{"id":"https://openalex.org/W2004419043","doi":"https://doi.org/10.1109/slt.2014.7078606","title":"Constrained speaker diarization of TV series based on visual patterns","display_name":"Constrained speaker diarization of TV series based on visual patterns","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2004419043","doi":"https://doi.org/10.1109/slt.2014.7078606","mag":"2004419043"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2014.7078606","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078606","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1812.07209","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xavier Bost","orcid":null},"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"],"affiliations":[{"raw_affiliation_string":"LIA, University of Avignon, Avignon, France","institution_ids":["https://openalex.org/I198415970"]}]},{"author_position":"last","author":{"id":null,"display_name":"Georges Linares","orcid":null},"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"],"affiliations":[{"raw_affiliation_string":"LIA, University of Avignon, Avignon, France","institution_ids":["https://openalex.org/I198415970"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I198415970"],"apc_list":null,"apc_paid":null,"fwci":1.1803,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78450197,"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":"390","last_page":"395"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9993000030517578,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9973000288009644,"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":0.8837000131607056},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6568999886512756},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5795999765396118},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.49160000681877136},{"id":"https://openalex.org/keywords/series","display_name":"Series (stratigraphy)","score":0.38960000872612},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3578999936580658}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8837000131607056},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6568999886512756},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6503000259399414},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6499999761581421},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5795999765396118},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.49160000681877136},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.38960000872612},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3578999936580658},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34929999709129333},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.33090001344680786},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26570001244544983}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/slt.2014.7078606","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078606","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1812.07209","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1812.07209","pdf_url":"https://arxiv.org/pdf/1812.07209","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-01957900v2","is_oa":true,"landing_page_url":"https://hal.science/hal-01957900","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":"2014 IEEE Spoken Language Technology Workshop (SLT), Dec 2014, South Lake Tahoe, United States. pp.390-395, ⟨10.1109/SLT.2014.7078606⟩","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1812.07209","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1812.07209","pdf_url":"https://arxiv.org/pdf/1812.07209","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1589339348","https://openalex.org/W1977991519","https://openalex.org/W1987971958","https://openalex.org/W2097553100","https://openalex.org/W2109456962","https://openalex.org/W2115130489","https://openalex.org/W2115175902","https://openalex.org/W2125336414","https://openalex.org/W2140752593","https://openalex.org/W2150769028","https://openalex.org/W2161827960","https://openalex.org/W2401027203","https://openalex.org/W6712967240","https://openalex.org/W6738902873"],"related_works":[],"abstract_inverted_index":{"Speaker":[0],"diarization,":[1],"usually":[2],"denoted":[3],"as":[4,73],"the":[5,44,70,76,89,103,123],"\u201cwho":[6],"spoke":[7],"when\u201d":[8],"task,":[9],"turns":[10],"out":[11],"to":[12,18,55,95,102,113,122],"be":[13,96,100],"particularly":[14],"challenging":[15],"when":[16],"applied":[17,121],"fictional":[19],"films,":[20],"where":[21],"many":[22],"characters":[23],"talk":[24],"in":[25,43,59,69,82],"various":[26],"acoustic":[27,35],"conditions":[28],"(background":[29],"music,":[30],"sound":[31],"effects...).":[32],"Despite":[33],"this":[34,48],"variability,":[36],"such":[37],"movies":[38],"exhibit":[39],"specific":[40],"visual":[41],"patterns":[42],"dialogue":[45],"scenes.":[46],"In":[47],"paper,":[49],"we":[50],"introduce":[51],"a":[52,62,83],"two-step":[53],"method":[54],"achieve":[56],"speaker":[57,63,118],"diarization":[58,64,119],"TV":[60],"series:":[61],"is":[65],"first":[66],"performed":[67],"locally":[68,93],"scenes":[71],"detected":[72],"dialogues;":[74],"then,":[75],"hypothesized":[77,94],"local":[78],"speakers":[79,92],"are":[80,111],"merged":[81],"second":[84],"agglomerative":[85],"clustering":[86],"process,":[87],"with":[88],"constraint":[90],"that":[91],"distinct":[97],"must":[98],"not":[99],"assigned":[101],"same":[104,124],"cluster.":[105],"The":[106],"performances":[107],"of":[108],"our":[109],"approach":[110],"compared":[112],"those":[114],"obtained":[115],"by":[116],"standard":[117],"tools":[120],"data.":[125]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2016-06-24T00:00:00"}