{"id":"https://openalex.org/W2960868309","doi":"https://doi.org/10.1186/s13636-019-0154-z","title":"Latent class model with application to speaker diarization","display_name":"Latent class model with application to speaker diarization","publication_year":2019,"publication_date":"2019-07-09","ids":{"openalex":"https://openalex.org/W2960868309","doi":"https://doi.org/10.1186/s13636-019-0154-z","mag":"2960868309"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-019-0154-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-019-0154-z","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-019-0154-z","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-019-0154-z","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049944728","display_name":"Liang He","orcid":"https://orcid.org/0000-0003-4076-7479"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Liang He","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Zhongguancun Street, Beijing, 100084, China"],"raw_orcid":"https://orcid.org/0000-0003-4076-7479","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Zhongguancun Street, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059065171","display_name":"Xianhong Chen","orcid":"https://orcid.org/0000-0002-5001-0587"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianhong Chen","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Zhongguancun Street, Beijing, 100084, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Zhongguancun Street, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101801662","display_name":"Can Xu","orcid":"https://orcid.org/0000-0003-1365-4778"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Can Xu","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Zhongguancun Street, Beijing, 100084, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Zhongguancun Street, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330618","display_name":"Yi Liu","orcid":"https://orcid.org/0000-0003-1399-7420"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Liu","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Zhongguancun Street, Beijing, 100084, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Zhongguancun Street, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100409741","display_name":"Jia Liu","orcid":"https://orcid.org/0000-0003-0383-0934"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Liu","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Zhongguancun Street, Beijing, 100084, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Zhongguancun Street, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015797517","display_name":"Michael T. Johnson","orcid":"https://orcid.org/0000-0001-5424-4877"},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael T. Johnson","raw_affiliation_strings":["Electrical and Computer Engineering, University of Kentucky, 453E FPAT, Lexington, 40506-0046, KY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of Kentucky, 453E FPAT, Lexington, 40506-0046, KY, USA","institution_ids":["https://openalex.org/I143302722"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5049944728"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1635},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1635},"fwci":0.3191,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.69346963,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"2019","issue":"1","first_page":null,"last_page":null},"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/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":0.9983000159263611,"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":0.7999060153961182},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7799357771873474},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7715464234352112},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5979946851730347},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.5875653028488159},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.549201488494873},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5396080613136292},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.515903115272522},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5151063799858093},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5031070113182068},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.43030399084091187},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.2650589048862457}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7999060153961182},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7799357771873474},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7715464234352112},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5979946851730347},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.5875653028488159},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.549201488494873},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5396080613136292},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.515903115272522},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5151063799858093},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5031070113182068},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.43030399084091187},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2650589048862457},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/s13636-019-0154-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-019-0154-z","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-019-0154-z","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:uknowledge.uky.edu:ece_facpub-1033","is_oa":true,"landing_page_url":"https://uknowledge.uky.edu/ece_facpub/33","pdf_url":null,"source":{"id":"https://openalex.org/S4306402623","display_name":"UKnowledge (University of Kentucky)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I143302722","host_organization_name":"University of Kentucky","host_organization_lineage":["https://openalex.org/I143302722"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Electrical and Computer Engineering Faculty Publications","raw_type":"text"},{"id":"pmh:oai:doaj.org/article:a2d4e4f68bda48c8983e6c16ad161bbb","is_oa":false,"landing_page_url":"https://doaj.org/article/a2d4e4f68bda48c8983e6c16ad161bbb","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2019, Iss 1, Pp 1-19 