{"id":"https://openalex.org/W2039932784","doi":"https://doi.org/10.1145/1647314.1647327","title":"A speaker diarization method based on the probabilistic fusion of audio-visual location information","display_name":"A speaker diarization method based on the probabilistic fusion of audio-visual location information","publication_year":2009,"publication_date":"2009-11-02","ids":{"openalex":"https://openalex.org/W2039932784","doi":"https://doi.org/10.1145/1647314.1647327","mag":"2039932784"},"language":"en","primary_location":{"id":"doi:10.1145/1647314.1647327","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1647314.1647327","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2009 international conference on Multimodal interfaces","raw_type":"proceedings-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/A5066431676","display_name":"Kentaro Ishizuka","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":true,"raw_author_name":"Kentaro Ishizuka","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, 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":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014373252","display_name":"Kazuhiro Otsuka","orcid":"https://orcid.org/0000-0003-4352-3955"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kazuhiro Otsuka","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Atsugi, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Atsugi, Japan","institution_ids":[]}]},{"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":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109368288","display_name":"Masakiyo Fujimoto","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":"Masakiyo Fujimoto","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5066431676"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":1.391403,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.82250301,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"55","last_page":"62"},"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":0.9984999895095825,"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":0.9937999844551086,"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":0.8783116340637207},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8026818633079529},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6477206945419312},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5826721787452698},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5545451641082764},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4624194800853729},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.443654328584671},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4290929436683655}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8783116340637207},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8026818633079529},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6477206945419312},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5826721787452698},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5545451641082764},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4624194800853729},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.443654328584671},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4290929436683655},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1647314.1647327","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1647314.1647327","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2009 international conference on Multimodal interfaces","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.47999998927116394,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W56546390","https://openalex.org/W124143575","https://openalex.org/W1524832141","https://openalex.org/W1540832706","https://openalex.org/W1556857061","https://openalex.org/W1557470594","https://openalex.org/W1578455363","https://openalex.org/W1584960981","https://openalex.org/W1781788938","https://openalex.org/W1876378865","https://openalex.org/W1987906574","https://openalex.org/W2000221426","https://openalex.org/W2018898818","https://openalex.org/W2035090801","https://openalex.org/W2046317813","https://openalex.org/W2071795835","https://openalex.org/W2081841744","https://openalex.org/W2091699016","https://openalex.org/W2094694057","https://openalex.org/W2103738385","https://openalex.org/W2106213684","https://openalex.org/W2113679114","https://openalex.org/W2113850638","https://openalex.org/W2115175902","https://openalex.org/W2117321034","https://openalex.org/W2120478181","https://openalex.org/W2121973264","https://openalex.org/W2125336414","https://openalex.org/W2129120544","https://openalex.org/W2134584072","https://openalex.org/W2138414774","https://openalex.org/W2141398670","https://openalex.org/W2145887942","https://openalex.org/W2146507038","https://openalex.org/W2148613904","https://openalex.org/W2153994037","https://openalex.org/W2156972497","https://openalex.org/W2159591770","https://openalex.org/W2163704482","https://openalex.org/W2171092607","https://openalex.org/W2171784699","https://openalex.org/W2338994564","https://openalex.org/W3147539069","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1879255185","https://openalex.org/W1977167953","https://openalex.org/W2149220986","https://openalex.org/W4247736853","https://openalex.org/W2120442551","https://openalex.org/W2162158162","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W1493012537"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,34,51,61,100,104,111,143,158,175,186],"speaker":[4,129,134,190,198,204],"diarization":[5,84],"method":[6,88],"for":[7],"determining":[8],"\"\"who":[9],"spoke":[10],"when\"\"":[11],"in":[12,73,99,142,174],"multi-party":[13,42],"conversations,":[14,223],"based":[15,128,162],"on":[16],"the":[17,90,93,133,138,149,215,236,239],"probabilistic":[18],"fusion":[19],"of":[20,47,75,92,95,109,114,119,189,238],"audio":[21,27,69],"and":[22,28,50,58,70,125,203,228],"visual":[23,29,71],"location":[24],"information.":[25],"The":[26,44,172,200],"information":[30,126],"is":[31],"obtained":[32,156],"from":[33,68,77,152],"compact":[35],"system":[36,45],"designed":[37],"to":[38,196,212],"analyze":[39],"round":[40],"table":[41],"conversations.":[43],"consists":[46],"two":[48,166],"cameras":[49,167],"triangular":[52],"microphone":[53,106],"array":[54],"with":[55,103,148,157,165,169,178],"three":[56],"microphones,":[57],"can":[59],"cover":[60],"spherical":[62],"region.":[63],"Speaker":[64],"locations":[65,155,173],"are":[66,146,182,206],"estimated":[67,151],"observations":[72],"terms":[74],"azimuths":[76],"this":[78],"recording":[79],"system.":[80],"Unlike":[81],"conventional":[82],"speech":[83,115,139,230],"methods,":[85],"our":[86],"proposed":[87,240],"estimates":[89],"probability":[91,201],"presence":[94,135,140],"multiple":[96],"simultaneous":[97],"speakers":[98],"physical":[101,144,176],"space":[102,145,177],"small":[105],"setup":[107],"instead":[108],"using":[110,193,220],"cascade":[112],"consisting":[113],"activity":[116],"detection,":[117],"direction":[118],"arrival":[120],"estimation,":[121],"acoustic":[122],"feature":[123],"extraction,":[124],"criteria":[127],"segmentation.":[130],"To":[131],"estimate":[132],"more":[136,226],"correctly,":[137],"probabilities":[141,150,181],"integrated":[147,180],"participants'":[153],"face":[154,163],"robust":[159],"particle":[160],"filtering":[161],"tracker":[164],"equipped":[168],"fisheye":[170],"lenses.":[171],"highly":[179],"then":[183],"classified":[184],"into":[185],"certain":[187],"number":[188],"classes":[191],"by":[192],"on-line":[194],"classification":[195],"realize":[197],"diarization.":[199],"calculations":[202],"classifications":[205],"conducted":[207],"on-line,":[208],"making":[209],"it":[210],"unnecessary":[211],"observe":[213],"all":[214],"conversation":[216],"data.":[217],"An":[218],"experiment":[219],"real":[221],"casual":[222],"which":[224],"include":[225],"overlaps":[227],"short":[229],"segments":[231],"than":[232],"formal":[233],"meetings,":[234],"showed":[235],"advantages":[237],"method.":[241]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
