{"id":"https://openalex.org/W2885307078","doi":"https://doi.org/10.21437/interspeech.2018-2028","title":"AVA-Speech: A Densely Labeled Dataset of Speech Activity in Movies","display_name":"AVA-Speech: A Densely Labeled Dataset of Speech Activity in Movies","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2885307078","doi":"https://doi.org/10.21437/interspeech.2018-2028","mag":"2885307078"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-2028","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2028","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","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/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":true,"raw_author_name":"Sourish Chaudhuri","raw_affiliation_strings":["Google Inc"],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","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 Inc"],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055458377","display_name":"Daniel P. W. Ellis","orcid":"https://orcid.org/0000-0002-5076-4311"},"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":"Daniel P. W. Ellis","raw_affiliation_strings":["Google Inc"],"affiliations":[{"raw_affiliation_string":"Google Inc","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 Inc"],"affiliations":[{"raw_affiliation_string":"Google Inc","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 Inc"],"affiliations":[{"raw_affiliation_string":"Google Inc","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 Inc"],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","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 Inc"],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090919573","display_name":"Nathan Reale","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":"Nathan Reale","raw_affiliation_strings":["Google Inc"],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023823822","display_name":"Loretta Guarino Reid","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":"Loretta Guarino Reid","raw_affiliation_strings":["Google Inc"],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087313939","display_name":"Kevin Wilson","orcid":"https://orcid.org/0000-0001-9141-2219"},"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":"Kevin Wilson","raw_affiliation_strings":["Google Inc"],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","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 Inc"],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5083515346"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":2.6612,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.9116594,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1239","last_page":"1243"},"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":0.9998999834060669,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8362571597099304},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7166029810905457},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7025862336158752},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6682268381118774},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6677805781364441},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5651363134384155},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5236915349960327},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5197986364364624},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4798807203769684},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4340086579322815},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.41664552688598633},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38954925537109375},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3849424123764038},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.34529370069503784},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.10687479376792908}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8362571597099304},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7166029810905457},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7025862336158752},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6682268381118774},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6677805781364441},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5651363134384155},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5236915349960327},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5197986364364624},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4798807203769684},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4340086579322815},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.41664552688598633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38954925537109375},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3849424123764038},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.34529370069503784},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.10687479376792908},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2018-2028","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2028","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W15516501","https://openalex.org/W72302491","https://openalex.org/W163811496","https://openalex.org/W1482149378","https://openalex.org/W1503933356","https://openalex.org/W1506438021","https://openalex.org/W1837709900","https://openalex.org/W1973067693","https://openalex.org/W1975879668","https://openalex.org/W1993583497","https://openalex.org/W2023582935","https://openalex.org/W2032362923","https://openalex.org/W2106793713","https://openalex.org/W2147520277","https://openalex.org/W2158146178","https://openalex.org/W2250641567","https://openalex.org/W2400845926","https://openalex.org/W2403186097","https://openalex.org/W2406262283","https://openalex.org/W2407751501","https://openalex.org/W2526050071","https://openalex.org/W2574741591","https://openalex.org/W2593116425","https://openalex.org/W2618799552","https://openalex.org/W2621109248","https://openalex.org/W2742061524","https://openalex.org/W2745640009","https://openalex.org/W2748934350","https://openalex.org/W2749694333","https://openalex.org/W4297775537"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2696990509"],"abstract_inverted_index":{"Speech":[0],"activity":[1,87,113],"detection":[2],"(or":[3],"endpointing)":[4],"is":[5],"an":[6],"important":[7],"processing":[8],"step":[9],"for":[10,27,102],"applications":[11],"such":[12],"as":[13,158],"speech":[14,86,112,117,122],"recognition,":[15],"language":[16],"identification":[17],"and":[18,65,69,121,153],"speaker":[19],"diarization.Both":[20],"audio-and":[21],"vision-based":[22],"approaches":[23,64],"have":[24],"been":[25],"used":[26],"this":[28,71,103],"task":[29],"in":[30,45,88,106,132],"various":[31],"settings,":[32,47],"often":[33],"tailored":[34],"toward":[35],"end":[36],"applications.However,":[37],"much":[38],"of":[39,96,129,140],"the":[40,94,107,138],"prior":[41],"work":[42],"reports":[43],"results":[44],"synthetic":[46],"on":[48,52,137,147],"taskspecific":[49],"datasets,":[50],"or":[51],"datasets":[53],"that":[54,156],"are":[55],"not":[56],"openly":[57],"available.This":[58],"makes":[59],"it":[60],"difficult":[61],"to":[62,161],"compare":[63],"understand":[66],"their":[67],"strengths":[68],"weaknesses.In":[70],"paper,":[72],"we":[73,79],"describe":[74],"a":[75,98,159],"new":[76],"dataset":[77,101,108],"which":[78,126],"will":[80],"release":[81],"publicly":[82],"containing":[83],"densely":[84],"labeled":[85],"YouTube":[89],"videos":[90],"1":[91],",":[92],"with":[93,119,124],"goal":[95],"creating":[97],"shared,":[99],"available":[100],"task.The":[104],"labels":[105],"annotate":[109],"three":[110],"different":[111],"conditions:":[114],"clean":[115],"speech,":[116],"co-occurring":[118],"music,":[120],"cooccurring":[123],"noise,":[125],"enable":[127],"analysis":[128],"model":[130],"performance":[131,145],"more":[133],"challenging":[134],"conditions":[135],"based":[136],"presence":[139],"overlapping":[141],"noise.We":[142],"report":[143],"benchmark":[144],"numbers":[146],"AVA-Speech":[148],"using":[149],"off-the-shelf,":[150],"state-of-the-art":[151],"audio":[152],"vision":[154],"models":[155],"serve":[157],"baseline":[160],"facilitate":[162],"future":[163],"research.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}