{"id":"https://openalex.org/W4366548962","doi":"https://doi.org/10.1109/taslp.2023.3268568","title":"Self-Supervised Training of Speaker Encoder With Multi-Modal Diverse Positive Pairs","display_name":"Self-Supervised Training of Speaker Encoder With Multi-Modal Diverse Positive Pairs","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4366548962","doi":"https://doi.org/10.1109/taslp.2023.3268568"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3268568","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3268568","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10106039.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/ielx7/6570655/6633080/10106039.pdf","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":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"affiliations":[{"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/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I168639165","display_name":"Singapore Institute of Technology","ror":"https://ror.org/01v2c2791","country_code":"SG","type":"education","lineage":["https://openalex.org/I168639165"]},{"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"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kong Aik Lee","raw_affiliation_strings":["Singapore Institute of Technology, Singapore","Institute for Infocomm Research, A*STAR, Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore Institute of Technology, Singapore","institution_ids":["https://openalex.org/I168639165"]},{"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"],"affiliations":[{"raw_affiliation_string":"Fortemedia, 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"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ville Hautam\u00e4ki","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"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"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China","Kriston AI, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I4210099586"]},{"raw_affiliation_string":"Kriston AI, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"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":1.8929,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88231265,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"1706","last_page":"1719"},"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":0.9988999962806702,"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":0.738669753074646},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6552845239639282},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5761638283729553},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5756664872169495},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5750474333763123},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5355242490768433},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5298240780830383},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5068021416664124},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4896900951862335},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.477123498916626},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4496026635169983}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.738669753074646},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6552845239639282},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5761638283729553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5756664872169495},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5750474333763123},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5355242490768433},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5298240780830383},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5068021416664124},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4896900951862335},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.477123498916626},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4496026635169983},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3268568","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3268568","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10106039.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.2023.3268568","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3268568","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10106039.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":[{"display_name":"No poverty","id":"https://metadata.un.org/sdg/1","score":0.5600000023841858}],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2799040894","display_name":null,"funder_award_id":"62271432","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2981938667","display_name":null,"funder_award_id":"Shenzhen","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3085993365","display_name":null,"funder_award_id":"(Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3616239415","display_name":null,"funder_award_id":"A18A2b0046","funder_id":"https://openalex.org/F4320320696","funder_display_name":"Agency for Science, Technology and Research"},{"id":"https://openalex.org/G4020255992","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5088964179","display_name":null,"funder_award_id":"T00120220002","funder_id":"https://openalex.org/F4320331102","funder_display_name":"Shenzhen Research Institute of Big Data"},{"id":"https://openalex.org/G5249178904","display_name":null,"funder_award_id":"Grant No. 6","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5921878779","display_name":null,"funder_award_id":"18A2b0046","funder_id":"https://openalex.org/F4320320696","funder_display_name":"Agency for Science, Technology and Research"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G62282921","display_name":null,"funder_award_id":"Grant No. 