{"id":"https://openalex.org/W2000942689","doi":"https://doi.org/10.1109/icassp.2014.6853569","title":"A conditional random field approach for audio-visual people diarization","display_name":"A conditional random field approach for audio-visual people diarization","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2000942689","doi":"https://doi.org/10.1109/icassp.2014.6853569","mag":"2000942689"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6853569","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853569","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/198435","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113558267","display_name":"G.Prem paul","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]},{"id":"https://openalex.org/I7947594","display_name":"University of Maine","ror":"https://ror.org/01adr0w49","country_code":"US","type":"education","lineage":["https://openalex.org/I2802397601","https://openalex.org/I7947594"]},{"id":"https://openalex.org/I4210108471","display_name":"Le Mans Universit\u00e9","ror":"https://ror.org/01mtcc283","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108471"]}],"countries":["CH","FR","US"],"is_corresponding":true,"raw_author_name":"Gay Paul","raw_affiliation_strings":["LIUM, University of Maine, Le Mans, France","LIUM - Laboratoire d'Informatique de l'Universit\u00e9 du Mans (Avenue Laennec 72085 Le Mans cedex 9 - France)","IDIAP Research Institute (Centre du Parc Rue Marconi 19 PO Box 592 CH - 1920 Martigny Switzerland - Switzerland)"],"affiliations":[{"raw_affiliation_string":"LIUM, University of Maine, Le Mans, France","institution_ids":["https://openalex.org/I4210108471","https://openalex.org/I7947594"]},{"raw_affiliation_string":"LIUM - Laboratoire d'Informatique de l'Universit\u00e9 du Mans (Avenue Laennec 72085 Le Mans cedex 9 - France)","institution_ids":["https://openalex.org/I4210108471"]},{"raw_affiliation_string":"IDIAP Research Institute (Centre du Parc Rue Marconi 19 PO Box 592 CH - 1920 Martigny Switzerland - Switzerland)","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105986270","display_name":"Khoury Elie","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Khoury Elie","raw_affiliation_strings":["Idiap Research Institute, Switzerland","IDIAP Research Institute (Centre du Parc Rue Marconi 19 PO Box 592 CH - 1920 Martigny Switzerland - Switzerland)"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Research Institute (Centre du Parc Rue Marconi 19 PO Box 592 CH - 1920 Martigny Switzerland - Switzerland)","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105835153","display_name":"Meignier Sylvain","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108471","display_name":"Le Mans Universit\u00e9","ror":"https://ror.org/01mtcc283","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108471"]},{"id":"https://openalex.org/I7947594","display_name":"University of Maine","ror":"https://ror.org/01adr0w49","country_code":"US","type":"education","lineage":["https://openalex.org/I2802397601","https://openalex.org/I7947594"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Meignier Sylvain","raw_affiliation_strings":["LIUM, University of Maine, Le Mans, France","LIUM - Laboratoire d'Informatique de l'Universit\u00e9 du Mans (Avenue Laennec 72085 Le Mans cedex 9 - France)"],"affiliations":[{"raw_affiliation_string":"LIUM, University of Maine, Le Mans, France","institution_ids":["https://openalex.org/I4210108471","https://openalex.org/I7947594"]},{"raw_affiliation_string":"LIUM - Laboratoire d'Informatique de l'Universit\u00e9 du Mans (Avenue Laennec 72085 Le Mans cedex 9 - France)","institution_ids":["https://openalex.org/I4210108471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053358969","display_name":"Jean\u2010Marc Odobez","orcid":"https://orcid.org/0000-0002-9537-9898"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Odobez Jean-Marc","raw_affiliation_strings":["Idiap Research Institute, Switzerland","IDIAP Research Institute (Centre du Parc Rue Marconi 19 PO Box 592 CH - 1920 Martigny Switzerland - Switzerland)"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Research Institute (Centre du Parc Rue Marconi 19 PO Box 592 CH - 1920 Martigny Switzerland - Switzerland)","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089825993","display_name":"Paul Del\u00e9glise","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108471","display_name":"Le Mans Universit\u00e9","ror":"https://ror.org/01mtcc283","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108471"]},{"id":"https://openalex.org/I7947594","display_name":"University of Maine","ror":"https://ror.org/01adr0w49","country_code":"US","type":"education","lineage":["https://openalex.org/I2802397601","https://openalex.org/I7947594"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Deleglise Paul","raw_affiliation_strings":["LIUM, University of Maine, Le Mans, France","LIUM - Laboratoire d'Informatique de l'Universit\u00e9 du Mans (Avenue Laennec 72085 Le Mans cedex 9 - France)"],"affiliations":[{"raw_affiliation_string":"LIUM, University of Maine, Le Mans, France","institution_ids":["https://openalex.org/I4210108471","https://openalex.org/I7947594"]},{"raw_affiliation_string":"LIUM - Laboratoire d'Informatique de l'Universit\u00e9 du Mans (Avenue Laennec 72085 Le Mans cedex 9 - France)","institution_ids":["https://openalex.org/I4210108471"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5113558267"],"corresponding_institution_ids":["https://openalex.org/I4210108471","https://openalex.org/I7495430","https://openalex.org/I7947594"],"apc_list":null,"apc_paid":null,"fwci":2.0609,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.86959001,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"116","last_page":"120"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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":0.9991000294685364,"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/T11448","display_name":"Face recognition and analysis","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/conditional-random-field","display_name":"Conditional