{"id":"https://openalex.org/W2805983503","doi":"https://doi.org/10.1109/taslp.2018.2844025","title":"An Adaptive Method for Cross-Recording Speaker Diarization","display_name":"An Adaptive Method for Cross-Recording Speaker Diarization","publication_year":2018,"publication_date":"2018-06-08","ids":{"openalex":"https://openalex.org/W2805983503","doi":"https://doi.org/10.1109/taslp.2018.2844025","mag":"2805983503"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2844025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2844025","pdf_url":null,"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":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012026156","display_name":"Ga\u00ebl Le Lan","orcid":"https://orcid.org/0000-0002-1493-5777"},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Gael Le Lan","raw_affiliation_strings":["Orange Labs, Lannion, France","Orange Labs - Orange Labs [Belfort] (All\u00e9e des Usines, BP 382, 90007 Belfort, France - France)"],"raw_orcid":"https://orcid.org/0000-0002-1493-5777","affiliations":[{"raw_affiliation_string":"Orange Labs, Lannion, France","institution_ids":["https://openalex.org/I19370010"]},{"raw_affiliation_string":"Orange Labs - Orange Labs [Belfort] (All\u00e9e des Usines, BP 382, 90007 Belfort, France - France)","institution_ids":["https://openalex.org/I19370010"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106430617","display_name":"Delphine Charlet","orcid":null},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Delphine Charlet","raw_affiliation_strings":["Orange Labs, Lannion, France","Orange Labs [Lannion] (Technopole Anticipa 2 avenue Pierre Marzin 22300 LANNION - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Orange Labs, Lannion, France","institution_ids":["https://openalex.org/I19370010"]},{"raw_affiliation_string":"Orange Labs [Lannion] (Technopole Anticipa 2 avenue Pierre Marzin 22300 LANNION - France)","institution_ids":["https://openalex.org/I19370010"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002979461","display_name":"Anthony Larcher","orcid":"https://orcid.org/0000-0003-4398-0224"},"institutions":[{"id":"https://openalex.org/I4210108471","display_name":"Le Mans Universit\u00e9","ror":"https://ror.org/01mtcc283","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108471"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Anthony Larcher","raw_affiliation_strings":["University of Le Mans, Le Mans, France","LIUM - Laboratoire d'Informatique de l'Universit\u00e9 du Mans (Avenue Laennec 72085 Le Mans cedex 9 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Le Mans, Le Mans, France","institution_ids":[]},{"raw_affiliation_string":"LIUM - Laboratoire d'Informatique de l'Universit\u00e9 du Mans (Avenue Laennec 72085 Le Mans cedex 9 - France)","institution_ids":["https://openalex.org/I4210108471"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075235121","display_name":"Sylvain Meignier","orcid":"https://orcid.org/0000-0001-7687-073X"},"institutions":[{"id":"https://openalex.org/I4210108471","display_name":"Le Mans Universit\u00e9","ror":"https://ror.org/01mtcc283","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108471"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sylvain Meignier","raw_affiliation_strings":["University of Le Mans, Le Mans, France","LIUM - Laboratoire d'Informatique de l'Universit\u00e9 du Mans (Avenue Laennec 72085 Le Mans cedex 9 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Le Mans, Le Mans, France","institution_ids":[]},{"raw_affiliation_string":"LIUM - Laboratoire d'Informatique de l'Universit\u00e9 du Mans (Avenue Laennec 72085 Le Mans cedex 9 - France)","institution_ids":["https://openalex.org/I4210108471"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2495,"currency":"USD","value_usd":2495},"apc_paid":null,"fwci":0.403,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.73622123,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":"26","issue":"10","first_page":"1821","last_page":"1832"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991000294685364,"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":0.8134968280792236},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7266389727592468},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6406716108322144},{"id":"https://openalex.org/keywords/compensation","display_name":"Compensation (psychology)","score":0.6018904447555542},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5856654644012451},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5080366134643555},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42237550020217896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38042399287223816},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3545965552330017},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.07582089304924011}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8134968280792236},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7266389727592468},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6406716108322144},{"id":"https://openalex.org/C2780023022","wikidata":"https://www.wikidata.org/wiki/Q1338171","display_name":"Compensation (psychology)","level":2,"score":0.6018904447555542},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5856654644012451},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5080366134643555},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42237550020217896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38042399287223816},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3545965552330017},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.07582089304924011},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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":2,"locations":[{"id":"doi:10.1109/taslp.2018.2844025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2844025","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-01818495v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01818495","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech and Language Processing, 2018, 14, pp.1-12. ⟨10.1109/TASLP.2018.2844025⟩","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W37845981","https://openalex.org/W76945434","https://openalex.org/W83866820","https://openalex.org/W163811496","https://openalex.org/W174669002","https://openalex.org/W205800972","https://openalex.org/W1221962394","https://openalex.org/W1480629789","https://openalex.org/W1482605500","https://openalex.org/W1484181928","https://openalex.org/W1504805125","https://openalex.org/W1670780163","https://openalex.org/W1999033484","https://openalex.org/W2011760672","https://openalex.org/W2038101708","https://openalex.org/W2041823554","https://openalex.org/W2046015436","https://openalex.org/W2052495386","https://openalex.org/W2067301010","https://openalex.org/W2072632448","https://openalex.org/W2073017590","https://openalex.org/W2102453655","https://openalex.org/W2110023316","https://openalex.org/W2121812409","https://openalex.org/W2141262306","https://openalex.org/W2142333570","https://openalex.org/W2150769028","https://openalex.org/W2151293655","https://openalex.org/W2151299225","https://openalex.org/W2166980079","https://openalex.org/W2168175751","https://openalex.org/W2181594395","https://openalex.org/W2251309269","https://openalex.org/W2289985966","https://openalex.org/W2360384684","https://openalex.org/W2395750323","https://openalex.org/W2396559392","https://openalex.org/W2397116154","https://openalex.org/W2397622291","https://openalex.org/W2400927397","https://openalex.org/W2403536560","https://openalex.org/W2404175974","https://openalex.org/W2405954614","https://openalex.org/W2406312423","https://openalex.org/W2406500670","https://openalex.org/W2407024733","https://openalex.org/W2463927909","https://openalex.org/W2513973755","https://openalex.org/W2514794854","https://openalex.org/W2624257360","https://openalex.org/W2782964974","https://openalex.org/W3104490327","https://openalex.org/W6601517864","https://openalex.org/W6603105437","https://openalex.org/W6607140380","https://openalex.org/W6628802092","https://openalex.org/W6628911050","https://openalex.org/W6682143266","https://openalex.org/W6691378126","https://openalex.org/W6712346771","https://openalex.org/W6712379007","https://openalex.org/W6713727690","https://openalex.org/W6713752199","https://openalex.org/W6982185968","https://openalex.org/W7034119735"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W1521049138","https://openalex.org/W2938358845"],"abstract_inverted_index":{"Nowadays,":[0],"state-of-the-art":[1,103],"speaker":[2],"diarization":[3,104],"systems":[4,38],"heavily":[5],"rely":[6],"on":[7,23,109,125],"between-recording":[8,75],"variability":[9,76,94],"compensation":[10],"methods":[11],"to":[12,78],"accurately":[13],"process":[14],"large":[15],"collections":[16,54],"of":[17,36,52,57,93,115,137,151],"recordings.":[18,139],"Variability":[19],"estimation":[20],"is":[21,39,135],"performed":[22],"consequent":[24],"training":[25,44,133],"datasets,":[26],"which":[27],"must":[28],"be":[29],"labeled":[30],"by":[31],"speaker.":[32],"One":[33],"major":[34],"problem":[35],"such":[37],"the":[40,53,80,113,116,131,143,148],"acoustic":[41,62],"mismatch":[42,81,121],"between":[43],"and":[45,105],"target":[46],"data":[47,114],"that":[48,142],"degrades":[49],"performances.":[50],"Most":[51],"contain":[55],"lots":[56],"speakers":[58,71],"speaking":[59],"in":[60,100,120,153],"various":[61],"conditions.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67],"investigate":[68],"how":[69],"unlabeled":[70],"can":[72],"help":[73],"improve":[74],"estimation,":[77],"overcome":[79],"issue.":[82],"We":[83],"propose":[84],"a":[85,102],"scalable":[86],"unsupervised":[87],"adaptation":[88,145],"framework":[89,98,146],"for":[90,155],"two":[91,126],"types":[92],"compensation.":[95],"The":[96],"proposed":[97,144],"consists":[99],"adapting":[101],"linking":[106],"system,":[107],"trained":[108],"out-of-domain":[110],"data,":[111],"using":[112],"collection":[117,157],"itself.":[118],"Experiments":[119],"condition":[122],"are":[123],"run":[124],"French":[127],"Television":[128],"shows,":[129],"while":[130],"initial":[132],"dataset":[134],"composed":[136],"Radio":[138],"Results":[140],"indicate":[141],"reduces":[147],"cross-recording":[149],"DER":[150],"13%":[152],"average":[154],"variable":[156],"sizes.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}