{"id":"https://openalex.org/W4390137121","doi":"https://doi.org/10.1109/taslp.2023.3346643","title":"Leveraging Visual Supervision for Array-Based Active Speaker Detection and Localization","display_name":"Leveraging Visual Supervision for Array-Based Active Speaker Detection and Localization","publication_year":2023,"publication_date":"2023-12-25","ids":{"openalex":"https://openalex.org/W4390137121","doi":"https://doi.org/10.1109/taslp.2023.3346643"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3346643","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3346643","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2312.14021","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005679652","display_name":"Davide Berghi","orcid":"https://orcid.org/0000-0001-6279-6364"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Davide Berghi","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Surrey, U.K"],"raw_orcid":"https://orcid.org/0000-0001-6279-6364","affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Surrey, U.K","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022165330","display_name":"Philip J. B. Jackson","orcid":"https://orcid.org/0000-0001-7933-5935"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philip J.B. Jackson","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Surrey, U.K"],"raw_orcid":"https://orcid.org/0000-0001-7933-5935","affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Surrey, U.K","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5005679652"],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":1.3432,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82407923,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"984","last_page":"995"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9993000030517578,"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":0.9976000189781189,"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":0.8260391354560852},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6331145763397217},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6138913631439209},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5558244585990906},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5291768908500671},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.49701836705207825},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.43929606676101685},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4294174611568451},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3417356610298157},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.13340651988983154}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8260391354560852},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6331145763397217},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6138913631439209},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5558244585990906},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5291768908500671},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.49701836705207825},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.43929606676101685},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4294174611568451},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3417356610298157},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.13340651988983154},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2023.3346643","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3346643","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2312.14021","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.14021","pdf_url":"https://arxiv.org/pdf/2312.14021","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:alma.44SUR_INST:11199500170002346","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2312.14021","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.14021","pdf_url":"https://arxiv.org/pdf/2312.14021","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7799999713897705}],"awards":[{"id":"https://openalex.org/G1478229083","display_name":null,"funder_award_id":"EP/V038087/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3186182679","display_name":null,"funder_award_id":"EP/L000539/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"},{"id":"https://openalex.org/F4320321979","display_name":"University of