{"id":"https://openalex.org/W2038101708","doi":"https://doi.org/10.1109/tasl.2013.2264673","title":"Unsupervised Methods for Speaker Diarization: An Integrated and Iterative Approach","display_name":"Unsupervised Methods for Speaker Diarization: An Integrated and Iterative Approach","publication_year":2013,"publication_date":"2013-05-22","ids":{"openalex":"https://openalex.org/W2038101708","doi":"https://doi.org/10.1109/tasl.2013.2264673","mag":"2038101708"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2013.2264673","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2013.2264673","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 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/A5051278718","display_name":"Stephen Shum","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]},{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen H. Shum","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA","MIT Comput. Sci. & Artificial Intell. Lab., Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4405258931"]},{"raw_affiliation_string":"MIT Comput. Sci. & Artificial Intell. Lab., Cambridge, MA, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]},{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA","MIT Comput. Sci. & Artificial Intell. Lab., Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4405258931"]},{"raw_affiliation_string":"MIT Comput. Sci. & Artificial Intell. Lab., Cambridge, MA, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012784735","display_name":"R\u00e9da Dehak","orcid":"https://orcid.org/0000-0002-4078-7261"},"institutions":[{"id":"https://openalex.org/I4210138808","display_name":"\u00c9cole Pour l'Informatique et les Techniques Avanc\u00e9es","ror":"https://ror.org/04r5ddq29","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210138808"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Reda Dehak","raw_affiliation_strings":["Laboratoire de Recherche et de D\u00e9veloppement, IEPITA, Paris, France","Lab. de Rech. et de Dev. de l'EPITA, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire de Recherche et de D\u00e9veloppement, IEPITA, Paris, France","institution_ids":[]},{"raw_affiliation_string":"Lab. de Rech. et de Dev. de l'EPITA, Paris, France","institution_ids":["https://openalex.org/I4210138808"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]},{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James R. Glass","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA","MIT Comput. Sci. & Artificial Intell. Lab., Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4405258931"]},{"raw_affiliation_string":"MIT Comput. Sci. & Artificial Intell. Lab., Cambridge, MA, USA","institution_ids":["https://openalex.org/I1343180700"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.7091,"has_fulltext":false,"cited_by_count":191,"citation_normalized_percentile":{"value":0.98120362,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"21","issue":"10","first_page":"2015","last_page":"2028"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9955999851226807,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9921000003814697,"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":0.9033927917480469},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7730376720428467},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6968280076980591},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6131736636161804},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6024330258369446},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5615019798278809},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5342954993247986},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.532547652721405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5312478542327881},{"id":"https://openalex.org/keywords/bayesian-information-criterion","display_name":"Bayesian information criterion","score":0.4953712224960327},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4691191017627716}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9033927917480469},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7730376720428467},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6968280076980591},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6131736636161804},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6024330258369446},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5615019798278809},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5342954993247986},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.532547652721405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5312478542327881},{"id":"https://openalex.org/C168136583","wikidata":"https://www.wikidata.org/wiki/Q1988242","display_name":"Bayesian information criterion","level":2,"score":0.4953712224960327},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4691191017627716},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tasl.2013.2264673","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2013.2264673","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.647.308","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.647.308","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://groups.csail.mit.edu/sls//publications/2013/Shum_IEEE_Oct-2013.