{"id":"https://openalex.org/W4399513009","doi":"https://doi.org/10.1109/tbiom.2024.3412821","title":"WASD: A Wilder Active Speaker Detection Dataset","display_name":"WASD: A Wilder Active Speaker Detection Dataset","publication_year":2024,"publication_date":"2024-06-11","ids":{"openalex":"https://openalex.org/W4399513009","doi":"https://doi.org/10.1109/tbiom.2024.3412821"},"language":"en","primary_location":{"id":"doi:10.1109/tbiom.2024.3412821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tbiom.2024.3412821","pdf_url":null,"source":{"id":"https://openalex.org/S4210209367","display_name":"IEEE Transactions on Biometrics Behavior and Identity Science","issn_l":"2637-6407","issn":["2637-6407"],"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 Transactions on Biometrics, Behavior, and Identity Science","raw_type":"journal-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/A5088262626","display_name":"Tiago Roxo","orcid":"https://orcid.org/0000-0001-9563-8039"},"institutions":[{"id":"https://openalex.org/I161321875","display_name":"University of Beira Interior","ror":"https://ror.org/03nf36p02","country_code":"PT","type":"education","lineage":["https://openalex.org/I161321875"]},{"id":"https://openalex.org/I4210120471","display_name":"Instituto de Telecomunica\u00e7\u00f5es","ror":"https://ror.org/02ht4fk33","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210120471"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Tiago Roxo","raw_affiliation_strings":["Instituto de Telecomunica&#x00E7;&#x00F5;es, University of Beira Interior, Covilh&#x00E3;, Portugal","Instituto de Telecomunica&#x00E7;&#x00F5;es, University of Beira Interior, Portugal"],"raw_orcid":"https://orcid.org/0000-0001-9563-8039","affiliations":[{"raw_affiliation_string":"Instituto de Telecomunica&#x00E7;&#x00F5;es, University of Beira Interior, Covilh&#x00E3;, Portugal","institution_ids":["https://openalex.org/I161321875"]},{"raw_affiliation_string":"Instituto de Telecomunica&#x00E7;&#x00F5;es, University of Beira Interior, Portugal","institution_ids":["https://openalex.org/I4210120471","https://openalex.org/I161321875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016093558","display_name":"Joana C. Costa","orcid":"https://orcid.org/0000-0003-3995-4621"},"institutions":[{"id":"https://openalex.org/I161321875","display_name":"University of Beira Interior","ror":"https://ror.org/03nf36p02","country_code":"PT","type":"education","lineage":["https://openalex.org/I161321875"]},{"id":"https://openalex.org/I4210120471","display_name":"Instituto de Telecomunica\u00e7\u00f5es","ror":"https://ror.org/02ht4fk33","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210120471"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Joana Cabral Costa","raw_affiliation_strings":["Instituto de Telecomunica&#x00E7;&#x00F5;es, University of Beira Interior, Covilh&#x00E3;, Portugal","Instituto de Telecomunica&#x00E7;&#x00F5;es, University of Beira Interior, Portugal"],"raw_orcid":"https://orcid.org/0000-0003-3995-4621","affiliations":[{"raw_affiliation_string":"Instituto de Telecomunica&#x00E7;&#x00F5;es, University of Beira Interior, Covilh&#x00E3;, Portugal","institution_ids":["https://openalex.org/I161321875"]},{"raw_affiliation_string":"Instituto de Telecomunica&#x00E7;&#x00F5;es, University of Beira Interior, Portugal","institution_ids":["https://openalex.org/I4210120471","https://openalex.org/I161321875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058284019","display_name":"Pedro R. M. In\u00e1cio","orcid":"https://orcid.org/0000-0001-8221-0666"},"institutions":[{"id":"https://openalex.org/I161321875","display_name":"University of Beira Interior","ror":"https://ror.org/03nf36p02","country_code":"PT","type":"education","lineage":["https://openalex.org/I161321875"]},{"id":"https://openalex.org/I4210120471","display_name":"Instituto de Telecomunica\u00e7\u00f5es","ror":"https://ror.org/02ht4fk33","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210120471"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Pedro R. M. In\u00e1cio","raw_affiliation_strings":["Instituto de Telecomunica&#x00E7;&#x00F5;es, University of Beira