{"id":"https://openalex.org/W2039206676","doi":"https://doi.org/10.1109/tasl.2011.2151858","title":"Probabilistic Speaker Diarization With Bag-of-Words Representations of Speaker Angle Information","display_name":"Probabilistic Speaker Diarization With Bag-of-Words Representations of Speaker Angle Information","publication_year":2011,"publication_date":"2011-05-10","ids":{"openalex":"https://openalex.org/W2039206676","doi":"https://doi.org/10.1109/tasl.2011.2151858","mag":"2039206676"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2011.2151858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2011.2151858","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/A5000004444","display_name":"Katsuhiko Ishiguro","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katsuhiko Ishiguro","raw_affiliation_strings":["The NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073170587","display_name":"Takeshi Yamada","orcid":"https://orcid.org/0000-0002-5744-8469"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takeshi Yamada","raw_affiliation_strings":["NTT Science and Core Technology Laboratory Group, NTT Corporation, Kanagawa, Japan","NTT Sci. & Core Technol. Lab. Group, NTT Corp., Atsugi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Science and Core Technology Laboratory Group, NTT Corporation, Kanagawa, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Sci. & Core Technol. Lab. Group, NTT Corp., Atsugi, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009309584","display_name":"Shoko Araki","orcid":"https://orcid.org/0000-0003-4363-4305"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoko Araki","raw_affiliation_strings":["The NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["The NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007032557","display_name":"Hiroshi Sawada","orcid":"https://orcid.org/0000-0002-4831-9286"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Sawada","raw_affiliation_strings":["The NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1847,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.879901,"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":"447","last_page":"460"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9998999834060669,"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":0.9988999962806702,"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":0.9418396353721619},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7259976267814636},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6752541065216064},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6010276675224304},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5815915465354919},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5766472220420837},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4902415871620178},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.4793282747268677},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4786418676376343},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.452282190322876},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.431182324886322},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3874531090259552},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34830522537231445}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9418396353721619},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7259976267814636},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6752541065216064},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6010276675224304},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5815915465354919},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5766472220420837},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4902415871620178},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.4793282747268677},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4786418676376343},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.452282190322876},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.431182324886322},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3874531090259552},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34830522537231445},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tasl.2011.2151858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2011.2151858","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:10.1.1.710.7246","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.710.7246","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.kecl.ntt.co.jp/as/members/ishiguro/open/2012IEEE_TASLP.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1556857061","https://openalex.org/W1557470594","https://openalex.org/W1663973292","https://openalex.org/W1876378865","https://openalex.org/W1880262756","https://openalex.org/W1991048564","https://openalex.org/W2000221426","https://openalex.org/W2031109238","https://openalex.org/W2035090801","https://openalex.org/W2042737139","https://openalex.org/W2057099756","https://openalex.org/W2082968463","https://openalex.org/W2091699016","https://openalex.org/W2103738385","https://openalex.org/W2113679114","https://openalex.org/W2113850638","https://openalex.org/W2115417872","https://openalex.org/W2115878730","https://openalex.org/W2121903040","https://openalex.org/W2125336414","https://openalex.org/W2134665698","https://openalex.org/W2135537007","https://openalex.org/W2141398670","https://openalex.org/W2146078527","https://openalex.org/W2148780922","https://openalex.org/W2151103935","https://openalex.org/W2159284737","https://openalex.org/W2159591770","https://openalex.org/W2167270514","https://openalex.org/W2169264834","https://openalex.org/W2171784699","https://openalex.org/W2172085063","https://openalex.org/W2338994564","https://openalex.org/W2532363096","https://openalex.org/W2539222059","https://openalex.org/W2610184409","https://openalex.org/W4205687621","https://openalex.org/W4212863985","https://openalex.org/W4237791300","https://openalex.org/W4256205487","https://openalex.org/W6633097512","https://openalex.org/W6639431793","https://openalex.org/W6676004468","https://openalex.org/W6676892421","https://openalex.org/W6838334432"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1493012537","https://openalex.org/W1977167953","https://openalex.org/W1197719229","https://openalex.org/W2381158726","https://openalex.org/W2552734076","https://openalex.org/W2162158162","https://openalex.org/W1992796048","https://openalex.org/W4247736853","https://openalex.org/W2175373321"],"abstract_inverted_index":{"Speaker":[0],"diarization":[1,111,180],"determines":[2],"\u201cwho":[3],"spoke":[4],"when\u201d":[5],"from":[6,126],"the":[7,25,27,31,34,46,51,72,76,79,110,115,141,146,154,162,168],"recorded":[8],"conversations":[9],"of":[10,14,33,43,78,88,121,145,172],"an":[11,85,149],"unknown":[12,86],"number":[13,87,142,169],"people.":[15],"In":[16,67],"general,":[17],"we":[18,70],"have":[19],"no":[20],"a":[21,95,127,131],"priori":[22],"information":[23,124],"about":[24],"number,":[26],"locations,":[28],"or":[29,177],"even":[30,59],"characteristics":[32],"speakers.":[35],"Additionally,":[36],"speakers'":[37],"speech":[38],"utterances":[39],"vary":[40],"dynamically":[41],"because":[42],"turn-taking":[44],"during":[45],"conversations.":[47],"These":[48],"conditions":[49],"make":[50],"speaker-clustering":[52,73],"task":[53],"extremely":[54],"difficult.":[55],"The":[56,136],"problem":[57,74],"becomes":[58],"harder":[60],"if":[61],"online":[62,150],"(incremental)":[63],"processing":[64],"is":[65],"required.":[66],"this":[68],"paper,":[69],"formulate":[71],"as":[75],"clustering":[77],"sequential":[80],"audio":[81],"features":[82,171],"generated":[83],"by":[84],"latent":[89],"mixture":[90],"components":[91],"(speakers).":[92],"We":[93,113],"employ":[94],"probabilistic":[96,117],"model":[97,118,164],"that":[98,161],"assumes":[99],"time-sensitive":[100],"speaker":[101,179],"mixtures":[102],"at":[103],"every":[104],"time":[105],"frame,":[106],"which,":[107],"surprisingly,":[108],"suits":[109],"scenario.":[112],"combine":[114],"time-varying":[116],"with":[119,183],"direction":[120],"arrival":[122],"(DOA)":[123],"calculated":[125],"microphone":[128],"array":[129],"in":[130,148,186],"bag-of-words":[132],"(BoW)-style":[133],"feature":[134],"representation.":[135],"proposed":[137,163],"system":[138],"effectively":[139],"estimates":[140],"and":[143,170,174],"locations":[144],"speakers":[147,173],"manner":[151],"based":[152],"on":[153],"standard":[155],"Bayes":[156],"inference":[157],"scheme.":[158],"Experiments":[159],"confirm":[160],"can":[165],"successfully":[166],"infer":[167],"yield":[175],"better":[176],"comparable":[178],"results":[181],"compared":[182],"conventional":[184],"methods":[185],"several":[187],"datasets.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}