{"id":"https://openalex.org/W4317383069","doi":"https://doi.org/10.1109/robio55434.2022.10011692","title":"Real-time Architecture for Audio-Visual Active Speaker Detection","display_name":"Real-time Architecture for Audio-Visual Active Speaker Detection","publication_year":2022,"publication_date":"2022-12-05","ids":{"openalex":"https://openalex.org/W4317383069","doi":"https://doi.org/10.1109/robio55434.2022.10011692"},"language":"en","primary_location":{"id":"doi:10.1109/robio55434.2022.10011692","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/robio55434.2022.10011692","pdf_url":null,"source":{"id":"https://openalex.org/S4363607789","display_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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/A5078866305","display_name":"Min Huang","orcid":"https://orcid.org/0000-0001-6152-7912"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Min Huang","raw_affiliation_strings":["Intelligent Robotics Research Center, Zhejiang Lab and Zhejiang Engineering Research Center for Intelligent Robotics,Hangzhou,China,311100"],"affiliations":[{"raw_affiliation_string":"Intelligent Robotics Research Center, Zhejiang Lab and Zhejiang Engineering Research Center for Intelligent Robotics,Hangzhou,China,311100","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396400","display_name":"Wen Wang","orcid":"https://orcid.org/0009-0009-1644-2341"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Wang","raw_affiliation_strings":["Intelligent Robotics Research Center, Zhejiang Lab and Zhejiang Engineering Research Center for Intelligent Robotics,Hangzhou,China,311100"],"affiliations":[{"raw_affiliation_string":"Intelligent Robotics Research Center, Zhejiang Lab and Zhejiang Engineering Research Center for Intelligent Robotics,Hangzhou,China,311100","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028966460","display_name":"Zheyuan Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheyuan Lin","raw_affiliation_strings":["Intelligent Robotics Research Center, Zhejiang Lab and Zhejiang Engineering Research Center for Intelligent Robotics,Hangzhou,China,311100"],"affiliations":[{"raw_affiliation_string":"Intelligent Robotics Research Center, Zhejiang Lab and Zhejiang Engineering Research Center for Intelligent Robotics,Hangzhou,China,311100","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090074861","display_name":"Fiseha B. Tesema","orcid":"https://orcid.org/0000-0002-7472-4007"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fiseha B. Tesema","raw_affiliation_strings":["Intelligent Robotics Research Center, Zhejiang Lab and Zhejiang Engineering Research Center for Intelligent Robotics,Hangzhou,China,311100"],"affiliations":[{"raw_affiliation_string":"Intelligent Robotics Research Center, Zhejiang Lab and Zhejiang Engineering Research Center for Intelligent Robotics,Hangzhou,China,311100","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060009985","display_name":"Shanshan Ji","orcid":"https://orcid.org/0000-0001-7944-8155"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanshan Ji","raw_affiliation_strings":["Intelligent Robotics Research Center, Zhejiang Lab and Zhejiang Engineering Research Center for Intelligent Robotics,Hangzhou,China,311100"],"affiliations":[{"raw_affiliation_string":"Intelligent Robotics Research Center, Zhejiang Lab and Zhejiang Engineering Research Center for Intelligent Robotics,Hangzhou,China,311100","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010340252","display_name":"Jason Gu","orcid":"https://orcid.org/0000-0002-7626-1077"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jason Gu","raw_affiliation_strings":["Dalhousie University,Department of Electrical And Computer Engineering,Canada","Department of Electrical And Computer Engineering, Dalhousie University, Canada"],"affiliations":[{"raw_affiliation_string":"Dalhousie University,Department of Electrical And Computer Engineering,Canada","institution_ids":["https://openalex.org/I129902397"]},{"raw_affiliation_string":"Department of Electrical And Computer Engineering, Dalhousie University, Canada","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030612194","display_name":"Minhong Wan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minhong Wan","raw_affiliation_strings":["Intelligent Robotics Research Center, Zhejiang Lab and Zhejiang Engineering Research Center for Intelligent Robotics,Hangzhou,China,311100"],"affiliations":[{"raw_affiliation_string":"Intelligent Robotics Research Center, Zhejiang Lab and Zhejiang Engineering Research Center for Intelligent Robotics,Hangzhou,China,311100","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074371475","display_name":"Wei Song","orcid":"https://orcid.org/0000-0002-0828-7486"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Song","raw_affiliation_strings":["Intelligent Robotics Research Center, Zhejiang Lab and Zhejiang Engineering Research Center for Intelligent Robotics,Hangzhou,China,311100"],"affiliations":[{"raw_affiliation_string":"Intelligent Robotics Research Center, Zhejiang Lab and Zhejiang Engineering Research Center for Intelligent Robotics,Hangzhou,China,311100","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100679282","display_name":"Te Li","orcid":"https://orcid.org/0000-0002-4471-107X"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Te Li","raw_affiliation_strings":["Intelligent Robotics Research Center, Zhejiang Lab and Zhejiang Engineering Research Center for Intelligent Robotics,Hangzhou,China,311100"],"affiliations":[{"raw_affiliation_string":"Intelligent Robotics Research Center, Zhejiang Lab and Zhejiang Engineering Research Center for Intelligent