{"id":"https://openalex.org/W4297841865","doi":"https://doi.org/10.21437/interspeech.2022-777","title":"Self-supervised Speaker Diarization","display_name":"Self-supervised Speaker Diarization","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841865","doi":"https://doi.org/10.21437/interspeech.2022-777"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-777","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-777","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5035675810","display_name":"Yehoshua Dissen","orcid":"https://orcid.org/0000-0002-9380-8169"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yehoshua Dissen","raw_affiliation_strings":["Department of Computer Science, Bar-Ilan University, Ramat-Gan, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Bar-Ilan University, Ramat-Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000406733","display_name":"Felix Kreuk","orcid":null},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Felix Kreuk","raw_affiliation_strings":["Department of Computer Science, Bar-Ilan University, Ramat-Gan, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Bar-Ilan University, Ramat-Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008847407","display_name":"Joseph Keshet","orcid":"https://orcid.org/0000-0003-2332-5783"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Joseph Keshet","raw_affiliation_strings":["Electrical and Computer Engineering, Technion-Israel Institute of Technology, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Technion-Israel Institute of Technology, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5008847407"],"corresponding_institution_ids":["https://openalex.org/I174306211"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4013","last_page":"4017"},"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/T11309","display_name":"Music and Audio Processing","score":0.995199978351593,"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/T10860","display_name":"Speech and Audio Processing","score":0.9947999715805054,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.829351544380188},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7096399068832397},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5758134722709656},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4862348139286041},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3816696107387543},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33220866322517395}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.829351544380188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7096399068832397},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5758134722709656},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4862348139286041},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3816696107387543},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33220866322517395}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-777","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-777","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1589137271","https://openalex.org/W2035890032","https://openalex.org/W2038101708","https://openalex.org/W2088234478","https://openalex.org/W2125642021","https://openalex.org/W2150769028","https://openalex.org/W2166637769","https://openalex.org/W2396834488","https://openalex.org/W2757910899","https://openalex.org/W2765122878","https://openalex.org/W2890964092","https://openalex.org/W2896538040","https://openalex.org/W2962788625","https://openalex.org/W2963263347","https://openalex.org/W2963745998","https://openalex.org/W2972949456","https://openalex.org/W3008357631","https://openalex.org/W3010196324","https://openalex.org/W3095212884","https://openalex.org/W3096656254","https://openalex.org/W3134652006","https://openalex.org/W3163019736","https://openalex.org/W4286695273","https://openalex.org/W4287164729"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W2144208207","https://openalex.org/W4389984014","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"Over":[0],"the":[1,26,60,81,106,128,157,175],"last":[2],"few":[3],"years,":[4],"deep":[5],"learning":[6],"has":[7],"grown":[8],"in":[9,93,174],"popularity":[10],"for":[11,57],"speaker":[12,31,58,67,85],"verification,":[13],"identification,":[14],"and":[15,43,137,177],"diarization.Inarguably,":[16],"a":[17,94,121,141],"significant":[18],"part":[19],"of":[20,29,40,80,99,105,127],"this":[21],"success":[22],"is":[23,112,178],"due":[24],"to":[25,47,103,115,118,139,148,160],"demonstrated":[27],"effectiveness":[28],"their":[30],"representations.These,":[32],"however,":[33],"are":[34,87,172],"heavily":[35],"dependent":[36],"on":[37,63,76,156],"large":[38],"amounts":[39],"annotated":[41,71],"data":[42],"can":[44],"be":[45,104],"sensitive":[46],"new":[48],"domains.This":[49],"study":[50,61],"proposes":[51],"an":[52,90],"entirely":[53],"unsupervised":[54,150,166],"deep-learning":[55],"model":[56,82,111,147],"diarization.Specifically,":[59],"focuses":[62],"generating":[64],"highquality":[65],"neural":[66],"representations":[68],"without":[69,83],"any":[70],"data,":[72],"as":[73,75,151,153],"well":[74,152],"estimating":[77],"secondary":[78],"hyperparameters":[79],"annotations.The":[84],"embeddings":[86],"represented":[88],"by":[89],"encoder":[91,110],"trained":[92,109],"self-supervised":[95],"fashion":[96],"using":[97,131],"pairs":[98],"adjacent":[100],"segments":[101,126],"assumed":[102],"same":[107,129],"speaker.The":[108],"then":[113],"used":[114],"self-generate":[116],"pseudo-labels":[117],"subsequently":[119],"train":[120],"similarity":[122],"score":[123],"between":[124],"different":[125],"call":[130],"probabilistic":[132],"linear":[133],"discriminant":[134],"analysis":[135],"(PLDA)":[136],"further":[138],"learn":[140],"clustering":[142],"stopping":[143],"threshold.We":[144],"compared":[145],"our":[146,163],"state-of-the-art":[149],"supervised":[154,184],"baselines":[155],"CallHome":[158],"benchmarks.According":[159],"empirical":[161],"results,":[162],"approach":[164],"outperforms":[165],"methods":[167],"when":[168],"only":[169,179],"two":[170],"speakers":[171],"present":[173],"call,":[176],"slightly":[180],"worse":[181],"than":[182],"recent":[183],"models.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}