{"id":"https://openalex.org/W1969290787","doi":"https://doi.org/10.1109/tasl.2011.2159203","title":"Speaker Clustering and Cluster Purification Methods for RT07 and RT09 Evaluation Meeting Data","display_name":"Speaker Clustering and Cluster Purification Methods for RT07 and RT09 Evaluation Meeting Data","publication_year":2012,"publication_date":"2012-01-31","ids":{"openalex":"https://openalex.org/W1969290787","doi":"https://doi.org/10.1109/tasl.2011.2159203","mag":"1969290787"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2011.2159203","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2011.2159203","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/A5050008407","display_name":"Tin Lay Nwe","orcid":"https://orcid.org/0000-0003-1111-580X"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Tin Lay Nwe","raw_affiliation_strings":["Human Language Technology Department Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore","Human Language Technol. Dept., A*STAR, Singapore, Singapore#TAB#"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Department Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Human Language Technol. Dept., A*STAR, Singapore, Singapore#TAB#","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100813843","display_name":"Hanwu Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hanwu Sun","raw_affiliation_strings":["Human Language Technology Department Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore","Human Language Technol. Dept., A*STAR, Singapore, Singapore#TAB#"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Department Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Human Language Technol. Dept., A*STAR, Singapore, Singapore#TAB#","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749735","display_name":"Bin Ma","orcid":"https://orcid.org/0000-0002-9223-9654"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bin Ma","raw_affiliation_strings":["Human Language Technology Department Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore","Human Language Technol. Dept., A*STAR, Singapore, Singapore#TAB#"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Department Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Human Language Technol. Dept., A*STAR, Singapore, Singapore#TAB#","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Human Language Technology Department Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore","Human Language Technol. Dept., A*STAR, Singapore, Singapore#TAB#"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Department Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Human Language Technol. Dept., A*STAR, Singapore, Singapore#TAB#","institution_ids":["https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5050008407"],"corresponding_institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"],"apc_list":null,"apc_paid":null,"fwci":1.9588,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.88563898,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"20","issue":"2","first_page":"461","last_page":"473"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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":0.9409594535827637},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7521475553512573},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.745036780834198},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.604224443435669},{"id":"https://openalex.org/keywords/bayesian-information-criterion","display_name":"Bayesian information criterion","score":0.5896729826927185},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5384718179702759},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5240597724914551},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.5004012584686279},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4594886898994446},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42854517698287964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37689968943595886}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9409594535827637},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7521475553512573},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.745036780834198},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.604224443435669},{"id":"https://openalex.org/C168136583","wikidata":"https://www.wikidata.org/wiki/Q1988242","display_name":"Bayesian information criterion","level":2,"score":0.5896729826927185},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5384718179702759},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5240597724914551},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.5004012584686279},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4594886898994446},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42854517698287964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37689968943595886},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2011.2159203","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2011.2159203","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":[{"display_name":"Peace, Justice and strong institutions","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W41021157","https://openalex.org/W1482605500","https://openalex.org/W1484181928","https://openalex.org/W1526948613","https://openalex.org/W1548779692","https://openalex.org/W1800068500","https://openalex.org/W1963976507","https://openalex.org/W2040023846","https://openalex.org/W2041823554","https://openalex.org/W2044591814","https://openalex.org/W2100969003","https://openalex.org/W2106015547","https://openalex.org/W2113386290","https://openalex.org/W2114863372","https://openalex.org/W2115130489","https://openalex.org/W2115417872","https://openalex.org/W2135636388","https://openalex.org/W2136752740","https://openalex.org/W2144125830","https://openalex.org/W2146871184","https://openalex.org/W2153994037","https://openalex.org/W2159591770","https://openalex.org/W2159730002","https://openalex.org/W2162627003","https://openalex.org/W2338994564","https://openalex.org/W3129653033","https://openalex.org/W4244494905","https://openalex.org/W6601719842","https://openalex.org/W6628802092","https://openalex.org/W6628911050","https://openalex.org/W6682965620"],"related_works":["https://openalex.org/W2118039276","https://openalex.org/W2206035908","https://openalex.org/W2119836628","https://openalex.org/W2356325859","https://openalex.org/W106647055","https://openalex.org/W1977167953","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,46,73,112,138,148,170],"design":[4],"strategy":[5],"for":[6,29,176,191],"the":[7,12,16,30,59,68,89,92,99,108,119,156,163],"speaker":[8,109,153,157,160,174],"diarization":[9,47,175],"system":[10,37,168],"in":[11,45,129,155,162],"IIR":[13],"submissions":[14],"to":[15,117,121,131,150],"2007":[17],"and":[18,27,55,58,65,76,102,178,184,194],"2009":[19],"NIST":[20],"Rich":[21],"Transcription":[22],"Meeting":[23],"Recognition":[24],"Evaluations":[25],"(RT07":[26],"RT09)":[28],"multiple":[31,95],"distant":[32,96],"microphone":[33],"(MDM)":[34],"condition.":[35],"The":[36,49,125,167],"features":[38,86],"two":[39,42,126],"algorithms":[40],"supporting":[41],"important":[43],"steps":[44,127],"process.":[48,135,166],"first":[50],"step":[51],"is":[52,62],"Initial":[53],"Segmentation":[54],"Clustering":[56],"(ISC),":[57],"second":[60],"one":[61],"cluster":[63,100,164],"merging":[64,101],"purification.":[66],"In":[67,98],"ISC":[69],"step,":[70,104],"we":[71,105],"propose":[72,137],"histogram":[74],"quantization":[75],"clustering":[77],"technique":[78,149],"based":[79],"on":[80],"time":[81],"delay":[82],"of":[83,173],"arrival":[84],"(TDOA)":[85],"by":[87],"analyzing":[88],"correlation":[90],"among":[91],"signals":[93],"across":[94],"microphones.":[97],"purification":[103,165],"further":[106],"merge":[107],"clusters":[110,120,158],"using":[111],"Bayesian":[113],"information":[114],"criterion":[115],"(BIC)":[116],"consolidate":[118],"arrive":[122],"at":[123],"one-cluster-per-speaker.":[124],"work":[128],"tandem":[130],"form":[132],"an":[133],"integral":[134],"We":[136],"novel":[139],"Consensus":[140],"Based":[141],"Cluster":[142],"Purification":[143],"(CBCP)":[144],"method":[145],"that":[146],"involves":[147],"remove":[151],"impure":[152],"segments":[154],"before":[159],"modeling":[161],"reports":[169],"state-of-the-art":[171],"performance":[172],"RT07":[177],"RT09":[179],"MDM":[180],"condition":[181],"with":[182],"7.47%":[183],"8.77%":[185],"Diarization":[186],"error":[187],"rates":[188],"(DERs),":[189],"respectively,":[190],"both":[192],"overlapping":[193],"non-overlapping":[195],"speech.":[196]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}