Interior, Covilh&#x00E3;, Portugal","Instituto de Telecomunica&#x00E7;&#x00F5;es, University of Beira Interior, Portugal"],"raw_orcid":"https://orcid.org/0000-0001-8221-0666","affiliations":[{"raw_affiliation_string":"Instituto de Telecomunica&#x00E7;&#x00F5;es, University of Beira Interior, Covilh&#x00E3;, Portugal","institution_ids":["https://openalex.org/I161321875"]},{"raw_affiliation_string":"Instituto de Telecomunica&#x00E7;&#x00F5;es, University of Beira Interior, Portugal","institution_ids":["https://openalex.org/I4210120471","https://openalex.org/I161321875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090305015","display_name":"Hugo Proen\u00e7a","orcid":"https://orcid.org/0000-0003-2551-8570"},"institutions":[{"id":"https://openalex.org/I161321875","display_name":"University of Beira Interior","ror":"https://ror.org/03nf36p02","country_code":"PT","type":"education","lineage":["https://openalex.org/I161321875"]},{"id":"https://openalex.org/I4210120471","display_name":"Instituto de Telecomunica\u00e7\u00f5es","ror":"https://ror.org/02ht4fk33","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210120471"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Hugo Proen\u00e7a","raw_affiliation_strings":["Instituto de Telecomunica&#x00E7;&#x00F5;es, University of Beira Interior, Covilh&#x00E3;, Portugal","Instituto de Telecomunica&#x00E7;&#x00F5;es, University of Beira Interior, Portugal"],"raw_orcid":"https://orcid.org/0000-0003-2551-8570","affiliations":[{"raw_affiliation_string":"Instituto de Telecomunica&#x00E7;&#x00F5;es, University of Beira Interior, Covilh&#x00E3;, Portugal","institution_ids":["https://openalex.org/I161321875"]},{"raw_affiliation_string":"Instituto de Telecomunica&#x00E7;&#x00F5;es, University of Beira Interior, Portugal","institution_ids":["https://openalex.org/I4210120471","https://openalex.org/I161321875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9449,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.87629596,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"7","issue":"1","first_page":"61","last_page":"70"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9817000031471252,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9817000031471252,"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/T10860","display_name":"Speech and Audio Processing","score":0.9660999774932861,"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":0.9375,"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":0.55866539478302},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48599347472190857},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37174761295318604}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.55866539478302},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48599347472190857},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37174761295318604}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tbiom.2024.3412821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tbiom.2024.3412821","pdf_url":null,"source":{"id":"https://openalex.org/S4210209367","display_name":"IEEE Transactions on Biometrics Behavior and Identity Science","issn_l":"2637-6407","issn":["2637-6407"],"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 Transactions on Biometrics, Behavior, and Identity Science","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2577126906","display_name":null,"funder_award_id":"CENTRO-01-0145-FEDER-000019","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G3375535518","display_name":"Instituto de Telecomunica\u00e7\u00f5es","funder_award_id":"UIDB/50008/2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G4140754189","display_name":"Mecanismos de Defesa para Redes de Aprendizagem Profunda para Dete\u00e7\u00e3o Facial em Contexto Real","funder_award_id":"2021.04905.BD","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G8125926532","display_name":"An\u00e1lise Comportamental em Ambientes de Video-Vigil\u00e2ncia Usando Arquiteturas de Aprendizagem