{"id":"https://openalex.org/W2753324760","doi":"https://doi.org/10.1109/taslp.2017.2747097","title":"Active Learning Based Constrained Clustering For Speaker Diarization","display_name":"Active Learning Based Constrained Clustering For Speaker Diarization","publication_year":2017,"publication_date":"2017-09-08","ids":{"openalex":"https://openalex.org/W2753324760","doi":"https://doi.org/10.1109/taslp.2017.2747097","mag":"2753324760"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2017.2747097","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2747097","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/A5040951732","display_name":"Chengzhu Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chengzhu Yu","raw_affiliation_strings":["Jonsson School of Engineering and Computer, Center for Robust Speech Systems, Richardson, TX, USA"],"affiliations":[{"raw_affiliation_string":"Jonsson School of Engineering and Computer, Center for Robust Speech Systems, Richardson, TX, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H. L. Hansen","raw_affiliation_strings":["Center for Robust Speech, University of Texas at Dallas, Richardson, TX, USA"],"affiliations":[{"raw_affiliation_string":"Center for Robust Speech, University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5040951732"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5355,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.91916302,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"25","issue":"11","first_page":"2188","last_page":"2198"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9958000183105469,"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":0.994700014591217,"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/cluster-analysis","display_name":"Cluster analysis","score":0.881564736366272},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.8187134265899658},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7855523824691772},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.500192403793335},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.49748876690864563},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4403063952922821},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42582836747169495},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3626590073108673},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3362797498703003}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.881564736366272},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8187134265899658},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7855523824691772},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.500192403793335},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.49748876690864563},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4403063952922821},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42582836747169495},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3626590073108673},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3362797498703003},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2017.2747097","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2747097","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G391327479","display_name":null,"funder_award_id":"1219130","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8087301405","display_name":null,"funder_award_id":"FA8750-15-1-0205","funder_id":"https://openalex.org/F4320338294","funder_display_name":"Air Force Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310578","display_name":"University of Maryland","ror":"https://ror.org/01r0c1p88"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W106647055","https://openalex.org/W120286951","https://openalex.org/W202636654","https://openalex.org/W1482605500","https://openalex.org/W1484181928","https://openalex.org/W1558643924","https://openalex.org/W1569447338","https://openalex.org/W1583620810","https://openalex.org/W1936725236","https://openalex.org/W1971791733","https://openalex.org/W2038101708","https://openalex.org/W2038162002","https://openalex.org/W2052269122","https://openalex.org/W2060656758","https://openalex.org/W2069642050","https://openalex.org/W2081074144","https://openalex.org/W2086086554","https://openalex.org/W2098726438","https://openalex.org/W2100346396","https://openalex.org/W2104353650","https://openalex.org/W2115130489","https://openalex.org/W2115175902","https://openalex.org/W2121415728","https://openalex.org/W2121812409","https://openalex.org/W2125094180","https://openalex.org/W2135914502","https://openalex.org/W2141030161","https://openalex.org/W2141262306","https://openalex.org/W2142458924","https://openalex.org/W2144125830","https://openalex.org/W2148613904","https://openalex.org/W2150769028","https://openalex.org/W2153839362","https://openalex.org/W2159591770","https://openalex.org/W2166467513","https://openalex.org/W2181464176","https://openalex.org/W2198484938","https://openalex.org/W2338994564","https://openalex.org/W2397622291","https://openalex.org/W2405472765","https://openalex.org/W2406312423","https://openalex.org/W2406555014","https://openalex.org/W2514325906","https://openalex.org/W2576939402","https://openalex.org/W4245862033","https://openalex.org/W4301688325","https://openalex.org/W6604245201","https://openalex.org/W6604900475","https://openalex.org/W6628802092","https://openalex.org/W6628911050","https://openalex.org/W6633348054","https://openalex.org/W6633847657","https://openalex.org/W6680343000","https://openalex.org/W6686172093","https://openalex.org/W6712379007","https://openalex.org/W6713727690","https://openalex.org/W6714102123","https://openalex.org/W6743236028","https://openalex.org/W7035534229"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"Most":[0],"speaker":[1,48,54,67,90,93,99,167,175,214],"diarization":[2,55,192,259],"research":[3],"has":[4,69],"focused":[5],"on":[6,229],"unsupervised":[7],"scenarios,":[8],"where":[9],"no":[10],"human":[11,24,32,59,196,221,269],"supervision":[12,33],"is":[13,80,117,121,170],"available.":[14],"However,":[15],"in":[16],"many":[17],"real-world":[18],"applications,":[19],"a":[20,105,200,264],"certain":[21],"amount":[22,267],"of":[23,107,163,268],"input":[25],"could":[26],"be":[27],"expected,":[28],"especially":[29],"when":[30],"minimal":[31],"brings":[34],"significant":[35],"performance":[36,56,177,193],"improvement.":[37],"In":[38],"this":[39],"study,":[40],"we":[41,198],"propose":[42,199],"an":[43,129],"active":[44,64,164,252],"learning":[45,65,165,253],"based":[46,66,166],"bottom-up":[47,125],"clustering":[49,68,94,116,120,126,147,168],"algorithm":[50,169],"to":[51,81,123,171,257],"effectively":[52],"improve":[53,191],"with":[57,96,128,143,194,263],"limited":[58],"input.":[60],"Specifically,":[61],"the":[62,108,114,133,151,155,161,211,250],"proposed":[63,251],"two":[70],"different":[71],"stages:":[72],"explore":[73,78,112,137,156],"and":[74,223],"constrained":[75,115],"clustering.":[76],"The":[77,225,246],"stage":[79,138,157],"quickly":[82],"discover":[83],"at":[84],"least":[85],"one":[86],"sample":[87],"for":[88,91,186,210,220],"each":[89,144,187],"boosting":[92],"process":[95,127],"reliable":[97],"initial":[98,174],"clusters.":[100],"After":[101],"discovering":[102],"all,":[103],"or":[104],"majority,":[106],"involved":[109],"speakers":[110],"during":[111,136],"stage,":[113],"performed.":[118],"Constrained":[119,146],"similar":[122],"traditional":[124],"important":[130],"difference":[131],"that":[132,208,249],"clusters":[134,152],"created":[135,232],"are":[139,158,184,227,255],"restricted":[140],"from":[141,154,216],"merging":[142],"other.":[145],"continues":[148],"until":[149],"only":[150],"generated":[153],"left.":[159],"Since":[160],"objective":[162],"provide":[172],"good":[173],"models,":[176],"saturates":[178],"as":[179,181,238,240],"soon":[180],"sufficient":[182],"examples":[183],"ensured":[185],"cluster.":[188],"To":[189],"further":[190],"increasing":[195],"input,":[197],"second":[201],"method":[202],"which":[203],"actively":[204],"select":[205],"speech":[206],"segments":[207],"account":[209],"largest":[212],"expected":[213],"error":[215,260],"existing":[217],"cluster":[218],"assignments":[219],"evaluation":[222],"reassignment.":[224],"algorithms":[226,254],"evaluated":[228],"our":[230],"recently":[231],"Apollo":[233],"Mission":[234],"Control":[235],"Center":[236],"dataset":[237],"well":[239],"augmented":[241],"multiparty":[242],"interaction":[243],"meeting":[244],"corpus.":[245],"results":[247],"indicate":[248],"able":[256],"reduce":[258],"rate":[261],"significantly":[262],"relatively":[265],"small":[266],"supervision.":[270]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2026-02-27T16:54:17.756197","created_date":"2025-10-10T00:00:00"}