{"id":"https://openalex.org/W2906848589","doi":"https://doi.org/10.1109/icassp40776.2020.9053900","title":"Ava Active Speaker: An Audio-Visual Dataset for Active Speaker Detection","display_name":"Ava Active Speaker: An Audio-Visual Dataset for Active Speaker Detection","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2906848589","doi":"https://doi.org/10.1109/icassp40776.2020.9053900","mag":"2906848589"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053900","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053900","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1901.01342","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041852716","display_name":"Joseph Roth","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph Roth","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083515346","display_name":"Sourish Chaudhuri","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sourish Chaudhuri","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044666169","display_name":"Ond\u0159ej Klejch","orcid":"https://orcid.org/0000-0001-5495-967X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ondrej Klejch","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062133033","display_name":"Radhika Marvin","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Radhika Marvin","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068559933","display_name":"Andrew Gallagher","orcid":"https://orcid.org/0000-0003-2448-4145"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Gallagher","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084384753","display_name":"Liat Kaver","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liat Kaver","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033832936","display_name":"Sharadh Ramaswamy","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sharadh Ramaswamy","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074995400","display_name":"Arkadiusz Stopczynski","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arkadiusz Stopczynski","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109890544","display_name":"Cordelia Schmid","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cordelia Schmid","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019766344","display_name":"Zhonghua Xi","orcid":"https://orcid.org/0000-0002-7147-3476"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhonghua Xi","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065761531","display_name":"Caroline Pantofaru","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Caroline Pantofaru","raw_affiliation_strings":["Google Research","Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":2.7838,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.91924062,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4492","last_page":"4496"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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":0.998199999332428,"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":0.7959861755371094},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6886559724807739},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6600303053855896},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6065530776977539},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5879209041595459},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.545071005821228},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5190528035163879},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48698100447654724},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4603867530822754},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32101958990097046},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2999802231788635},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.09542578458786011}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7959861755371094},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6886559724807739},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6600303053855896},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6065530776977539},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5879209041595459},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.545071005821228},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5190528035163879},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48698100447654724},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4603867530822754},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32101958990097046},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2999802231788635},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.09542578458786011},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053900","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053900","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1901.01342","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1901.01342","pdf_url":"https://arxiv.org/pdf/1901.01342","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2906848589","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1901.01342","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1901.01342","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1901.01342","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.17023/qtk7-0f03","is_oa":true,"landing_page_url":"https://doi.org/10.17023/qtk7-0f03","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1901.01342","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1901.01342","pdf_url":"https://arxiv.org/pdf/1901.01342","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2906848589.pdf","grobid_xml":"https://content.openalex.org/works/W2906848589.grobid-xml"},"referenced_works_count":58,"referenced_works":["https://openalex.org/W163811496","https://openalex.org/W1569447338","https://openalex.org/W1872883209","https://openalex.org/W1934410531","https://openalex.org/W1975879668","https://openalex.org/W2015293542","https://openalex.org/W2064194796","https://openalex.org/W2066348332","https://openalex.org/W2071828724","https://openalex.org/W2093153344","https://openalex.org/W2098923380","https://openalex.org/W2099403067","https://openalex.org/W2100561338","https://openalex.org/W2104804886","https://openalex.org/W2106488367","https://openalex.org/W2106793713","https://openalex.org/W2118847468","https://openalex.org/W2138761194","https://openalex.org/W2142075667","https://openalex.org/W2147520277","https://openalex.org/W2163973301","https://openalex.org/W2168996682","https://openalex.org/W2250641567","https://openalex.org/W2287407690","https://openalex.org/W2293467699","https://openalex.org/W2296073425","https://openalex.org/W2316138215","https://openalex.org/W2330149154","https://openalex.org/W2547701628","https://openalex.org/W2550543432","https://openalex.org/W2604379605","https://openalex.org/W2612445135","https://openalex.org/W2618799552","https://openalex.org/W2621109248","https://openalex.org/W2726515241","https://openalex.org/W2749694333","https://openalex.org/W2759799350","https://openalex.org/W2883383043","https://openalex.org/W2885307078","https://openalex.org/W2937949426","https://openalex.org/W2962960500","https://openalex.org/W2963082324","https://openalex.org/W2964161785","https://openalex.org/W2964171275","https://openalex.org/W2964327384","https://openalex.org/W2972756321","https://openalex.org/W3042359118","https://openalex.org/W3105099157","https://openalex.org/W3123318516","https://openalex.org/W6675048546","https://openalex.org/W6684193366","https://openalex.org/W6702266465","https://openalex.org/W6735927292","https://openalex.org/W6737664043","https://openalex.org/W6738390143","https://openalex.org/W6740167877","https://openalex.org/W6750169759","https://openalex.org/W6780788142"],"related_works":["https://openalex.org/W2194775991","https://openalex.org/W3016098309","https://openalex.org/W1927052826","https://openalex.org/W2963524571","https://openalex.org/W2962711930","https://openalex.org/W2108598243","https://openalex.org/W3194371751","https://openalex.org/W3123318516","https://openalex.org/W2990503944","https://openalex.org/W2954458766","https://openalex.org/W2619947201","https://openalex.org/W2618799552","https://openalex.org/W2604379605","https://openalex.org/W2507009361","https://openalex.org/W3023271457","https://openalex.org/W2961193895","https://openalex.org/W2808631503","https://openalex.org/W2726515241","https://openalex.org/W2287407690","https://openalex.org/W2117539524"],"abstract_inverted_index":{"Active":[0,55],"speaker":[1,15,35,119],"detection":[2,57,120],"is":[3,83,93],"an":[4],"important":[5],"component":[6],"in":[7,40,77],"video":[8,17],"analysis":[9],"algorithms":[10],"for":[11,19,116],"applications":[12],"such":[13],"as":[14,85],"diarization,":[16],"re-targeting":[18],"meetings,":[20],"speech":[21,92],"enhancement,":[22],"and":[23,46,69,89,121,136],"human-robot":[24],"interaction.":[25],"The":[26,95,125],"absence":[27],"of":[28,42],"a":[29,110,129],"large,":[30],"carefully":[31],"labeled":[32,74,84,102],"audio-visual":[33,114,134],"active":[34,118],"dataset":[36,58,96],"has":[37,61],"limited":[38],"evaluation":[39,126],"terms":[41],"data":[43],"diversity,":[44],"environments,":[45],"accuracy.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51],"present":[52],"the":[53,91],"AVA":[54],"Speaker":[56],"(AVA-ActiveSpeaker)":[59],"which":[60],"been":[62],"publicly":[63],"released":[64],"to":[65,133],"facilitate":[66],"algorithm":[67],"development":[68],"comparison.":[70],"It":[71],"contains":[72,97],"temporally":[73],"face":[75,81],"tracks":[76],"videos,":[78],"where":[79],"each":[80],"instance":[82],"speaking":[86],"or":[87],"not,":[88],"whether":[90],"audible.":[94],"about":[98],"3.65":[99],"million":[100],"human":[101],"frames":[103],"spanning":[104],"38.5":[105],"hours.":[106],"We":[107],"also":[108],"introduce":[109],"state-of-the-art,":[111],"jointly":[112],"trained":[113],"model":[115],"real-time":[117],"compare":[122],"several":[123],"variants.":[124],"clearly":[127],"demonstrates":[128],"significant":[130],"gain":[131],"due":[132],"modeling":[135],"temporal":[137],"integration":[138],"over":[139],"multiple":[140],"frames.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":1}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}