{"id":"https://openalex.org/W4200633018","doi":"https://doi.org/10.1109/icassp43922.2022.9747526","title":"Self-Supervised Speaker Verification with Simple Siamese Network and Self-Supervised Regularization","display_name":"Self-Supervised Speaker Verification with Simple Siamese Network and Self-Supervised Regularization","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4200633018","doi":"https://doi.org/10.1109/icassp43922.2022.9747526"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747526","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747526","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/A5005211900","display_name":"Mufan Sang","orcid":null},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mufan Sang","raw_affiliation_strings":["The University of Texas at Dallas,TX,USA","The University of Texas at Dallas, TX, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas,TX,USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"The University of Texas at Dallas, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101654854","display_name":"Haoqi Li","orcid":"https://orcid.org/0009-0007-5191-9999"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoqi Li","raw_affiliation_strings":["Amazon AWS AI,USA","Amazon AWS AI, USA"],"affiliations":[{"raw_affiliation_string":"Amazon AWS AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon AWS AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100453075","display_name":"Fang Liu","orcid":"https://orcid.org/0000-0002-5669-9354"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fang Liu","raw_affiliation_strings":["Amazon AWS AI,USA","Amazon AWS AI, USA"],"affiliations":[{"raw_affiliation_string":"Amazon AWS AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon AWS AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010148946","display_name":"Andrew O. Arnold","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew O. Arnold","raw_affiliation_strings":["Amazon AWS AI,USA","Amazon AWS AI, USA"],"affiliations":[{"raw_affiliation_string":"Amazon AWS AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon AWS AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029416441","display_name":"Li Wan","orcid":"https://orcid.org/0000-0002-1926-8758"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Wan","raw_affiliation_strings":["Amazon AWS AI,USA","Amazon AWS AI, USA"],"affiliations":[{"raw_affiliation_string":"Amazon AWS AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon AWS AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5005211900"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":2.9224,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.92489532,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6127","last_page":"6131"},"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":0.998199999332428,"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":0.9968000054359436,"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":0.7346452474594116},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.7049795389175415},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7042169570922852},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6346855163574219},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.5874947905540466},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5589202642440796},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.5489561557769775},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5376713275909424},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.47559818625450134},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3842449486255646},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33927884697914124},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3074883818626404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7346452474594116},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.7049795389175415},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7042169570922852},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6346855163574219},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.5874947905540466},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5589202642440796},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.5489561557769775},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5376713275909424},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.47559818625450134},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3842449486255646},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33927884697914124},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3074883818626404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747526","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747526","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":[{"id":"https://metadata.un.org/sdg/10","score":0.75,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2219249508","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2936774411","https://openalex.org/W2962788262","https://openalex.org/W2962788625","https://openalex.org/W2962898354","https://openalex.org/W2963371159","https://openalex.org/W2969985801","https://openalex.org/W3000000254","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/W3035060554","https://openalex.org/W3035524453","https://openalex.org/W3044308976","https://openalex.org/W3096730275","https://openalex.org/W3160397447","https://openalex.org/W3161606033","https://openalex.org/W3163829335","https://openalex.org/W3171007011","https://openalex.org/W6688816777","https://openalex.org/W6745415975","https://openalex.org/W6748257384","https://openalex.org/W6772379172","https://openalex.org/W6773803412","https://openalex.org/W6774314701","https://openalex.org/W6779230768","https://openalex.org/W6779326418","https://openalex.org/W6781368565"],"related_works":["https://openalex.org/W34092691","https://openalex.org/W4312414840","https://openalex.org/W2794908468","https://openalex.org/W2531570999","https://openalex.org/W2943467239","https://openalex.org/W1571801203","https://openalex.org/W4206276646","https://openalex.org/W101422005","https://openalex.org/W192740413","https://openalex.org/W2952937263"],"abstract_inverted_index":{"Training":[0],"speaker-discriminative":[1],"and":[2,13,27,79,102,143],"robust":[3],"speaker":[4,8,35,111],"verification":[5],"systems":[6],"without":[7,98],"labels":[9],"is":[10],"still":[11],"challenging":[12],"worthwhile":[14],"to":[15,32],"explore.":[16],"In":[17],"this":[18],"study,":[19],"we":[20],"propose":[21],"an":[22],"effective":[23,140],"self-supervised":[24,34,42,47,96,110,130,141],"learning":[25,43,97,113],"framework":[26],"a":[28,115,133],"novel":[29],"regularization":[30,48,142],"strategy":[31],"facilitate":[33],"representation":[36,112],"learning.":[37],"Different":[38],"from":[39],"contrastive":[40],"learning-based":[41],"methods,":[44],"the":[45,53,56,66,76,89,93,107,123,139],"proposed":[46,90,129],"(SSReg)":[49],"focuses":[50],"exclusively":[51],"on":[52,74,122],"similarity":[54],"between":[55],"latent":[57],"representations":[58],"of":[59,68,95,109],"positive":[60],"data":[61,71,86],"pairs.":[62],"We":[63],"also":[64],"explore":[65],"effectiveness":[67],"alternative":[69],"online":[70,85],"augmentation":[72,87],"strategies":[73],"both":[75],"time":[77],"domain":[78],"frequency":[80],"domain.":[81],"With":[82],"our":[83,128],"strong":[84],"strategy,":[88],"SSReg":[91],"shows":[92],"potential":[94],"using":[99],"negative":[100],"pairs":[101],"it":[103],"can":[104],"significantly":[105],"improve":[106],"performance":[108],"with":[114],"simple":[116],"Siamese":[117],"network":[118],"architecture.":[119],"Comprehensive":[120],"experiments":[121],"VoxCeleb":[124],"datasets":[125],"demonstrate":[126],"that":[127],"approach":[131],"obtains":[132],"23.4%":[134],"relative":[135],"improvement":[136],"by":[137],"adding":[138],"outperforms":[144],"other":[145],"previous":[146],"works.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":3}],"updated_date":"2026-04-04T06:10:10.580331","created_date":"2025-10-10T00:00:00"}