{"id":"https://openalex.org/W1595802121","doi":"https://doi.org/10.1109/icassp.2015.7178882","title":"Audiovisual speaker diarization of TV series","display_name":"Audiovisual speaker diarization of TV series","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1595802121","doi":"https://doi.org/10.1109/icassp.2015.7178882","mag":"1595802121"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178882","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178882","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1812.07205","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074844950","display_name":"Xavier Bost","orcid":"https://orcid.org/0000-0002-5624-8721"},"institutions":[{"id":"https://openalex.org/I198415970","display_name":"Universit\u00e9 d'Avignon et des Pays de Vaucluse","ror":"https://ror.org/00mfpxb84","country_code":"FR","type":"education","lineage":["https://openalex.org/I198415970"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Xavier Bost","raw_affiliation_strings":["LIA, University of Avignon, Avignon, France","LIA, University of Avignon, 339 chemin des Meinajari\u00e8s, 84000, France"],"affiliations":[{"raw_affiliation_string":"LIA, University of Avignon, Avignon, France","institution_ids":["https://openalex.org/I198415970"]},{"raw_affiliation_string":"LIA, University of Avignon, 339 chemin des Meinajari\u00e8s, 84000, France","institution_ids":["https://openalex.org/I198415970"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050508708","display_name":"Georges Linar\u00e8s","orcid":"https://orcid.org/0000-0001-8049-9056"},"institutions":[{"id":"https://openalex.org/I198415970","display_name":"Universit\u00e9 d'Avignon et des Pays de Vaucluse","ror":"https://ror.org/00mfpxb84","country_code":"FR","type":"education","lineage":["https://openalex.org/I198415970"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Georges Linares","raw_affiliation_strings":["LIA, University of Avignon, Avignon, France","LIA, University of Avignon, 339 chemin des Meinajari\u00e8s, 84000, France"],"affiliations":[{"raw_affiliation_string":"LIA, University of Avignon, Avignon, France","institution_ids":["https://openalex.org/I198415970"]},{"raw_affiliation_string":"LIA, University of Avignon, 339 chemin des Meinajari\u00e8s, 84000, France","institution_ids":["https://openalex.org/I198415970"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014362095","display_name":"Serigne Gu\u00e8ye","orcid":"https://orcid.org/0000-0001-7217-8543"},"institutions":[{"id":"https://openalex.org/I198415970","display_name":"Universit\u00e9 d'Avignon et des Pays de Vaucluse","ror":"https://ror.org/00mfpxb84","country_code":"FR","type":"education","lineage":["https://openalex.org/I198415970"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Serigne Gueye","raw_affiliation_strings":["LIA, University of Avignon, Avignon, France","LIA, University of Avignon, 339 chemin des Meinajari\u00e8s, 84000, France"],"affiliations":[{"raw_affiliation_string":"LIA, University of Avignon, Avignon, France","institution_ids":["https://openalex.org/I198415970"]},{"raw_affiliation_string":"LIA, University of Avignon, 339 chemin des Meinajari\u00e8s, 84000, France","institution_ids":["https://openalex.org/I198415970"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5074844950"],"corresponding_institution_ids":["https://openalex.org/I198415970"],"apc_list":null,"apc_paid":null,"fwci":2.3167,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.88654566,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"24","issue":null,"first_page":"4799","last_page":"4803"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9993000030517578,"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":0.9990000128746033,"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":0.8937534093856812},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7492460012435913},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6447650194168091},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5788041353225708},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5561860799789429},{"id":"https://openalex.org/keywords/intonation","display_name":"Intonation (linguistics)","score":0.5387957692146301},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5149950981140137},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.4842914938926697},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4483107030391693},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43269675970077515},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33578652143478394},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.21642401814460754}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8937534093856812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7492460012435913},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6447650194168091},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5788041353225708},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5561860799789429},{"id":"https://openalex.org/C2781045179","wikidata":"https://www.wikidata.org/wiki/Q5576720","display_name":"Intonation (linguistics)","level":2,"score":0.5387957692146301},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5149950981140137},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.4842914938926697},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4483107030391693},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43269675970077515},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33578652143478394},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.21642401814460754},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp.2015.7178882","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178882","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1812.07205","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1812.07205","pdf_url":"https://arxiv.org/pdf/1812.07205","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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-01313080v1","is_oa":false,"landing_page_url":"https://hal.archives-ouvertes.fr/hal-01313080","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Interspeech","raw_type":"\\ninfo:eu-repo/semantics/conferenceObject\\n"},{"id":"pmh:oai:HAL:hal-01313080v2","is_oa":true,"landing_page_url":"https://hal.science/hal-01313080","pdf_url":null,"source":{"id":"https://openalex.org/S4406922276","display_name":"INRIA a CCSD electronic archive server","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr 2015, Brisbane, Australia. pp.4799-4803, ⟨10.1109/ICASSP.2015.7178882⟩","raw_type":"Conference papers"},{"id":"pmh:oai:HAL:hal-02463990v1","is_oa":false,"landing_page_url":"https://hal.science/hal-02463990","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr 2015, Brisbane, Australia. IEEE, pp.4799-4803, 2015, ⟨10.1109/ICASSP.2015.7178882⟩","raw_type":"Proceedings"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1812.07205","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1812.07205","pdf_url":"https://arxiv.org/pdf/1812.07205","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"score":0.4300000071525574,"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/W371407676","https://openalex.org/W1589339348","https://openalex.org/W1977991519","https://openalex.org/W2038162002","https://openalex.org/W2097470427","https://openalex.org/W2097553100","https://openalex.org/W2102750402","https://openalex.org/W2109456962","https://openalex.org/W2115175902","https://openalex.org/W2127859636","https://openalex.org/W2140752593","https://openalex.org/W2150769028","https://openalex.org/W2155414712","https://openalex.org/W2161827960","https://openalex.org/W2396559392","https://openalex.org/W2399762392","https://openalex.org/W2748231125","https://openalex.org/W4299302339","https://openalex.org/W4300520566","https://openalex.org/W4301688325","https://openalex.org/W6627081022","https://openalex.org/W6635144179","https://openalex.org/W6712475220"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4403618900","https://openalex.org/W36105149","https://openalex.org/W2545131480","https://openalex.org/W4401661962","https://openalex.org/W4247736853","https://openalex.org/W1521049138","https://openalex.org/W2997340161","https://openalex.org/W1589374915","https://openalex.org/W2136038945"],"abstract_inverted_index":{"Speaker":[0],"diarization":[1,37,67,82],"may":[2,28],"be":[3],"difficult":[4],"to":[5,9,64,107,126,131],"achieve":[6],"when":[7],"applied":[8],"narrative":[10],"films,":[11],"where":[12],"speakers":[13],"usually":[14],"talk":[15],"in":[16,26],"adverse":[17],"acoustic":[18],"conditions:":[19],"background":[20],"music,":[21],"sound":[22],"effects,":[23],"wide":[24],"variations":[25],"intonation":[27],"hide":[29],"the":[30,42,52,76,90,95,103],"inter-speaker":[31],"variability":[32],"and":[33,78],"make":[34],"audio-based":[35],"speaker":[36,66,81],"approaches":[38],"error":[39],"prone.":[40],"On":[41],"other":[43],"hand,":[44],"such":[45,122],"fictional":[46,127],"movies":[47],"exhibit":[48],"strong":[49],"regularities":[50],"at":[51],"image":[53],"level,":[54],"particularly":[55],"within":[56,68],"dialogue":[57,69],"scenes.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62],"propose":[63],"perform":[65],"scenes":[70],"of":[71,94,109],"TV":[72],"series":[73],"by":[74,86,120,135],"combining":[75],"audio":[77],"video":[79],"modalities:":[80],"is":[83],"first":[84],"performed":[85],"using":[87],"each":[88],"modality;":[89],"two":[91],"resulting":[92],"partitions":[93],"instance":[96],"set":[97],"are":[98,114],"then":[99],"optimally":[100],"matched,":[101],"before":[102],"remaining":[104],"instances,":[105],"corresponding":[106],"cases":[108],"disagreement":[110],"between":[111],"both":[112],"modalities,":[113],"finally":[115],"processed.":[116],"The":[117],"results":[118],"obtained":[119,134],"applying":[121],"a":[123,138],"multi-modal":[124],"approach":[125],"films":[128],"turn":[129],"out":[130],"outperform":[132],"those":[133],"relying":[136],"on":[137],"single":[139],"modality.":[140]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}