{"id":"https://openalex.org/W4308097564","doi":"https://doi.org/10.1109/euvip53989.2022.9922810","title":"Active Speaker Recognition using Cross Attention Audio-Video Fusion","display_name":"Active Speaker Recognition using Cross Attention Audio-Video Fusion","publication_year":2022,"publication_date":"2022-09-11","ids":{"openalex":"https://openalex.org/W4308097564","doi":"https://doi.org/10.1109/euvip53989.2022.9922810"},"language":"en","primary_location":{"id":"doi:10.1109/euvip53989.2022.9922810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/euvip53989.2022.9922810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 10th European Workshop on Visual Information Processing (EUVIP)","raw_type":"proceedings-article"},"type":"preprint","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":["University \"Politehnica\" of Bucharest,Department of Telecommunications, Faculty of ETTI,Romania","UPB - University Politehnica of Bucharest [Romania] (Splaiul Independentei nr. 313, sector 6, Bucuresti\r\nCP 060042\r\nROUMANIE - Romania)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University \"Politehnica\" of Bucharest,Department of Telecommunications, Faculty of ETTI,Romania","institution_ids":["https://openalex.org/I61641377"]},{"raw_affiliation_string":"UPB - University Politehnica of Bucharest [Romania] (Splaiul Independentei nr. 313, sector 6, Bucuresti\r\nCP 060042\r\nROUMANIE - Romania)","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008070329","display_name":"Tapu Ruxandra","orcid":null},"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"]},{"id":"https://openalex.org/I4387153010","display_name":"Telecom SudParis","ror":"https://ror.org/05xvk4r52","country_code":"FR","type":"education","lineage":["https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4387153010"]}],"countries":["FR","RO"],"is_corresponding":false,"raw_author_name":"Tapu Ruxandra","raw_affiliation_strings":["Institut Polytechnique de Paris, Télécom SudParis,ARTEMIS Department,Évry,France,91000","ARMEDIA-SAMOVAR - ARMEDIA (TELECOM Sudparis\r\n 9 rue Charles Fourier\r\n 91011 EVRY - France)","UPB - University Politehnica of Bucharest [Romania] (Splaiul Independentei nr. 313, sector 6, Bucuresti\r\nCP 060042\r\nROUMANIE - Romania)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris, Télécom SudParis,ARTEMIS Department,Évry,France,91000","institution_ids":[]},{"raw_affiliation_string":"ARMEDIA-SAMOVAR - ARMEDIA (TELECOM Sudparis\r\n 9 rue Charles Fourier\r\n 91011 EVRY - France)","institution_ids":["https://openalex.org/I4387153010"]},{"raw_affiliation_string":"UPB - University Politehnica of Bucharest [Romania] (Splaiul Independentei nr. 313, sector 6, Bucuresti\r\nCP 060042\r\nROUMANIE - Romania)","institution_ids":["https://openalex.org/I61641377"]}]}],"institutions":[],"countries_distinct_count":2,"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":0.8927,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.72803871,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9907000064849854,"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":0.9526000022888184,"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":0.8412379622459412},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5848545432090759},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5457701683044434},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5442585349082947},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5105031728744507},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4875635504722595},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4455549716949463},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4211016893386841}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8412379622459412},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5848545432090759},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5457701683044434},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5442585349082947},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5105031728744507},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4875635504722595},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4455549716949463},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4211016893386841},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/euvip53989.2022.9922810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/euvip53989.2022.9922810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 10th European Workshop on Visual Information Processing (EUVIP)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-03937091v1","is_oa":false,"landing_page_url":"https://hal.science/hal-03937091","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":"2022 10th European Workshop on Visual Information Processing (EUVIP), Sep 2022, Lisbon, Portugal. pp.1-6, ⟨10.1109/EUVIP53989.2022.9922810⟩","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1964448421","https://openalex.org/W2001342242","https://openalex.org/W2029848040","https://openalex.org/W2050968192","https://openalex.org/W2092206588","https://openalex.org/W2108598243","https://openalex.org/W2149060028","https://openalex.org/W2194775991","https://openalex.org/W2325939864","https://openalex.org/W2703895418","https://openalex.org/W2766925079","https://openalex.org/W2768859775","https://openalex.org/W2789824578","https://openalex.org/W2890000801","https://openalex.org/W2912083425","https://openalex.org/W2916104401","https://openalex.org/W2959980708","https://openalex.org/W2963566548","https://openalex.org/W2964095005","https://openalex.org/W3010034298","https://openalex.org/W3016092640","https://openalex.org/W3105099157","https://openalex.org/W3160183718","https://openalex.org/W3162024001","https://openalex.org/W6620707391","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W2185469136","https://openalex.org/W4306353150","https://openalex.org/W8219677","https://openalex.org/W4293226380","https://openalex.org/W2168054807","https://openalex.org/W2058990474","https://openalex.org/W2026860389","https://openalex.org/W2043363698","https://openalex.org/W4301143707","https://openalex.org/W2952745240"],"abstract_inverted_index":{"The":[0,147,163],"audio-video":[1],"based":[2,69],"multimodal":[3],"active":[4,136],"speaker":[5,137],"recognition":[6],"from":[7,89],"video":[8,32,45,101],"streams":[9],"has":[10],"attracted":[11],"the":[12,15,36,51,78,95,111,126,132,135,143,155,166],"attention":[13,67,119],"of":[14,23,35,98,113,134,165,179],"scientific":[16],"community":[17],"due":[18],"to":[19,76,85,116,140,161],"its":[20],"wide":[21],"range":[22],"applications,":[24],"such":[25],"as":[26],"human":[27],"centered":[28],"computing":[29],"or":[30,41],"semantic":[31],"understanding.":[33],"Most":[34],"existing":[37],"techniques":[38],"use":[39],"early":[40],"late":[42],"fusion":[43],"audio-":[44],"(A-V)":[46],"strategies":[47],"without":[48],"considering":[49],"completely":[50],"inter-":[52],"modal":[53],"and":[54,72,84,100,138,175],"intra-modal":[55],"interactions.":[56],"In":[57],"this":[58,60],"context,":[59],"research":[61],"work":[62],"proposes":[63],"a":[64,117],"novel":[65],"cross-modal":[66],"mechanism":[68],"on":[70,151],"visual":[71],"audio":[73,99],"modalities":[74,115],"designed":[75],"capture":[77],"complex":[79],"spatiotemporal":[80],"relationship":[81],"between":[82],"descriptors":[83],"fuse":[86],"complementary":[87],"information":[88],"multiple":[90],"modalities.":[91],"First,":[92],"we":[93,109,130],"perform":[94],"representation":[96],"learning":[97],"using":[102],"deep":[103],"convolutional":[104],"neural":[105],"networks":[106],"(CNNs).":[107],"Secondly,":[108],"feed":[110],"features":[112,124],"both":[114],"cross":[118],"block":[120],"by":[121],"fusing":[122],"A-V":[123],"at":[125],"model":[127],"level.":[128],"Finally,":[129],"obtain":[131],"identity":[133],"associate":[139],"each":[141],"character":[142],"corresponding":[144],"subtitle":[145],"segment.":[146],"experimental":[148],"evaluation":[149],"performed":[150],"30":[152],"videos":[153],"validates":[154],"approach":[156],"with":[157],"average":[158],"F1-scores":[159],"superior":[160],"88%.":[162],"effectiveness":[164],"proposed":[167],"system":[168],"architecture":[169],"is":[170],"compared":[171],"against":[172],"state-of-the-art":[173],"methods":[174],"demonstrates":[176],"accuracy":[177],"gains":[178],"more":[180],"than":[181],"3%.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}