62271432","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G766701999","display_name":null,"funder_award_id":"20220002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320320696","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320331102","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89"},{"id":"https://openalex.org/F4320333998","display_name":"Shenzhen Research Institute, City University of Hong Kong","ror":"https://ror.org/00xc0ma20"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4366548962.pdf","grobid_xml":"https://content.openalex.org/works/W4366548962.grobid-xml"},"referenced_works_count":69,"referenced_works":["https://openalex.org/W2048679005","https://openalex.org/W2121812409","https://openalex.org/W2150593711","https://openalex.org/W2154278880","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2296073425","https://openalex.org/W2516764878","https://openalex.org/W2594690981","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2747165665","https://openalex.org/W2752782242","https://openalex.org/W2808631503","https://openalex.org/W2890952074","https://openalex.org/W2890964092","https://openalex.org/W2896457183","https://openalex.org/W2921475306","https://openalex.org/W2928165649","https://openalex.org/W2969985801","https://openalex.org/W2973049979","https://openalex.org/W2973084242","https://openalex.org/W2998845736","https://openalex.org/W3011193554","https://openalex.org/W3013020904","https://openalex.org/W3015734344","https://openalex.org/W3016361963","https://openalex.org/W3023351797","https://openalex.org/W3024869864","https://openalex.org/W3025260599","https://openalex.org/W3026006730","https://openalex.org/W3035524453","https://openalex.org/W3035682985","https://openalex.org/W3103434036","https://openalex.org/W3110446398","https://openalex.org/W3126757411","https://openalex.org/W3137249133","https://openalex.org/W3141035251","https://openalex.org/W3158714121","https://openalex.org/W3159481202","https://openalex.org/W3160397447","https://openalex.org/W3161606033","https://openalex.org/W3163187953","https://openalex.org/W3163527109","https://openalex.org/W3196906655","https://openalex.org/W3205635414","https://openalex.org/W3206008172","https://openalex.org/W3209059054","https://openalex.org/W3213212519","https://openalex.org/W4200633018","https://openalex.org/W4220739185","https://openalex.org/W4221167533","https://openalex.org/W4283078310","https://openalex.org/W4286981691","https://openalex.org/W4287635082","https://openalex.org/W4290712827","https://openalex.org/W6631190155","https://openalex.org/W6688816777","https://openalex.org/W6762913911","https://openalex.org/W6773005947","https://openalex.org/W6778883912","https://openalex.org/W6779230768","https://openalex.org/W6781368565","https://openalex.org/W6784245331","https://openalex.org/W6784330115","https://openalex.org/W6784400926","https://openalex.org/W6784660784","https://openalex.org/W6804082488","https://openalex.org/W6809668307"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W4406496871","https://openalex.org/W1521049138","https://openalex.org/W2023466863"],"abstract_inverted_index":{"We":[0,132,211],"study":[1],"a":[2,26,32,41,72,83,100,196],"novel":[3,106,187],"neural":[4,235],"speaker":[5,12,20,29,52,130,135,143,225],"encoder":[6,21,53,136],"and":[7,63,113,145,155,163,169,221,237],"its":[8],"training":[9],"strategies":[10,239],"for":[11,122],"recognition":[13],"without":[14,141],"using":[15],"any":[16,142],"identity":[17],"labels.":[18],"The":[19],"is":[22,40,67,227],"trained":[23],"to":[24],"extract":[25],"fixed":[27],"dimensional":[28],"embedding":[30],"from":[31,77],"spoken":[33],"utterance":[34],"of":[35,50,61,75,129,152,166,184],"variable":[36],"length.":[37],"Contrastive":[38],"learning":[39,44,49,103,174,193,209,216],"typical":[42],"self-supervised":[43,192,215],"technique.":[45],"However,":[46],"the":[47,51,58,78,92,127,134,138,158,172,180,190,200,207,219,233],"contrastive":[48,102,123],"depends":[54],"very":[55],"much":[56],"on":[57,137,179,218],"sampling":[59,107,238],"strategy":[60,175],"positive":[62,73,88,119],"negative":[64],"pairs.":[65],"It":[66],"common":[68],"that":[69,232],"we":[70,98,116],"sample":[71],"pair":[74],"segments":[76],"same":[79,201],"utterance.":[80],"Unfortunately,":[81],"such":[82],"strategy,":[84,162],"denoted":[85],"as":[86],"poor-man's":[87],"pairs":[89,120],"(PPP),":[90],"lacks":[91],"necessary":[93],"diversity.":[94],"In":[95],"this":[96],"work,":[97],"propose":[99],"multi-modal":[101],"technique":[104,217],"with":[105,176,206],"strategies.":[108],"By":[109],"cross-referencing":[110],"between":[111],"speech":[112],"face":[114],"data,":[115],"find":[117],"diverse":[118],"(DPP)":[121],"learning,":[124],"thus":[125],"improving":[126],"robustness":[128],"encoder.":[131],"train":[133],"VoxCeleb2":[139],"dataset":[140],"labels,":[144,178],"achieve":[146],"an":[147,164],"equal":[148],"error":[149],"rate":[150],"(EER)":[151],"2.89%,":[153],"3.17%":[154],"6.27%":[156],"under":[157,171],"proposed":[159,234],"progressive":[160],"clustering":[161],"EER":[165],"1.44%,":[167],"1.77%":[168],"3.27%":[170],"two-stage":[173],"pseudo":[177],"three":[181],"test":[182],"sets":[183],"VoxCeleb1.":[185],"This":[186],"solution":[188],"outperforms":[189],"state-of-the-art":[191],"methods":[194],"by":[195],"large":[197],"margin,":[198],"at":[199],"time,":[202],"achieves":[203],"comparable":[204],"results":[205],"supervised":[208],"counterpart.":[210],"also":[212],"evaluate":[213],"our":[214],"LRS2":[220],"LRW":[222],"datasets,":[223],"where":[224],"information":[226],"unavailable.":[228],"All":[229],"experiments":[230],"suggest":[231],"architecture":[236],"are":[240],"robust":[241],"across":[242],"datasets.":[243]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":3}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}