{"id":"https://openalex.org/W4392248695","doi":"https://doi.org/10.1109/icce59016.2024.10444380","title":"Multimodal active speaker detection using cross-attention and contextual information","display_name":"Multimodal active speaker detection using cross-attention and contextual information","publication_year":2024,"publication_date":"2024-01-06","ids":{"openalex":"https://openalex.org/W4392248695","doi":"https://doi.org/10.1109/icce59016.2024.10444380"},"language":"en","primary_location":{"id":"doi:10.1109/icce59016.2024.10444380","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icce59016.2024.10444380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Consumer Electronics (ICCE)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073509926","display_name":"Bogdan Mocanu","orcid":"https://orcid.org/0000-0002-2751-0954"},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Bogdan Mocanu","raw_affiliation_strings":["Institut Polytechnique de Paris,T&#x00E9;l&#x00E9;com SudParis, Laboratoire SAMOVAR,Evry,France","Department of Telecommunications, Faculty of ETTI, University \"Politehnica\" of Bucharest, Romania"],"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,T&#x00E9;l&#x00E9;com SudParis, Laboratoire SAMOVAR,Evry,France","institution_ids":[]},{"raw_affiliation_string":"Department of Telecommunications, Faculty of ETTI, University \"Politehnica\" of Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025204322","display_name":"Ruxandra \u021aapu","orcid":"https://orcid.org/0000-0003-3170-4150"},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Ruxandra Tapu","raw_affiliation_strings":["Institut Polytechnique de Paris,T&#x00E9;l&#x00E9;com SudParis, Laboratoire SAMOVAR,Evry,France","Department of Telecommunications, Faculty of ETTI, University \"Politehnica\" of Bucharest, Romania"],"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,T&#x00E9;l&#x00E9;com SudParis, Laboratoire SAMOVAR,Evry,France","institution_ids":[]},{"raw_affiliation_string":"Department of Telecommunications, Faculty of ETTI, University \"Politehnica\" of Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5073509926"],"corresponding_institution_ids":["https://openalex.org/I61641377"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01975586,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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":0.9911999702453613,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7606603503227234},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5118052363395691},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36624836921691895}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7606603503227234},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5118052363395691},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36624836921691895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icce59016.2024.10444380","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icce59016.2024.10444380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Consumer Electronics (ICCE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2100561338","https://openalex.org/W2154636774","https://openalex.org/W2890952074","https://openalex.org/W3016098309","https://openalex.org/W3092990874","https://openalex.org/W3162475350","https://openalex.org/W3172472082","https://openalex.org/W3181255780","https://openalex.org/W4221154746","https://openalex.org/W4386075783","https://openalex.org/W6675048546","https://openalex.org/W6798523648"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"An":[0],"active":[1],"speaker":[2],"detection":[3],"(ASD)":[4],"framework":[5],"is":[6,14],"aimed":[7],"to":[8,43],"identify":[9],"whether":[10],"an":[11,77],"on-screen":[12],"person":[13],"speaking":[15],"or":[16],"not":[17],"in":[18],"each":[19],"frame":[20],"of":[21,36,73,81],"the":[22,49,54,57,61,64,71,74],"video.":[23],"In":[24],"this":[25],"paper,":[26],"we":[27],"introduce":[28],"a":[29,40],"novel":[30],"ASD":[31],"system":[32,55],"by":[33],"mindful":[34],"integration":[35],"audio-video":[37],"cues":[38],"through":[39],"cross-attention":[41],"module":[42],"capture":[44],"inter-modal":[45],"information":[46],"while":[47],"retaining":[48],"distinct":[50],"intra-modal":[51],"features.":[52],"Furthermore,":[53],"models":[56],"inter-speaker":[58],"relations":[59],"between":[60],"speakers":[62],"within":[63],"same":[65],"scene.":[66],"The":[67],"experimental":[68],"evaluation":[69],"validates":[70],"effectiveness":[72],"approach,":[75],"achieving":[76],"average":[78],"mAP":[79],"score":[80],"94.8%.":[82]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}