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-019-0154-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-019-0154-z","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-019-0154-z","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6899999976158142}],"awards":[{"id":"https://openalex.org/G1479414115","display_name":null,"funder_award_id":"61403224","funder_id":"https://openalex.org/F4320335581","funder_display_name":"Young Scientists Fund"},{"id":"https://openalex.org/G4665116016","display_name":null,"funder_award_id":"61403224","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6174077271","display_name":null,"funder_award_id":"No. 61403224","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320332178","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416"},{"id":"https://openalex.org/F4320335581","display_name":"Young Scientists Fund","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2960868309.pdf","grobid_xml":"https://content.openalex.org/works/W2960868309.grobid-xml"},"referenced_works_count":66,"referenced_works":["https://openalex.org/W41021157","https://openalex.org/W106647055","https://openalex.org/W144883574","https://openalex.org/W1497939657","https://openalex.org/W1502693945","https://openalex.org/W1504503307","https://openalex.org/W1524333225","https://openalex.org/W1586180564","https://openalex.org/W1597208282","https://openalex.org/W1607302042","https://openalex.org/W1965819578","https://openalex.org/W1969290787","https://openalex.org/W2014158063","https://openalex.org/W2018419535","https://openalex.org/W2031823405","https://openalex.org/W2038101708","https://openalex.org/W2038162002","https://openalex.org/W2072632448","https://openalex.org/W2081074144","https://openalex.org/W2088173118","https://openalex.org/W2093499222","https://openalex.org/W2106793713","https://openalex.org/W2115130489","https://openalex.org/W2115599677","https://openalex.org/W2119968850","https://openalex.org/W2121812409","https://openalex.org/W2122364000","https://openalex.org/W2123075901","https://openalex.org/W2125234026","https://openalex.org/W2125642021","https://openalex.org/W2131562924","https://openalex.org/W2140046090","https://openalex.org/W2140807505","https://openalex.org/W2148613904","https://openalex.org/W2150769028","https://openalex.org/W2153842971","https://openalex.org/W2153918101","https://openalex.org/W2157005274","https://openalex.org/W2188703032","https://openalex.org/W2289985966","https://openalex.org/W2294814385","https://openalex.org/W2338994564","https://openalex.org/W2395750323","https://openalex.org/W2405137844","https://openalex.org/W2405802804","https://openalex.org/W2509864590","https://openalex.org/W2513973755","https://openalex.org/W2514325906","https://openalex.org/W2514794854","https://openalex.org/W2516047932","https://openalex.org/W2554987453","https://openalex.org/W2588638982","https://openalex.org/W2620757702","https://openalex.org/W2667475753","https://openalex.org/W2673722796","https://openalex.org/W2746241180","https://openalex.org/W2749214709","https://openalex.org/W2770992561","https://openalex.org/W2801213956","https://openalex.org/W2805869973","https://openalex.org/W2963702081","https://openalex.org/W3145829579","https://openalex.org/W4212792737","https://openalex.org/W4285719527","https://openalex.org/W4299594765","https://openalex.org/W4365806309"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W184241528","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162"],"abstract_inverted_index":{"In":[0,40,97],"this":[1,86],"paper,":[2],"we":[3],"apply":[4],"a":[5,50,55,80,123,176],"latent":[6],"class":[7],"model":[8,126],"(LCM)":[9],"to":[10,19,42,104,112,127,139,150,200],"the":[11,43,69,152,159,173,182,188,201,204,234,239],"task":[12],"of":[13,71,154,162,175,187,207],"speaker":[14,115,130,169],"diarization.":[15],"LCM":[16,53],"is":[17,47,66],"similar":[18],"Patrick":[20],"Kenny\u2019s":[21],"variational":[22],"Bayes":[23],"(VB)":[24],"method":[25],"in":[26,37,85,148],"that":[27,181,233],"it":[28],"uses":[29],"soft":[30,146],"information":[31,116],"and":[32,60,79,93,142,145,164,210,216,226],"avoids":[33],"premature":[34],"hard":[35,144],"decisions":[36],"its":[38,106],"iterations.":[39],"contrast":[41],"VB":[44,202],"method,":[45,203],"which":[46],"based":[48],"on":[49,158,220],"generative":[51,59],"model,":[52],"provides":[54],"framework":[56],"allowing":[57],"both":[58],"discriminative":[61,64,76],"models.":[62],"The":[63],"property":[65],"realized":[67],"through":[68],"use":[70],"i-vector":[72],"(Ivec),":[73],"probabilistic":[74],"linear":[75],"analysis":[77],"(PLDA),":[78],"support":[81],"vector":[82],"machine":[83],"(SVM)":[84],"work.":[87],"Systems":[88],"denoted":[89],"as":[90],"LCM-Ivec-PLDA,":[91,208],"LCM-Ivec-SVM,":[92,209],"LCM-Ivec-Hybrid":[94,211,236],"are":[95,102,213],"introduced.":[96],"addition,":[98],"three":[99],"further":[100],"improvements":[101,194,206],"applied":[103],"enhance":[105],"performance.":[107,242],"(1)":[108],"Adding":[109],"neighbor":[110],"windows":[111],"extract":[113],"more":[114],"for":[117],"each":[118],"short":[119],"segment.":[120],"(2)":[121],"Using":[122,134],"hidden":[124],"Markov":[125],"avoid":[128],"frequent":[129],"change":[131],"points.":[132],"(3)":[133],"an":[135],"agglomerative":[136],"hierarchical":[137],"cluster":[138],"do":[140],"initialization":[141],"present":[143],"priors,":[147],"order":[149],"overcome":[151],"problem":[153],"initial":[155],"sensitivity.":[156],"Experiments":[157,219],"National":[160],"Institute":[161],"Standards":[163],"Technology":[165],"Rich":[166],"Transcription":[167],"2009":[168],"diarization":[170,183],"database,":[171,223],"under":[172],"condition":[174],"single":[177],"distant":[178],"microphone,":[179],"show":[180,232],"error":[184],"rate":[185],"(DER)":[186],"proposed":[189,235],"methods":[190],"has":[191,238],"substantial":[192],"relative":[193,205],"compared":[195],"with":[196],"mainstream":[197],"systems.":[198],"Compared":[199],"systems":[212],"23.5%,":[214],"27.1%,":[215],"43.0%,":[217],"respectively.":[218],"our":[221],"collected":[222],"CALLHOME97,":[224],"CALLHOME00,":[225],"SRE08":[227],"short2-summed":[228],"trial":[229],"conditions":[230],"also":[231],"system":[237],"best":[240],"overall":[241]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}