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6200000047683716,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W36432376","https://openalex.org/W48568691","https://openalex.org/W115846232","https://openalex.org/W1501972811","https://openalex.org/W1538006706","https://openalex.org/W1663973292","https://openalex.org/W2011760672","https://openalex.org/W2041823554","https://openalex.org/W2049633694","https://openalex.org/W2052269122","https://openalex.org/W2074394031","https://openalex.org/W2081074144","https://openalex.org/W2088234478","https://openalex.org/W2105767795","https://openalex.org/W2112582577","https://openalex.org/W2115130489","https://openalex.org/W2115599677","https://openalex.org/W2115979064","https://openalex.org/W2121415728","https://openalex.org/W2125642021","https://openalex.org/W2127498532","https://openalex.org/W2135537007","https://openalex.org/W2140807505","https://openalex.org/W2145001205","https://openalex.org/W2147520277","https://openalex.org/W2150769028","https://openalex.org/W2151101344","https://openalex.org/W2156255174","https://openalex.org/W2159591770","https://openalex.org/W2161710584","https://openalex.org/W2165874743","https://openalex.org/W2168905067","https://openalex.org/W2187089797","https://openalex.org/W2289985966","https://openalex.org/W2397622291","https://openalex.org/W2397634864","https://openalex.org/W2398928324","https://openalex.org/W2400584454","https://openalex.org/W2403456716","https://openalex.org/W2403589179","https://openalex.org/W2610299321","https://openalex.org/W2963774573","https://openalex.org/W2979473749","https://openalex.org/W3097609957","https://openalex.org/W3104490327","https://openalex.org/W3155171291","https://openalex.org/W4212863985","https://openalex.org/W6601947329","https://openalex.org/W6604730075","https://openalex.org/W6630066523","https://openalex.org/W6675884203","https://openalex.org/W6681846537","https://openalex.org/W6684578312","https://openalex.org/W6684844159","https://openalex.org/W6712325649","https://openalex.org/W6712379007","https://openalex.org/W6712796495","https://openalex.org/W6713967443"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2119836628","https://openalex.org/W2356325859","https://openalex.org/W1197719229","https://openalex.org/W2381158726","https://openalex.org/W2552734076","https://openalex.org/W2162158162","https://openalex.org/W1992796048","https://openalex.org/W3184936773","https://openalex.org/W2166980079"],"abstract_inverted_index":{"In":[0,28,68],"speaker":[1,7,48,66,94,139],"diarization,":[2],"standard":[3],"approaches":[4],"typically":[5],"perform":[6],"clustering":[8,35,95,129],"on":[9,164],"some":[10],"initial":[11],"segmentation":[12,52,143],"before":[13],"refining":[14],"the":[15,74,134,165],"segment":[16],"boundaries":[17,53,144],"in":[18,43,126,145,188],"a":[19,24,80,90,98,160,176],"re-segmentation":[20,40,131],"step":[21],"to":[22,70,93,104,118,136,157,180,184],"obtain":[23],"final":[25],"diarization":[26,181],"hypothesis.":[27],"this":[29],"paper,":[30],"we":[31,57,88],"integrate":[32],"an":[33,38,121,146],"improved":[34],"method":[36],"with":[37,175],"existing":[39],"algorithm":[41],"and,":[42],"iterative":[44,122],"fashion,":[45],"optimize":[46],"both":[47,138,189],"cluster":[49,140],"assignments":[50,141],"and":[51,130,142,182,191],"jointly.":[54],"For":[55],"clustering,":[56],"extend":[58],"our":[59,173],"previous":[60],"research":[61],"using":[62],"factor":[63,77],"analysis":[64,78,107],"for":[65,82],"modeling.":[67],"continuing":[69],"take":[71],"advantage":[72],"of":[73,76,159],"effectiveness":[75],"as":[79],"front-end":[81],"extracting":[83],"speaker-specific":[84],"features":[85],"(i.e.,":[86],"i-vectors),":[87],"develop":[89],"probabilistic":[91],"approach":[92,179],"by":[96],"applying":[97],"Bayesian":[99,177],"Gaussian":[100],"Mixture":[101],"Model":[102],"(GMM)":[103],"principal":[105],"component":[106],"(PCA)-processed":[108],"i-vectors.":[109],"We":[110,170],"then":[111],"utilize":[112],"information":[113],"at":[114,120],"different":[115],"temporal":[116],"resolutions":[117],"arrive":[119],"optimization":[123],"scheme":[124],"that,":[125],"alternating":[127],"between":[128],"steps,":[132],"demonstrates":[133],"ability":[135],"improve":[137],"unsupervised":[147],"manner.":[148],"Our":[149],"proposed":[150],"methods":[151],"attain":[152],"results":[153],"that":[154],"are":[155],"comparable":[156],"those":[158],"state-of-the-art":[161],"benchmark":[162],"set":[163],"multi-speaker":[166],"CallHome":[167],"telephone":[168],"corpus.":[169],"further":[171],"compare":[172],"system":[174],"nonparametric":[178],"attempt":[183],"reconcile":[185],"their":[186],"differences":[187],"methodology":[190],"performance.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":27},{"year":2019,"cited_by_count":24},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T08:27:34.040176","created_date":"2025-10-10T00:00:00"}