{"id":"https://openalex.org/W4387757629","doi":"https://doi.org/10.1109/access.2023.3325474","title":"Modeling Long-Term Multimodal Representations for Active Speaker Detection With Spatio-Positional Encoder","display_name":"Modeling Long-Term Multimodal Representations for Active Speaker Detection With Spatio-Positional Encoder","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4387757629","doi":"https://doi.org/10.1109/access.2023.3325474"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3325474","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2023.3325474","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10287283.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10287283.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010710953","display_name":"Minyoung Kyoung","orcid":"https://orcid.org/0009-0006-2814-9386"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minyoung Kyoung","raw_affiliation_strings":["Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0006-2814-9386","affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034406505","display_name":"Hwa Jeon Song","orcid":"https://orcid.org/0000-0002-8216-4812"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hwa Jeon Song","raw_affiliation_strings":["Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-8216-4812","affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I142401562"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I142401562"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.174,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.42404372,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"11","issue":null,"first_page":"116561","last_page":"116569"},"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":0.9929999709129333,"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":0.983299970626831,"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":0.871120810508728},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7317023277282715},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6048787832260132},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5800150036811829},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.551249623298645},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.45227015018463135},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.42931559681892395},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4255208373069763},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.42084434628486633},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3809962272644043},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3578304648399353},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3354681730270386}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.871120810508728},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7317023277282715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6048787832260132},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5800150036811829},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.551249623298645},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.45227015018463135},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.42931559681892395},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4255208373069763},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.42084434628486633},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3809962272644043},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3578304648399353},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3354681730270386},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2023.3325474","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2023.3325474","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10287283.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:a7ea5b0d83074c6c8bd508db958b69cb","is_oa":true,"landing_page_url":"https://doaj.org/article/a7ea5b0d83074c6c8bd508db958b69cb","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 11, Pp 116561-116569 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3325474","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2023.3325474","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10287283.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5400000214576721}],"awards":[{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G8472331835","display_name":null,"funder_award_id":"2022-0-00989","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387757629.pdf","grobid_xml":"https://content.openalex.org/works/W4387757629.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W2054852564","https://openalex.org/W2138761194","https://openalex.org/W2168996682","https://openalex.org/W2316138215","https://openalex.org/W2550543432","https://openalex.org/W2752782242","https://openalex.org/W2759799350","https://openalex.org/W2890952074","https://openalex.org/W2899771611","https://openalex.org/W2936774411","https://openalex.org/W2964110616","https://openalex.org/W2964171275","https://openalex.org/W2972729214","https://openalex.org/W2981857663","https://openalex.org/W3016098309","https://openalex.org/W3034702511","https://openalex.org/W3038871978","https://openalex.org/W3097777922","https://openalex.org/W3135222947","https://openalex.org/W3162475350","https://openalex.org/W3163287738","https://openalex.org/W3169351047","https://openalex.org/W3172472082","https://openalex.org/W3189964604","https://openalex.org/W3206008172","https://openalex.org/W3207207922","https://openalex.org/W4214701094","https://openalex.org/W4226191785","https://openalex.org/W4286378963","https://openalex.org/W4291920479","https://openalex.org/W4312268709","https://openalex.org/W4312466984","https://openalex.org/W4385245566","https://openalex.org/W4386065462","https://openalex.org/W4386075783","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6739901393","https://openalex.org/W6756040250"],"related_works":["https://openalex.org/W2185469136","https://openalex.org/W4306353150","https://openalex.org/W8219677","https://openalex.org/W2168054807","https://openalex.org/W2058990474","https://openalex.org/W2026860389","https://openalex.org/W2043363698","https://openalex.org/W3207883763","https://openalex.org/W4386977688","https://openalex.org/W4390516098"],"abstract_inverted_index":{"In":[0,22],"this":[1],"study,":[2],"we":[3,42,60,82,107],"present":[4,83],"an":[5,84],"end-to-end":[6],"framework":[7,111,124],"for":[8],"active":[9],"speaker":[10],"detection":[11],"to":[12,24,65],"achieve":[13],"robust":[14],"performance":[15],"in":[16,38,77],"challenging":[17,118],"scenarios":[18],"with":[19],"multiple":[20],"speakers.":[21],"contrast":[23],"recent":[25,114],"approaches,":[26],"which":[27],"rely":[28],"heavily":[29],"on":[30,49,103,137],"the":[31,50,68,90,104,122,127],"visual":[32,53,98,132],"relational":[33],"context":[34],"between":[35,95],"all":[36],"speakers":[37],"a":[39,56,62,78],"video":[40,79],"frame,":[41],"propose":[43,61],"collaboratively":[44],"learning":[45],"multimodal":[46,86],"representations":[47],"based":[48],"audio":[51,96],"and":[52,97,131],"signals":[54],"of":[55,70],"single":[57],"candidate.":[58],"Firstly,":[59],"spatio-positional":[63],"encoder":[64],"effectively":[66],"address":[67],"problem":[69],"false":[71],"detections":[72],"caused":[73],"by":[74],"indiscernible":[75],"faces":[76],"frame.":[80],"Secondly,":[81],"efficient":[85],"approach":[87],"that":[88,109],"models":[89],"long-term":[91],"temporal":[92],"contextual":[93],"interactions":[94],"modalities.":[99],"Through":[100],"extensive":[101],"experiments":[102],"AVA-ActiveSpeaker":[105],"dataset,":[106],"demonstrate":[108],"our":[110],"notably":[112],"outperforms":[113],"state-of-the-art":[115],"approaches":[116],"under":[117],"multi-speaker":[119],"settings.":[120],"Additionally,":[121],"proposed":[123],"significantly":[125],"improves":[126],"robustness":[128],"against":[129],"auditory":[130],"noise":[133],"interference":[134],"without":[135],"relying":[136],"pre-trained":[138],"networks":[139],"or":[140],"hand-crafted":[141],"training":[142],"strategies.":[143]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}