{"id":"https://openalex.org/W2288294901","doi":"https://doi.org/10.1109/asru.2015.7404820","title":"Multimodal embedding fusion for robust speaker role recognition in video broadcast","display_name":"Multimodal embedding fusion for robust speaker role recognition in video broadcast","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2288294901","doi":"https://doi.org/10.1109/asru.2015.7404820","mag":"2288294901"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2015.7404820","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404820","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-01475413","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004769977","display_name":"Michael Rouvier","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I21491767","display_name":"Aix-Marseille Universit\u00e9","ror":"https://ror.org/035xkbk20","country_code":"FR","type":"education","lineage":["https://openalex.org/I21491767"]},{"id":"https://openalex.org/I4210115196","display_name":"Laboratoire d\u2019Informatique Fondamentale de Marseille","ror":"https://ror.org/022my8t07","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I21491767","https://openalex.org/I4210115196","https://openalex.org/I4210142724","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Michael Rouvier","raw_affiliation_strings":["Aix-Marseille Universit\u00e9, CNRS, LIF, Marseille, France","Laboratoire d'informatique Fondamentale de Marseille"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aix-Marseille Universit\u00e9, CNRS, LIF, Marseille, France","institution_ids":["https://openalex.org/I21491767","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Laboratoire d'informatique Fondamentale de Marseille","institution_ids":["https://openalex.org/I4210115196"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066212734","display_name":"Sebastien Delecraz","orcid":"https://orcid.org/0000-0001-5977-4893"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I21491767","display_name":"Aix-Marseille Universit\u00e9","ror":"https://ror.org/035xkbk20","country_code":"FR","type":"education","lineage":["https://openalex.org/I21491767"]},{"id":"https://openalex.org/I4210115196","display_name":"Laboratoire d\u2019Informatique Fondamentale de Marseille","ror":"https://ror.org/022my8t07","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I21491767","https://openalex.org/I4210115196","https://openalex.org/I4210142724","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sebastien Delecraz","raw_affiliation_strings":["Aix-Marseille Universit\u00e9, CNRS, LIF, Marseille, France","Laboratoire d'informatique Fondamentale de Marseille"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aix-Marseille Universit\u00e9, CNRS, LIF, Marseille, France","institution_ids":["https://openalex.org/I21491767","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Laboratoire d'informatique Fondamentale de Marseille","institution_ids":["https://openalex.org/I4210115196"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071505335","display_name":"Beno\u00eet Favre","orcid":"https://orcid.org/0000-0002-9777-4613"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I21491767","display_name":"Aix-Marseille Universit\u00e9","ror":"https://ror.org/035xkbk20","country_code":"FR","type":"education","lineage":["https://openalex.org/I21491767"]},{"id":"https://openalex.org/I4210115196","display_name":"Laboratoire d\u2019Informatique Fondamentale de Marseille","ror":"https://ror.org/022my8t07","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I21491767","https://openalex.org/I4210115196","https://openalex.org/I4210142724","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Benoit Favre","raw_affiliation_strings":["Aix-Marseille Universit\u00e9, CNRS, LIF, Marseille, France","Traitement Automatique du Langage Ecrit et Parl\u00e9","Laboratoire d'informatique Fondamentale de Marseille"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aix-Marseille Universit\u00e9, CNRS, LIF, Marseille, France","institution_ids":["https://openalex.org/I21491767","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Traitement Automatique du Langage Ecrit et Parl\u00e9","institution_ids":[]},{"raw_affiliation_string":"Laboratoire d'informatique Fondamentale de Marseille","institution_ids":["https://openalex.org/I4210115196"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079440514","display_name":"Meriem Bendris","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I21491767","display_name":"Aix-Marseille Universit\u00e9","ror":"https://ror.org/035xkbk20","country_code":"FR","type":"education","lineage":["https://openalex.org/I21491767"]},{"id":"https://openalex.org/I4210115196","display_name":"Laboratoire d\u2019Informatique Fondamentale de Marseille","ror":"https://ror.org/022my8t07","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I21491767","https://openalex.org/I4210115196","https://openalex.org/I4210142724","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Meriem Bendris","raw_affiliation_strings":["Aix-Marseille Universit\u00e9, CNRS, LIF, Marseille, France","Laboratoire d'informatique Fondamentale de Marseille"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aix-Marseille Universit\u00e9, CNRS, LIF, Marseille, France","institution_ids":["https://openalex.org/I21491767","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Laboratoire d'informatique Fondamentale de Marseille","institution_ids":["https://openalex.org/I4210115196"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110498175","display_name":"Fr\u00e9d\u00e9ric B\u00e9chet","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I21491767","display_name":"Aix-Marseille Universit\u00e9","ror":"https://ror.org/035xkbk20","country_code":"FR","type":"education","lineage":["https://openalex.org/I21491767"]},{"id":"https://openalex.org/I4210115196","display_name":"Laboratoire d\u2019Informatique Fondamentale de Marseille","ror":"https://ror.org/022my8t07","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I21491767","https://openalex.org/I4210115196","https://openalex.org/I4210142724","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Frederic Bechet","raw_affiliation_strings":["Aix-Marseille Universit\u00e9, CNRS, LIF, Marseille, France","Laboratoire d'informatique Fondamentale de Marseille"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aix-Marseille Universit\u00e9, CNRS, LIF, Marseille, France","institution_ids":["https://openalex.org/I21491767","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Laboratoire