random field","score":0.8011785745620728},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7874916791915894},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7519259452819824},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.6656241416931152},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5505176782608032},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5410595536231995},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5376964807510376},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5143448114395142},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5092993974685669},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.436029314994812},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4275626838207245},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.16115760803222656},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.1443905532360077},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13828930258750916}],"concepts":[{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.8011785745620728},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7874916791915894},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7519259452819824},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.6656241416931152},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5505176782608032},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5410595536231995},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5376964807510376},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5143448114395142},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5092993974685669},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.436029314994812},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4275626838207245},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.16115760803222656},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.1443905532360077},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13828930258750916},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2014.6853569","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853569","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.432.5412","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.432.5412","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.idiap.ch/~odobez/publications/GayKhouryMeignierOdobezDeleglise-CRF-AV-Diarization-ICASSP-2014.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-01433223v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01433223","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014), 2014, Florence, Italy. pp.116 - 120, &#x27E8;10.1109/ICASSP.2014.6853569&#x27E9;","raw_type":"Conference papers"},{"id":"pmh:oai:infoscience.tind.io:198435","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/198435","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference proceedings"}],"best_oa_location":{"id":"pmh:oai:infoscience.tind.io:198435","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/198435","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference proceedings"},"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W787977356","https://openalex.org/W994709553","https://openalex.org/W1589339348","https://openalex.org/W2002256968","https://openalex.org/W2007998974","https://openalex.org/W2055251102","https://openalex.org/W2067577150","https://openalex.org/W2083976588","https://openalex.org/W2114981053","https://openalex.org/W2115546586","https://openalex.org/W2125731262","https://openalex.org/W2130105997","https://openalex.org/W2149224569","https://openalex.org/W2161011194","https://openalex.org/W2166980079","https://openalex.org/W2168996682","https://openalex.org/W2169833165","https://openalex.org/W2398758317","https://openalex.org/W2406500670","https://openalex.org/W2595056443","https://openalex.org/W4393363755","https://openalex.org/W6685247644","https://openalex.org/W6713752199"],"related_works":["https://openalex.org/W2356597680","https://openalex.org/W2093471820","https://openalex.org/W50079190","https://openalex.org/W2114846443","https://openalex.org/W3102147106","https://openalex.org/W2111726165","https://openalex.org/W2347460059","https://openalex.org/W4389272081","https://openalex.org/W135211875","https://openalex.org/W4301042974"],"abstract_inverted_index":{"We":[0],"investigate":[1],"the":[2,16,30,39,49,63,67,135,145],"problem":[3,40],"of":[4,20,52,66,75,110,124],"audio-visual":[5],"(AV)":[6],"person":[7,60],"diarization":[8,137],"in":[9,29,144],"broadcast":[10,125],"data.":[11],"That":[12],"is,":[13],"automatically":[14],"associate":[15],"faces":[17],"and":[18,22,54,62,69,78],"voices":[19,53],"people":[21],"determine":[23],"when":[24],"they":[25],"appear":[26],"or":[27],"speak":[28],"video.":[31],"The":[32],"contributions":[33],"are":[34],"twofolds.":[35],"First,":[36],"we":[37,83],"formulate":[38],"within":[41],"a":[42,73,90],"novel":[43],"CRF":[44],"framework":[45,130],"that":[46,92,113,128],"simultaneously":[47],"performs":[48],"AV":[50,59,76,87],"association":[51,80,88,118],"face":[55],"clusters":[56],"to":[57,115,133],"build":[58],"models,":[61],"joint":[64],"segmentation":[65],"audio":[68],"visual":[70,104],"streams":[71],"using":[72],"set":[74],"cues":[77],"their":[79],"strength.":[81],"Secondly,":[82],"use":[84],"for":[85,139],"this":[86],"strength":[89],"score":[91],"does":[93],"not":[94],"only":[95],"rely":[96],"on":[97,102,121],"lips":[98],"activity,":[99],"but":[100],"also":[101],"contextual":[103],"information":[105],"(face":[106],"size,":[107],"position,":[108],"number":[109],"detected":[111],"faces,...)":[112],"leads":[114],"more":[116],"reliable":[117],"measures.":[119],"Experiments":[120],"6":[122],"hours":[123],"data":[126],"show":[127],"our":[129],"is":[131],"able":[132],"improve":[134],"AV-person":[136],"especially":[138],"speaker":[140],"segments":[141],"erroneously":[142],"labeled":[143],"mono-modal":[146],"case.":[147]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":5},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
