972705840","https://openalex.org/W2973190269","https://openalex.org/W3010925296","https://openalex.org/W3024869864","https://openalex.org/W3035060554","https://openalex.org/W3035524453","https://openalex.org/W3044308976","https://openalex.org/W3094325190","https://openalex.org/W3159481202","https://openalex.org/W3160397447","https://openalex.org/W3161606033","https://openalex.org/W3198698812","https://openalex.org/W3205635414","https://openalex.org/W3206189675","https://openalex.org/W4200633018","https://openalex.org/W4283458492","https://openalex.org/W4287635082","https://openalex.org/W4288091954","https://openalex.org/W4297841773","https://openalex.org/W6688816777","https://openalex.org/W6695676441","https://openalex.org/W6754496211","https://openalex.org/W6769178842","https://openalex.org/W6770717842","https://openalex.org/W6779326418","https://openalex.org/W6781368565","https://openalex.org/W6784256521","https://openalex.org/W6784330115","https://openalex.org/W6801723603","https://openalex.org/W6802476440","https://openalex.org/W6839093550"],"related_works":["https://openalex.org/W4255044973","https://openalex.org/W2890936991","https://openalex.org/W2499802997","https://openalex.org/W2112059504","https://openalex.org/W2727729836","https://openalex.org/W1960256358","https://openalex.org/W2548037963","https://openalex.org/W2464377622","https://openalex.org/W2394963835","https://openalex.org/W2146197305"],"abstract_inverted_index":{"In":[0,60],"real":[1],"application":[2],"scenarios,":[3],"it":[4],"is":[5],"often":[6],"challenging":[7],"to":[8,21,38,94],"obtain":[9],"a":[10,32,65,95,107],"large":[11],"amount":[12],"of":[13,82,90],"labeled":[14],"data":[15,77],"for":[16,127],"speaker":[17,22,71,92,113,136],"representation":[18,72,93],"learning":[19,26],"due":[20],"privacy":[23],"concerns.":[24],"Self-supervised":[25],"with":[27,42],"no":[28],"labels":[29,137],"has":[30,86],"become":[31],"more":[33,35,58],"and":[34,55,124,131],"promising":[36],"way":[37],"solve":[39],"it.":[40],"Compared":[41],"contrastive":[43],"learning,":[44,73],"self-distilled":[45,69],"approaches":[46],"use":[47],"only":[48],"positive":[49],"samples":[50],"in":[51,138],"the":[52,88,91,139],"loss":[53],"function":[54],"thus":[56],"are":[57],"attractive.":[59],"this":[61],"paper,":[62],"we":[63],"present":[64],"comprehensive":[66],"study":[67],"on":[68,75,110],"self-supervised":[70],"especially":[74],"critical":[76],"augmentation.":[78],"Our":[79],"proposed":[80],"strategy":[81],"audio":[83],"perturbation":[84],"augmentation":[85],"pushed":[87],"performance":[89],"new":[96,108],"limit.":[97],"The":[98],"experimental":[99],"results":[100],"show":[101],"that":[102],"our":[103],"model":[104],"can":[105],"achieve":[106],"SoTA":[109],"Voxceleb":[111],"1":[112],"verification":[114],"evaluation":[115],"benchmark":[116],"(i.e.,":[117],"equal":[118],"error":[119],"rate":[120],"(EER)":[121],"2.505%,":[122],"2.473%,":[123],"4.791":[125],"%":[126],"trial":[128],"Vox1-O,":[129],"Vox1-E":[130],"Vox1-H,":[132],"respectively),":[133],"discarding":[134],"any":[135],"training":[140],"phase.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}