Surrey","ror":"https://ror.org/00ks66431"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390137121.pdf","grobid_xml":"https://content.openalex.org/works/W4390137121.grobid-xml"},"referenced_works_count":74,"referenced_works":["https://openalex.org/W1603075283","https://openalex.org/W1821462560","https://openalex.org/W1836465849","https://openalex.org/W1990334093","https://openalex.org/W2037227137","https://openalex.org/W2073902875","https://openalex.org/W2130357996","https://openalex.org/W2154636774","https://openalex.org/W2171727224","https://openalex.org/W2250436945","https://openalex.org/W2287407690","https://openalex.org/W2316138215","https://openalex.org/W2511428026","https://openalex.org/W2523915246","https://openalex.org/W2547701628","https://openalex.org/W2619697695","https://openalex.org/W2769321409","https://openalex.org/W2772736377","https://openalex.org/W2808631503","https://openalex.org/W2810934215","https://openalex.org/W2886300652","https://openalex.org/W2891205112","https://openalex.org/W2891591820","https://openalex.org/W2914911817","https://openalex.org/W2918984654","https://openalex.org/W2920582597","https://openalex.org/W2942551338","https://openalex.org/W2954458766","https://openalex.org/W2962730651","https://openalex.org/W2962865004","https://openalex.org/W2963115079","https://openalex.org/W2963218389","https://openalex.org/W2963307811","https://openalex.org/W2964109005","https://openalex.org/W2964171275","https://openalex.org/W2982382207","https://openalex.org/W2982624843","https://openalex.org/W2988200020","https://openalex.org/W2989980422","https://openalex.org/W3005741390","https://openalex.org/W3016098309","https://openalex.org/W3034658206","https://openalex.org/W3034702511","https://openalex.org/W3034742263","https://openalex.org/W3049847664","https://openalex.org/W3091667472","https://openalex.org/W3098454764","https://openalex.org/W3105684258","https://openalex.org/W3123318516","https://openalex.org/W3162475350","https://openalex.org/W3163193264","https://openalex.org/W3163881933","https://openalex.org/W3181255780","https://openalex.org/W3188558905","https://openalex.org/W3189964604","https://openalex.org/W3203177955","https://openalex.org/W3207207922","https://openalex.org/W3213455868","https://openalex.org/W3213716738","https://openalex.org/W4289665794","https://openalex.org/W4293569348","https://openalex.org/W4293665662","https://openalex.org/W4309598585","https://openalex.org/W4312268709","https://openalex.org/W4312356258","https://openalex.org/W4386763588","https://openalex.org/W4393535895","https://openalex.org/W6638523607","https://openalex.org/W6685120548","https://openalex.org/W6729831399","https://openalex.org/W6754420807","https://openalex.org/W6765195009","https://openalex.org/W6767453888","https://openalex.org/W6784117923"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W2385859805","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731"],"abstract_inverted_index":{"Conventional":[0],"audio-visual":[1,192],"approaches":[2],"for":[3],"active":[4,66,109],"speaker":[5,23,38,67,110],"detection":[6,68],"(ASD)":[7],"typically":[8],"rely":[9],"on":[10,169],"visually":[11],"pre-extracted":[12],"face":[13,35],"tracks":[14],"and":[15,69,81,146,194,230],"the":[16,22,34,37,74,79,120,123,136,141,149,153,170,180,187,190,199,218,234],"corresponding":[17],"single-channel":[18],"audio":[19,47,61,129,176,236],"to":[20,30,88,118,134,159],"find":[21],"in":[24,165,217],"a":[25,45,91,95,102,115],"video.":[26],"Therefore,":[27],"they":[28],"tend":[29],"fail":[31],"every":[32],"time":[33,80],"of":[36,73,83,122,189],"is":[39,112,132,156,215],"not":[40,157],"visible.":[41],"We":[42,204],"demonstrate":[43,205],"that":[44,100,152,174,206],"simple":[46],"convolutional":[48],"recurrent":[49],"neural":[50],"network":[51,117,131,143,155,177],"(CRNN)":[52],"trained":[53,133,178],"with":[54,179,198,226,233],"spatial":[55],"input":[56],"features":[57],"extracted":[58],"from":[59],"multichannel":[60,128,235],"can":[62,144,185,208],"perform":[63],"simultaneous":[64],"horizontal":[65],"localization":[70],"(ASDL),":[71],"independently":[72],"visual":[75],"modality.":[76],"To":[77],"address":[78],"cost":[82],"generating":[84],"ground":[85],"truth":[86],"labels":[87],"train":[89],"such":[90],"system,":[92],"we":[93],"propose":[94],"new":[96],"self-supervised":[97,182],"training":[98,228],"pipeline":[99],"embraces":[101],"\u201cstudent-teacher\u201d":[103],"learning":[104,183,219],"approach.":[105],"A":[106],"conventional":[107,201],"pre-trained":[108],"detector":[111],"adopted":[113],"as":[114,125],"\u201cteacher\u201d":[116],"provide":[119],"position":[121],"speakers":[124,151],"pseudo-labels.":[126],"The":[127],"\u201cstudent\u201d":[130],"generate":[135],"same":[137],"results.":[138],"At":[139],"inference,":[140],"student":[142],"generalize":[145],"locate":[147],"also":[148],"occluded":[150],"teacher":[154],"able":[158],"detect":[160],"visually,":[161],"yielding":[162],"considerable":[163],"improvements":[164,207],"recall":[166],"rate.":[167],"Experiments":[168],"TragicTalkers":[171],"dataset":[172],"show":[173],"an":[175],"proposed":[181],"approach":[184],"exceed":[186],"performance":[188],"typical":[191],"methods":[193],"produce":[195],"results":[196],"competitive":[197],"costly":[200],"supervised":[202],"training.":[203],"be":[209,224],"achieved":[210],"when":[211],"minimal":[212],"manual":[213],"supervision":[214],"introduced":[216],"pipeline.":[220],"Further":[221],"gains":[222],"may":[223],"sought":[225],"larger":[227],"sets":[229],"integrating":[231],"vision":[232],"system.":[237]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}