{"id":"https://openalex.org/W1966142845","doi":"https://doi.org/10.1109/tasl.2011.2161079","title":"Initialization of Iterative-Based Speaker Diarization Systems for Telephone Conversations","display_name":"Initialization of Iterative-Based Speaker Diarization Systems for Telephone Conversations","publication_year":2012,"publication_date":"2012-01-31","ids":{"openalex":"https://openalex.org/W1966142845","doi":"https://doi.org/10.1109/tasl.2011.2161079","mag":"1966142845"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2011.2161079","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2011.2161079","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/A5110494410","display_name":"Oshry Ben-Harush","orcid":null},"institutions":[{"id":"https://openalex.org/I124227911","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982","country_code":"IL","type":"education","lineage":["https://openalex.org/I124227911"]},{"id":"https://openalex.org/I3129975082","display_name":"Sami Shamoon College of Engineering","ror":"https://ror.org/011aa4g29","country_code":"IL","type":"education","lineage":["https://openalex.org/I3129975082"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Oshry Ben-Harush","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Ben-Gurion University of the Negev, Beersheva, Israel","Department of Electrical and Computer Engineering, Sami Shamoon College of Engineering, Beersheva, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Ben-Gurion University of the Negev, Beersheva, Israel","institution_ids":["https://openalex.org/I124227911"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Sami Shamoon College of Engineering, Beersheva, Israel","institution_ids":["https://openalex.org/I3129975082"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110106388","display_name":"Ortal Ben-Harush","orcid":null},"institutions":[{"id":"https://openalex.org/I124227911","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982","country_code":"IL","type":"education","lineage":["https://openalex.org/I124227911"]},{"id":"https://openalex.org/I3129975082","display_name":"Sami Shamoon College of Engineering","ror":"https://ror.org/011aa4g29","country_code":"IL","type":"education","lineage":["https://openalex.org/I3129975082"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ortal Ben-Harush","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Ben-Gurion University of the Negev, Beersheva, Israel","Department of Electrical and Computer Engineering, Sami Shamoon College of Engineering, Beersheva, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Ben-Gurion University of the Negev, Beersheva, Israel","institution_ids":["https://openalex.org/I124227911"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Sami Shamoon College of Engineering, Beersheva, Israel","institution_ids":["https://openalex.org/I3129975082"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002668439","display_name":"Itshak Lapidot","orcid":"https://orcid.org/0000-0003-1066-3441"},"institutions":[{"id":"https://openalex.org/I3129975082","display_name":"Sami Shamoon College of Engineering","ror":"https://ror.org/011aa4g29","country_code":"IL","type":"education","lineage":["https://openalex.org/I3129975082"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Itshak Lapidot","raw_affiliation_strings":["Department of Electrical and Electronics Engineering, Sami Shamoon College of Engineering, Beersheva, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronics Engineering, Sami Shamoon College of Engineering, Beersheva, Israel","institution_ids":["https://openalex.org/I3129975082"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014705705","display_name":"Hugo Guterman","orcid":"https://orcid.org/0000-0002-3803-9862"},"institutions":[{"id":"https://openalex.org/I3129975082","display_name":"Sami Shamoon College of Engineering","ror":"https://ror.org/011aa4g29","country_code":"IL","type":"education","lineage":["https://openalex.org/I3129975082"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Hugo Guterman","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Sami Shamoon College of Engineering, Beersheva, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Sami Shamoon College of Engineering, Beersheva, Israel","institution_ids":["https://openalex.org/I3129975082"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.2079,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.91801357,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"20","issue":"2","first_page":"414","last_page":"425"},"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.9333547949790955},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.8582592010498047},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7544811964035034},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6477372646331787},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6302398443222046},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.5778636932373047},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5252649188041687},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44574323296546936},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.42126813530921936},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3775794506072998},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3645628094673157},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3643447756767273},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13386395573616028},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09053957462310791},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.08197280764579773}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9333547949790955},