d'informatique Fondamentale de Marseille","institution_ids":["https://openalex.org/I4210115196"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4452,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78601404,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"383","last_page":"389"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9897000193595886,"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/computer-science","display_name":"Computer science","score":0.7772405743598938},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6767450571060181},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6340686082839966},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6251122951507568},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5445639491081238},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5324372053146362},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5216893553733826},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4870172142982483},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.4866202771663666},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4278873801231384},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4266960024833679},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33980047702789307},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3369932174682617},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0748525857925415}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7772405743598938},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6767450571060181},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6340686082839966},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6251122951507568},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5445639491081238},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5324372053146362},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5216893553733826},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4870172142982483},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.4866202771663666},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4278873801231384},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4266960024833679},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33980047702789307},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3369932174682617},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0748525857925415},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asru.2015.7404820","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404820","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01475413v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01475413","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":"Automatic Speech Recognition and Understanding, Dec 2015, Scottsdale, United States. pp.383 - 389, &#x27E8;10.1109/ASRU.2015.7404820&#x27E9;","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01475413v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01475413","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":"Automatic Speech Recognition and Understanding, Dec 2015, Scottsdale, United States. pp.383 - 389, &#x27E8;10.1109/ASRU.2015.7404820&#x27E9;","raw_type":"Conference papers"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W37854943","https://openalex.org/W98255950","https://openalex.org/W157724941","https://openalex.org/W163811496","https://openalex.org/W302849860","https://openalex.org/W1524333225","https://openalex.org/W1532958172","https://openalex.org/W1589339348","https://openalex.org/W1614298861","https://openalex.org/W1631260214","https://openalex.org/W1832693441","https://openalex.org/W1962262887","https://openalex.org/W1964428975","https://openalex.org/W2033620616","https://openalex.org/W2037740282","https://openalex.org/W2082112386","https://openalex.org/W2117539524","https://openalex.org/W2140381322","https://openalex.org/W2143229091","https://openalex.org/W2153875174","https://openalex.org/W2155893237","https://openalex.org/W2161448797","https://openalex.org/W2163605009","https://openalex.org/W2184188583","https://openalex.org/W2198484938","https://openalex.org/W2250641567","https://openalex.org/W2250742840","https://openalex.org/W2397622291","https://openalex.org/W2403310668","https://openalex.org/W2404901536","https://openalex.org/W2406418155","https://openalex.org/W2963871344","https://openalex.org/W4214784823","https://openalex.org/W4245862033","https://openalex.org/W6604056254","https://openalex.org/W6606390406","https://openalex.org/W6631362777","https://openalex.org/W6636510571","https://openalex.org/W6636811518","https://openalex.org/W6641205205","https://openalex.org/W6686207219","https://openalex.org/W6691613585","https://openalex.org/W6712379007","https://openalex.org/W6714078479"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"Person":[0],"role":[1,27,32,88],"recognition":[2,89],"in":[3,7,53,90],"video":[4,50],"broadcasts":[5],"consists":[6],"classifying":[8],"people":[9],"into":[10],"roles":[11],"such":[12],"as":[13],"anchor,":[14],"journalist,":[15],"guest,":[16],"etc.":[17],"Existing":[18],"approaches":[19,60],"mostly":[20],"consider":[21],"one":[22],"modality,":[23],"either":[24],"audio":[25],"(speaker":[26],"recognition)":[28],"or":[29],"image":[30,83],"(shot":[31],"recognition),":[33],"firstly":[34],"because":[35,44],"of":[36,45,48,79,108,124],"the":[37,46,62,113,118,122,125,131,137],"non-synchrony":[38],"between":[39],"both":[40,54],"modalities,":[41],"and":[42,70,82,100,135],"secondly":[43],"lack":[47],"a":[49,76,103],"corpus":[51,111,120],"annotated":[52],"modalities.":[55],"Deep":[56],"Neural":[57],"Networks":[58],"(DNN)":[59],"offer":[61],"ability":[63],"to":[64,130,136],"learn":[65],"simultaneously":[66],"feature":[67],"representations":[68],"(embeddings)":[69],"classification":[71],"functions.":[72],"This":[73],"paper":[74],"presents":[75],"multimodal":[77],"fusion":[78,128,140],"audio,":[80],"text":[81],"embeddings":[84,94,126,133],"spaces":[85],"for":[86,112],"speaker":[87],"asynchronous":[91],"data.":[92],"Monomodal":[93],"are":[95],"trained":[96],"on":[97,105,117],"exogenous":[98],"data":[99],"fine-tuned":[101],"using":[102],"DNN":[104],"70":[106],"hours":[107],"French":[109],"Broadcasts":[110],"target":[114],"task.":[115],"Experiments":[116],"REPERE":[119],"show":[121],"benefit":[123],"level":[127],"compared":[129],"monomodal":[132],"systems":[134],"standard":[138],"late":[139],"method.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