Profunda","funder_award_id":"2020.09847.BD","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"}],"funders":[{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1964448421","https://openalex.org/W2071828724","https://openalex.org/W2098923380","https://openalex.org/W2138621090","https://openalex.org/W2138761194","https://openalex.org/W2163973301","https://openalex.org/W2168996682","https://openalex.org/W2287407690","https://openalex.org/W2316138215","https://openalex.org/W2323437298","https://openalex.org/W2330149154","https://openalex.org/W2519887557","https://openalex.org/W2551572271","https://openalex.org/W2594690981","https://openalex.org/W2603203130","https://openalex.org/W2604379605","https://openalex.org/W2618799552","https://openalex.org/W2726515241","https://openalex.org/W2749694333","https://openalex.org/W2808631503","https://openalex.org/W2890952074","https://openalex.org/W2950864153","https://openalex.org/W2953092061","https://openalex.org/W2963037989","https://openalex.org/W2963781481","https://openalex.org/W2972729214","https://openalex.org/W3016098309","https://openalex.org/W3024085360","https://openalex.org/W3034702511","https://openalex.org/W3038871978","https://openalex.org/W3048939150","https://openalex.org/W3116298410","https://openalex.org/W3135222947","https://openalex.org/W3162475350","https://openalex.org/W3172472082","https://openalex.org/W3189964604","https://openalex.org/W3197584784","https://openalex.org/W3200102014","https://openalex.org/W3206008172","https://openalex.org/W4214701094","https://openalex.org/W4312268709","https://openalex.org/W4312466984","https://openalex.org/W4385245566","https://openalex.org/W4385822320","https://openalex.org/W4386075783","https://openalex.org/W6691613585","https://openalex.org/W6748370023","https://openalex.org/W6754420807","https://openalex.org/W6756215566","https://openalex.org/W6765195009","https://openalex.org/W6797761920","https://openalex.org/W6849258529","https://openalex.org/W7011482893"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Current":[0],"Active":[1,41],"Speaker":[2,42],"Detection":[3,43],"(ASD)":[4],"models":[5,115,135,186],"achieve":[6],"good":[7],"results":[8,129],"on":[9],"cooperative":[10,137],"settings":[11,138],"with":[12,46,70,159,178],"reliable":[13],"face":[14,76,107,179],"access":[15],"using":[16],"only":[17],"sound":[18],"and":[19,58,75,78,103,112,119,144,180,189],"facial":[20],"features,":[21],"which":[22],"is":[23],"not":[24,140,150],"suited":[25],"for":[26,68,83,136,168],"less":[27],"constrained":[28],"conditions.":[29],"To":[30,89,162],"demonstrate":[31],"this":[32],"limitation":[33],"of":[34,54,73,94,166],"current":[35,55,146],"datasets,":[36],"we":[37,96,171],"propose":[38,172],"a":[39,80,173],"Wilder":[40],"(WASD)":[44],"dataset,":[45],"increased":[47],"difficulty":[48],"by":[49],"targeting":[50],"the":[51,91,121,164],"key":[52],"components":[53],"ASD:":[56],"audio":[57,74,181],"face.":[59],"Grouped":[60],"into":[61,99],"5":[62],"categories,":[63],"WASD":[64,118,188],"contains":[65],"incremental":[66],"challenges":[67,93],"ASD":[69,84,125,147],"tactical":[71],"impairment":[72],"data,":[77],"provides":[79],"new":[81,92],"source":[82],"via":[85],"subject":[86],"body":[87,167,177],"annotations.":[88],"highlight":[90],"WASD,":[95],"divide":[97],"it":[98],"Easy":[100],"(cooperative":[101],"settings)":[102],"Hard":[104],"(audio":[105],"and/or":[106],"are":[108,193],"specifically":[109],"degraded)":[110],"groups,":[111],"assess":[113],"state-of-the-art":[114,185],"performance":[116],"in":[117,120,153,187],"most":[122],"challenging":[123,160],"available":[124,194],"dataset:":[126],"AVA-ActiveSpeaker.":[127],"The":[128],"show":[130],"that:":[131],"1)":[132],"AVA-ActiveSpeaker":[133],"prepares":[134],"but":[139],"wilder":[141,154],"ones":[142],"(surveillance);":[143],"2)":[145],"approaches":[148],"can":[149],"reliably":[151],"perform":[152],"settings,":[155],"even":[156],"if":[157],"trained":[158],"data.":[161],"prove":[163],"importance":[165],"wild":[169],"ASD,":[170],"baseline":[174],"that":[175,183],"complements":[176],"information":[182],"surpass":[184],"Columbia.":[190],"All":[191],"contributions":[192],"at":[195],"<uri":[196],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[197],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/Tiago-Roxo/WASD</uri>.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}