Robotics,Hangzhou,China,311100","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039356472","display_name":"Shiqiang Zhu","orcid":"https://orcid.org/0000-0002-5687-4001"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiqiang Zhu","raw_affiliation_strings":["Intelligent Robotics Research Center, Zhejiang Lab and Zhejiang Engineering Research Center for Intelligent Robotics,Hangzhou,China,311100"],"affiliations":[{"raw_affiliation_string":"Intelligent Robotics Research Center, Zhejiang Lab and Zhejiang Engineering Research Center for Intelligent Robotics,Hangzhou,China,311100","institution_ids":["https://openalex.org/I4210123185"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5078866305"],"corresponding_institution_ids":["https://openalex.org/I4210123185"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16619273,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":null,"first_page":"1377","last_page":"1382"},"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/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"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":0.9955999851226807,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8216677904129028},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6301745176315308},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.594114363193512},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4953533411026001},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4883853793144226},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4495649039745331},{"id":"https://openalex.org/keywords/frame-rate","display_name":"Frame rate","score":0.43882960081100464},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4243679642677307},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4241343140602112}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8216677904129028},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6301745176315308},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.594114363193512},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4953533411026001},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4883853793144226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4495649039745331},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.43882960081100464},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4243679642677307},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4241343140602112},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio55434.2022.10011692","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/robio55434.2022.10011692","pdf_url":null,"source":{"id":"https://openalex.org/S4363607789","display_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1797158261","https://openalex.org/W1983364832","https://openalex.org/W2060510034","https://openalex.org/W2154636774","https://openalex.org/W2156303437","https://openalex.org/W2526786524","https://openalex.org/W2673722796","https://openalex.org/W2792811594","https://openalex.org/W2907492528","https://openalex.org/W2962711930","https://openalex.org/W2963155035","https://openalex.org/W2963452667","https://openalex.org/W2963524571","https://openalex.org/W2964052309","https://openalex.org/W2982083293","https://openalex.org/W2999593439","https://openalex.org/W3016098309","https://openalex.org/W3034702511","https://openalex.org/W3035875334","https://openalex.org/W3085311298","https://openalex.org/W3134485584","https://openalex.org/W3143214123","https://openalex.org/W3149793578","https://openalex.org/W3157160370","https://openalex.org/W3172472082","https://openalex.org/W3206008172","https://openalex.org/W4214701094","https://openalex.org/W4214908293","https://openalex.org/W4289665794","https://openalex.org/W4304808241","https://openalex.org/W4312466984","https://openalex.org/W4385245566","https://openalex.org/W6682864246","https://openalex.org/W6751512325"],"related_works":["https://openalex.org/W8302103","https://openalex.org/W2588198209","https://openalex.org/W1909006023","https://openalex.org/W4205824991","https://openalex.org/W3200723557","https://openalex.org/W4312713546","https://openalex.org/W3171631314","https://openalex.org/W2977517636","https://openalex.org/W1969179582","https://openalex.org/W2810129309"],"abstract_inverted_index":{"Continuously":[0],"measuring":[1],"the":[2,34,65,82],"speaking":[3],"state":[4],"of":[5,16],"users":[6],"with":[7,81,96],"robot":[8],"in":[9,33,46,64,109],"a":[10,54,60,97],"human-robot":[11],"Interaction(HRI)":[12],"system":[13],"improves":[14],"metrics":[15],"interaction":[17],"quality.":[18],"Meanwhile,":[19],"mainstream":[20],"active":[21],"speaker":[22],"detection":[23],"(ASD)":[24],"algorithms":[25],"emphasize":[26],"achieving":[27],"high":[28,61],"AUCs":[29],"at":[30,117],"frame":[31],"level":[32],"AVA-Active":[35,66],"Speaker":[36,67],"dataset":[37,68],"and":[38,84,107],"pay":[39],"less":[40],"attention":[41],"to":[42,58,101],"get":[43],"real-time":[44],"performance":[45],"robotic":[47,111],"systems.":[48,112],"In":[49],"this":[50],"paper,":[51],"we":[52,91],"propose":[53],"model":[55,74],"named":[56],"FSDNet":[57],"keep":[59],"AUC":[62,76],"score":[63,77],"while":[69],"reducing":[70],"time":[71],"cost,":[72],"our":[73,103],"increase":[75],"by":[78],"0.1%":[79],"compared":[80],"State-Of-The-Art":[83],"need":[85],"only":[86],"75%":[87],"running":[88],"time.":[89],"Furthermore,":[90],"put":[92],"forward":[93],"an":[94],"architecture":[95],"time-related":[98],"prediction":[99],"function":[100],"make":[102],"algorithm":[104],"more":[105],"effective":[106],"generative":[108],"interactive":[110],"The":[113],"code":[114],"is":[115],"released":[116],"https://github.com/huangmin9966/FSDNet_RealTimeArch.":[118]},"counts_by_year":[],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}