{"id":"https://openalex.org/W4307357910","doi":"https://doi.org/10.1109/slt54892.2023.10023195","title":"Continual Self-Supervised Domain Adaptation for End-to-End Speaker Diarization","display_name":"Continual Self-Supervised Domain Adaptation for End-to-End Speaker Diarization","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4307357910","doi":"https://doi.org/10.1109/slt54892.2023.10023195"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023195","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":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-03824546/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017320570","display_name":"Juan Manuel Coria","orcid":"https://orcid.org/0000-0002-5035-147X"},"institutions":[{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Juan M. Coria","raw_affiliation_strings":["Université Paris-Saclay CNRS, LISN,Orsay,France"],"affiliations":[{"raw_affiliation_string":"Université Paris-Saclay CNRS, LISN,Orsay,France","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079257674","display_name":"Herv\u00e9 Bredin","orcid":"https://orcid.org/0000-0002-3739-925X"},"institutions":[{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I4210119061"]},{"id":"https://openalex.org/I134560555","display_name":"Universit\u00e9 Toulouse III - Paul Sabatier","ror":"https://ror.org/02v6kpv12","country_code":"FR","type":"education","lineage":["https://openalex.org/I134560555"]},{"id":"https://openalex.org/I3131550300","display_name":"Universit\u00e9 Toulouse-I-Capitole","ror":"https://ror.org/0443n9e75","country_code":"FR","type":"education","lineage":["https://openalex.org/I3131550300"]},{"id":"https://openalex.org/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]},{"id":"https://openalex.org/I4210152422","display_name":"Universit\u00e9 Toulouse - Jean Jaur\u00e8s","ror":"https://ror.org/04ezk3x31","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210152422"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Herve Bredin","raw_affiliation_strings":["IRIT, Université de Toulouse, CNRS,Toulouse,France"],"affiliations":[{"raw_affiliation_string":"IRIT, Université de Toulouse, CNRS,Toulouse,France","institution_ids":["https://openalex.org/I4210119061","https://openalex.org/I134560555","https://openalex.org/I3131550300","https://openalex.org/I4210160189","https://openalex.org/I4210152422","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000557257","display_name":"Sahar Ghannay","orcid":"https://orcid.org/0000-0002-7531-2522"},"institutions":[{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sahar Ghannay","raw_affiliation_strings":["Université Paris-Saclay CNRS, LISN,Orsay,France"],"affiliations":[{"raw_affiliation_string":"Université Paris-Saclay CNRS, LISN,Orsay,France","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001616788","display_name":"Sophie Rosset","orcid":"https://orcid.org/0000-0002-6865-4989"},"institutions":[{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sophie Rosset","raw_affiliation_strings":["Université Paris-Saclay CNRS, LISN,Orsay,France"],"affiliations":[{"raw_affiliation_string":"Université Paris-Saclay CNRS, LISN,Orsay,France","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I1294671590"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.412,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.558059,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":67,"max":78},"biblio":{"volume":null,"issue":null,"first_page":"626","last_page":"632"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998,"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":0.9998,"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/T11309","display_name":"Music and Audio Processing","score":0.9972,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9957,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.84897137},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.67459023},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain Adaptation","score":0.66124046},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.46731704},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4358532},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance Improvement","score":0.4295266}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.84897137},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8132194},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7130425},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.67459023},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.66563576},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.66124046},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6550884},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5748305},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.46731704},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.44398108},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4358532},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.4295266},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.41341564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35430697},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08503649},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.068752974},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023195","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":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://hal.science/hal-03824546","pdf_url":"https://hal.science/hal-03824546/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":["Centre National de la Recherche Scientifique"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://hal.science/hal-03824546/file/csda.pdf","pdf_url":"https://hal.science/hal-03824546/file/csda.pdf","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://hal.science/hal-03824546","pdf_url":"https://hal.science/hal-03824546/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":["Centre National de la Recherche Scientifique"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"display_name":"Quality education","id":"https://metadata.un.org/sdg/4","score":0.62}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":26,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2060277733","https://openalex.org/W2064675550","https://openalex.org/W2083751884","https://openalex.org/W2116522068","https://openalex.org/W2155653793","https://openalex.org/W2219249508","https://openalex.org/W2555915854","https://openalex.org/W2896457183","https://openalex.org/W2963559848","https://openalex.org/W2964052309","https://openalex.org/W2972949456","https://openalex.org/W2982593362","https://openalex.org/W3005680577","https://openalex.org/W3015522062","https://openalex.org/W3015783745","https://openalex.org/W3016011332","https://openalex.org/W3095212884","https://openalex.org/W3097816393","https://openalex.org/W3130320103","https://openalex.org/W3178462146","https://openalex.org/W3196595845","https://openalex.org/W3196781856","https://openalex.org/W3198482860","https://openalex.org/W3205181379","https://openalex.org/W4295883599"],"related_works":["https://openalex.org/W4247736853","https://openalex.org/W2696990509","https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W2149220986","https://openalex.org/W2125642021","https://openalex.org/W2023466863","https://openalex.org/W1999004162","https://openalex.org/W1521049138","https://openalex.org/W1493012537"],"abstract_inverted_index":{"In":[0,19],"conventional":[1],"domain":[2,16,30,122],"adaptation":[3,31,61],"for":[4,29,59],"speaker":[5,35],"diarization,":[6],"a":[7,24,43,64,68,103,107,119],"large":[8],"collection":[9],"of":[10,32,55,63,76,88,97],"annotated":[11],"conversations":[12],"from":[13,47,132],"the":[14,85,89,95],"target":[15,121],"is":[17],"required.":[18],"this":[20],"work,":[21],"we":[22],"propose":[23],"novel":[25],"continual":[26],"training":[27],"scheme":[28],"an":[33],"end-to-end":[34],"diarization":[36],"system,":[37],"which":[38],"processes":[39],"one":[40],"conversation":[41],"at":[42],"time":[44],"and":[45,93,118,129],"benefits":[46],"full":[48],"self-supervision":[49],"thanks":[50],"to":[51,67,102,126,130],"pseudo-labels.":[52],"The":[53],"qualities":[54],"our":[56,98],"method":[57],"allow":[58],"autonomous":[60],"(e.g.":[62],"voice":[65],"assistant":[66],"new":[69],"house-hold),":[70],"while":[71],"also":[72,113],"avoiding":[73],"permanent":[74],"storage":[75],"possibly":[77],"sensitive":[78],"user":[79],"conversations.":[80],"We":[81,112],"experiment":[82],"extensively":[83],"on":[84],"11":[86],"domains":[87],"DIHARD":[90],"III":[91],"corpus":[92],"show":[94],"effectiveness":[96],"approach":[99],"with":[100],"respect":[101],"pre-trained":[104],"base-line,":[105],"achieving":[106],"relative":[108],"17%":[109],"performance":[110],"improvement.":[111],"find":[114],"that":[115],"data":[116],"augmentation":[117],"well-defined":[120],"are":[123],"key":[124],"factors":[125],"avoid":[127],"divergence":[128],"benefit":[131],"transfer.":[133]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4307357910","counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-01-01T20:35:35.028063","created_date":"2022-10-31"}