{"id":"https://openalex.org/W2316138215","doi":"https://doi.org/10.1109/tpami.2017.2648793","title":"Audio-Visual Speaker Diarization Based on Spatiotemporal Bayesian Fusion","display_name":"Audio-Visual Speaker Diarization Based on Spatiotemporal Bayesian Fusion","publication_year":2017,"publication_date":"2017-01-05","ids":{"openalex":"https://openalex.org/W2316138215","doi":"https://doi.org/10.1109/tpami.2017.2648793","mag":"2316138215","pmid":"https://pubmed.ncbi.nlm.nih.gov/28103192"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2017.2648793","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2017.2648793","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1603.09725","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072548521","display_name":"Israel D. Gebru","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Israel D. Gebru","raw_affiliation_strings":["INRIA Grenoble Rh\u00f4ne-Alpes, Montbonnot Saint-Martin, France","PERCEPTION  - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rh\u00f4ne-Alpes, Montbonnot Saint-Martin, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"raw_affiliation_string":"PERCEPTION  - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037326211","display_name":"Sil\u00e8ye Ba","orcid":"https://orcid.org/0000-0003-4581-9880"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sileye Ba","raw_affiliation_strings":["INRIA Grenoble Rh\u00f4ne-Alpes, Montbonnot Saint-Martin, France","PERCEPTION  - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rh\u00f4ne-Alpes, Montbonnot Saint-Martin, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"raw_affiliation_string":"PERCEPTION  - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100358313","display_name":"Xiaofei Li","orcid":"https://orcid.org/0000-0003-0393-9905"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Xiaofei Li","raw_affiliation_strings":["INRIA Grenoble Rh\u00f4ne-Alpes, Montbonnot Saint-Martin, France","PERCEPTION  - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rh\u00f4ne-Alpes, Montbonnot Saint-Martin, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"raw_affiliation_string":"PERCEPTION  - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078307335","display_name":"Radu Horaud","orcid":"https://orcid.org/0000-0001-5232-024X"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Radu Horaud","raw_affiliation_strings":["INRIA Grenoble Rh\u00f4ne-Alpes, Montbonnot Saint-Martin, France","PERCEPTION  - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)"],"raw_orcid":"https://orcid.org/0000-0001-5232-024X","affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rh\u00f4ne-Alpes, Montbonnot Saint-Martin, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"raw_affiliation_string":"PERCEPTION  - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.4829,"has_fulltext":false,"cited_by_count":112,"citation_normalized_percentile":{"value":0.98592991,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"40","issue":"5","first_page":"1086","last_page":"1099"},"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":0.9986000061035156,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9860000014305115,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.8630198836326599},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8106334209442139},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6284599304199219},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5618544220924377},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5244122743606567},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5134575963020325},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5131924748420715},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4588322043418884},{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.4210284352302551},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3771158456802368},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3003205955028534}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8630198836326599},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8106334209442139},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6284599304199219},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5618544220924377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5244122743606567},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5134575963020325},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5131924748420715},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4588322043418884},{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.4210284352302551},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3771158456802368},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3003205955028534}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tpami.2017.2648793","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2017.2648793","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:28103192","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28103192","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:arXiv.org:1603.09725","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1603.09725","pdf_url":"https://arxiv.org/pdf/1603.09725","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-01413403v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01413403","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40 (5), pp.1086 - 1099. ⟨10.1109/TPAMI.2017.2648793⟩","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1603.09725","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1603.09725","pdf_url":"https://arxiv.org/pdf/1603.09725","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5199999809265137}],"awards":[{"id":"https://openalex.org/G8639352515","display_name":null,"funder_award_id":"2015-2017","funder_id":"https://openalex.org/F4320316964","funder_display_name":"Universidade dos A\u00e7ores"}],"funders":[{"id":"https://openalex.org/F4320316964","display_name":"Universidade dos A\u00e7ores","ror":"https://ror.org/04276xd64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W142991516","https://openalex.org/W1552633171","https://openalex.org/W1562651896","https://openalex.org/W1583773829","https://openalex.org/W1873027057","https://openalex.org/W1908118577","https://openalex.org/W1967504554","https://openalex.org/W1971791733","https://openalex.org/W1971901154","https://openalex.org/W1973878427","https://openalex.org/W1974644251","https://openalex.org/W1991048564","https://openalex.org/W2011699475","https://openalex.org/W2036365100","https://openalex.org/W2042608483","https://openalex.org/W2049893888","https://openalex.org/W2055022211","https://openalex.org/W2060108923","https://openalex.org/W2081074144","https://openalex.org/W2082198998","https://openalex.org/W2084637638","https://openalex.org/W2088725063","https://openalex.org/W2096301647","https://openalex.org/W2096391593","https://openalex.org/W2099151709","https://openalex.org/W2100818340","https://openalex.org/W2102759648","https://openalex.org/W2105582566","https://openalex.org/W2106488367","https://openalex.org/W2118847468","https://openalex.org/W2123921937","https://openalex.org/W2124247842","https://openalex.org/W2125336414","https://openalex.org/W2127211243","https://openalex.org/W2129171989","https://openalex.org/W2129821199","https://openalex.org/W2138414774","https://openalex.org/W2142352693","https://openalex.org/W2154524549","https://openalex.org/W2164899449","https://openalex.org/W2204714259","https://openalex.org/W2229192656","https://openalex.org/W2236062296","https://openalex.org/W2250436945","https://openalex.org/W2338994564","https://openalex.org/W2535410496","https://openalex.org/W6678809451","https://openalex.org/W6679546383","https://openalex.org/W6684193366","https://openalex.org/W6689904503"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W1992908141","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845"],"abstract_inverted_index":{"Speaker":[0],"diarization":[1,16,148,185,237],"consists":[2],"of":[3,30,126,169,183,210],"assigning":[4],"speech":[5,140,163],"signals":[6,141],"to":[7,68,120,233],"people":[8],"engaged":[9,33,215],"in":[10,34,66,136,216],"a":[11,79,95,99,112,137,153,208],"dialogue.":[12],"An":[13],"audio-visual":[14,81,101,171,202],"spatiotemporal":[15],"model":[17,21,157],"is":[18,22,60,76,132,150,221,226],"proposed.":[19],"The":[20,74,123,147,188,223],"well":[23,206],"suited":[24],"for":[25],"challenging":[26],"scenarios":[27,211],"that":[28,133,158,200],"consist":[29],"several":[31,213,234],"participants":[32,48,214],"multi-party":[35],"interaction":[36],"while":[37],"they":[38],"move":[39],"around":[40],"and":[41,54,110,162,179,218,229],"turn":[42],"their":[43],"heads":[44],"towards":[45],"the":[46,52,55,70,85,167,181,184],"other":[47],"rather":[49],"than":[50],"facing":[51],"cameras":[53],"microphones.":[56],"Multiple-person":[57],"visual":[58],"tracking":[59],"combined":[61],"with":[62,231],"multiple":[63,145],"speech-source":[64],"localization":[65],"order":[67],"tackle":[69],"speech-to-person":[71],"association":[72,172],"problem.":[73],"latter":[75],"solved":[77],"within":[78],"novel":[80,198],"fusion":[82],"method":[83,115,128,225],"on":[84,166,180],"following":[86],"grounds:":[87],"binaural":[88,117],"spectral":[89,118],"features":[90,106,119],"are":[91],"first":[92],"extracted":[93],"from":[94],"microphone":[96],"pair,":[97],"then":[98],"supervised":[100],"alignment":[102],"technique":[103],"maps":[104],"these":[105],"onto":[107],"an":[108,170,192],"image,":[109],"finally":[111],"semi-supervised":[113],"clustering":[114],"assigns":[116],"visible":[121],"persons.":[122,146],"main":[124],"advantage":[125],"this":[127],"over":[129],"previous":[130],"work":[131],"it":[134],"processes":[135],"principled":[138],"way":[139],"uttered":[142],"simultaneously":[143],"by":[144],"itself":[149],"cast":[151],"into":[152],"latent-variable":[154],"temporal":[155],"graphical":[156],"infers":[159],"speaker":[160],"identities":[161],"turns,":[164],"based":[165],"output":[168],"process,":[173],"executed":[174],"at":[175],"each":[176],"time":[177],"slice,":[178],"dynamics":[182],"variable":[186],"itself.":[187],"proposed":[189,224],"formulation":[190],"yields":[191],"efficient":[193],"exact":[194],"inference":[195],"procedure.":[196],"A":[197],"dataset,":[199],"contains":[201],"training":[203],"data":[204],"as":[205,207],"number":[209],"involving":[212],"formal":[217],"informal":[219],"dialogue,":[220],"introduced.":[222],"thoroughly":[227],"tested":[228],"benchmarked":[230],"respect":[232],"state-of-the":[235],"art":[236],"algorithms.":[238]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":6}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}