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.8582592010498047},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7544811964035034},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6477372646331787},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6302398443222046},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.5778636932373047},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5252649188041687},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44574323296546936},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.42126813530921936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3775794506072998},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3645628094673157},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3643447756767273},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13386395573616028},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09053957462310791},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.08197280764579773},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2011.2161079","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2011.2161079","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W30751557","https://openalex.org/W71947379","https://openalex.org/W106548914","https://openalex.org/W1482605500","https://openalex.org/W1560013842","https://openalex.org/W1663973292","https://openalex.org/W1966990998","https://openalex.org/W1974795023","https://openalex.org/W1990517717","https://openalex.org/W2001936727","https://openalex.org/W2002729367","https://openalex.org/W2049633694","https://openalex.org/W2099088086","https://openalex.org/W2115599677","https://openalex.org/W2125838338","https://openalex.org/W2127218421","https://openalex.org/W2129498120","https://openalex.org/W2135636388","https://openalex.org/W2144125830","https://openalex.org/W2147147599","https://openalex.org/W2154142081","https://openalex.org/W2156255174","https://openalex.org/W2158353986","https://openalex.org/W2159856503","https://openalex.org/W2165880886","https://openalex.org/W2168227362","https://openalex.org/W4212863985","https://openalex.org/W6602894216","https://openalex.org/W6628911050","https://openalex.org/W6675002796","https://openalex.org/W6678914141","https://openalex.org/W6683244702","https://openalex.org/W6684452406"],"related_works":["https://openalex.org/W1955177963","https://openalex.org/W2125642021","https://openalex.org/W1995876893","https://openalex.org/W2099333848","https://openalex.org/W2157809457","https://openalex.org/W2105667909","https://openalex.org/W1972077812","https://openalex.org/W2139113236","https://openalex.org/W2094356263","https://openalex.org/W30751557"],"abstract_inverted_index":{"Speaker":[0,71],"diarization":[1,56,72,118,129,152,199,240,278],"systems":[2],"attempt":[3],"to":[4,12,39,121,142,226,261,270],"assign":[5],"temporal":[6],"segments":[7],"from":[8,164,183],"a":[9,67,104,207],"conversation":[10],"betweenRspeakers":[11],"an":[13,77,115],"appropriate":[14,87],"speakerr.":[15],"This":[16,90],"task":[17],"is":[18,25,34,51,81,169,176],"generally":[19,58],"performed":[20,75],"when":[21,224,246],"no":[22],"prior":[23],"information":[24],"given":[26,68],"regarding":[27],"the":[28,47,84,93,112,144,149,170,184,197,202,213,220,236,239,248,259,265,272],"speakers.":[29],"The":[30,55,126,151,173,190],"number":[31,48],"of":[32,49,60,66,86,95,103,114,178,210,238,277,283],"speakers":[33,50,145],"usually":[35],"unknown":[36],"and":[37,64,146,154,217,281],"needs":[38],"be":[40,74],"estimated.":[41],"However,":[42,245],"there":[43],"are":[44,157,233,256],"applications":[45],"where":[46],"known":[52],"in":[53,140,148,275],"advance.":[54],"process":[57,241],"consists":[59],"change":[61],"detection,":[62],"clustering":[63],"labeling":[65],"audio":[69],"stream.":[70],"can":[73],"using":[76,159,201,242,247,264],"iterative":[78],"approach":[79],"that":[80,194],"optimized":[82],"by":[83,195],"selection":[85],"initial":[88],"conditions.":[89],"study":[91],"examines":[92],"influence":[94],"several":[96],"common":[97],"initialization":[98,109,155,228,251,267],"algorithms":[99,156,205],"including":[100],"two":[101,122],"variants":[102],"recently":[105],"proposed,":[106],"K-means":[107,203,249],"based":[108,204,250],"algorithm":[110],"over":[111],"performance":[113],"iterative-based":[116],"speaker":[117,123,128,198],"system":[119,130,153,200,260],"applied":[120],"telephone":[124,161,180],"conversations.":[125],"suggested":[127],"employs":[131],"either":[132],"self":[133],"organizing":[134],"maps":[135],"or":[136],"Gaussian":[137],"mixture":[138],"models":[139],"order":[141],"model":[143],"non-speech":[147],"conversation.":[150],"tuned":[158],"108":[160],"conversations":[162,181],"taken":[163],"LDC":[165,214],"CallHome":[166],"corpus,":[167],"this":[168],"development":[171,215],"set.":[172],"evaluation":[174,222],"subset":[175,223],"composed":[177],"2048":[179],"extracted":[182],"NIST":[185,221],"2005":[186],"Rich":[187],"Transcription":[188],"corpus.":[189],"results":[191],"obtained":[192],"show":[193],"initializing":[196],"provide":[206],"relative":[208],"improvement":[209],"10.4%":[211],"for":[212,219,235,258],"set":[216],"12.2%":[218],"compared":[225],"random":[227,243],"after":[229],"12":[230],"iterations":[231,255],"which":[232],"required":[234,257],"convergence":[237],"initialization.":[244],"approach,":[252],"only":[253],"five":[254],"converge.":[262],"Thus,":[263],"new":[266],"allows":[268],"us":[269],"improve":[271],"performances":[273],"both":[274],"terms":[276],"error":[279],"rate":[280],"speed":[282],"convergence.":[284]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":5},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}