{"id":"https://openalex.org/W4393599985","doi":"https://doi.org/10.5281/zenodo.3928151","title":"RealVAD: A Real-world Dataset for Voice Activity Detection","display_name":"RealVAD: A Real-world Dataset for Voice Activity Detection","publication_year":2020,"publication_date":"2020-07-02","ids":{"openalex":"https://openalex.org/W4393599985","doi":"https://doi.org/10.5281/zenodo.3928151"},"language":"en","primary_location":{"id":"pmh:oai:figshare.com:article/14350235","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"","raw_type":"Dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057859690","display_name":"Cigdem Beyan","orcid":"https://orcid.org/0000-0002-9583-0087"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Beyan, Cigdem","raw_affiliation_strings":["Istituto Italiano di Tecnologia"],"affiliations":[{"raw_affiliation_string":"Istituto Italiano di Tecnologia","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075523693","display_name":"Muhammad Shahid","orcid":"https://orcid.org/0000-0002-4573-0379"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Shahid, Muhammad","raw_affiliation_strings":["Istituto Italiano di Tecnologia"],"affiliations":[{"raw_affiliation_string":"Istituto Italiano di Tecnologia","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007242502","display_name":"Vittorio Murino","orcid":"https://orcid.org/0000-0002-8645-2328"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Murino, Vittorio","raw_affiliation_strings":["Istituto Italiano di Tecnologia"],"affiliations":[{"raw_affiliation_string":"Istituto Italiano di Tecnologia","institution_ids":["https://openalex.org/I30771326"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5057859690"],"corresponding_institution_ids":["https://openalex.org/I30771326"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9930999875068665,"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":0.9930999875068665,"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":0.9925000071525574,"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/T12031","display_name":"Speech and dialogue systems","score":0.9663000106811523,"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":0.5083679556846619},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4102979302406311}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5083679556846619},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4102979302406311}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:figshare.com:article/14350235","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"","raw_type":"Dataset"},{"id":"pmh:oai:zenodo.org:3928151","is_oa":true,"landing_page_url":"https://zenodo.org/record/3928151","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/other"},{"id":"doi:10.5281/zenodo.3928151","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.3928151","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/14350235","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"","raw_type":"Dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"<strong>RealVAD:":[0],"A":[1,342,346],"Real-world":[2,343],"Dataset":[3,344],"for":[4,251,290,323,348],"Voice":[5,22,349],"Activity":[6,23,350],"Detection</strong>":[7],"The":[8,67,139,188,214,271,274],"task":[9,32],"of":[10,37,59,89,96,116,235,278],"automatically":[11],"detecting":[12],"\u201cWho":[13],"is":[14,18,28,52,69,76,94,125,260],"Speaking":[15],"and":[16,33,47,85,135,146,185,193,237,300,314,338,345],"When\u201d":[17],"broadly":[19],"named":[20],"as":[21],"Detection":[24,351],"(VAD).":[25],"Automatic":[26],"VAD":[27,286],"a":[29,55,60,72,126],"very":[30],"important":[31],"also":[34,176,232],"the":[35,83,114,121,156,161,241,244,247,252,256,266,297,307,312,328],"foundation":[36],"several":[38],"domains,":[39],"e.g.,":[40],"human-human,":[41],"human-computer/":[42],"robot/":[43],"virtual-agent":[44],"interaction":[45],"analyses,":[46],"industrial":[48],"applications.":[49],"RealVAD":[50,90],"dataset":[51,91,322],"constructed":[53],"from":[54,71,173,177,296],"YouTube":[56],"video":[57],"composed":[58,95],"panel":[61],"discussion":[62],"lasting":[63],"approx.":[64],"83":[65],"minutes.":[66],"audio":[68],"available":[70],"single":[73],"channel.":[74],"There":[75,124,230],"one":[77],"static":[78],"camera":[79],"capturing":[80],"all":[81],"panelists,":[82,153],"moderator":[84,157],"audiences.":[86],"Particular":[87],"aspects":[88],"are:":[92],"It":[93],"panelists":[97,140,189,245,253,280],"with":[98],"different":[99,212],"nationalities":[100],"(British,":[101],"Dutch,":[102],"French,":[103],"German,":[104],"Italian,":[105],"American,":[106],"Mexican,":[107],"Columbian,":[108],"Thai).":[109],"This":[110],"aspect":[111],"allows":[112],"studying":[113],"effect":[115],"ethnic":[117],"origin":[118],"variety":[119],"to":[120],"automatic":[122],"VAD.":[123],"gender":[127],"balance":[128],"such":[129],"that":[130],"there":[131,259],"are":[132,141,190,194,218,231,309],"four":[133],"female":[134],"five":[136],"male":[137],"panelists.":[138,292],"sitting":[142,254],"in":[143,160,211,246,255,281,311,331,356],"two":[144],"rows":[145],"they":[147,168],"can":[148],"be":[149],"gazing":[150],"audience,":[151],"other":[152],"their":[154,182,203,207],"laptop,":[155,208],"or":[158,165,226],"anywhere":[159],"room":[162],"while":[163],"speaking":[164],"not-speaking.":[166],"Therefore,":[167],"were":[169],"captured":[170],"not":[171],"only":[172],"frontal-view":[174],"but":[175],"side-view":[178],"varying":[179],"based":[180],"on":[181,240,359],"instant":[183],"posture":[184],"head":[186],"orientation.":[187],"moving":[191],"freely":[192],"doing":[195],"various":[196],"spontaneous":[197],"actions":[198],"(e.g.,":[199,228],"drinking":[200],"water,":[201],"checking":[202],"cell":[204],"phone,":[205],"using":[206,320],"etc.),":[209],"resulting":[210],"postures.":[213],"panelists\u2019":[215],"body":[216,224,276],"parts":[217],"sometimes":[219,261],"partially":[220],"occluded":[221],"by":[222,352],"their/other's":[223],"part":[225],"belongings":[227],"laptop).":[229],"natural":[233],"changes":[234],"illumination":[236],"shadow":[238],"rising":[239],"wall":[242],"behind":[243,268],"back":[248],"row.":[249],"Especially,":[250],"front":[257],"row,":[258],"background":[262],"motion":[263],"occurring":[264],"when":[265],"person(s)":[267],"them":[269],"moves.":[270],"annotations":[272,308],"includes:":[273],"upper":[275],"detection":[277],"nine":[279,291],"bounding":[282],"box":[283],"form.":[284],"Associated":[285],"ground-truth":[287],"(speaking,":[288],"not-speaking)":[289],"Acoustic":[293,315],"features":[294],"extracted":[295],"video:":[298],"MFCC":[299],"raw":[301],"filterbank":[302],"energies.":[303],"<em>All":[304],"info":[305],"regarding":[306],"given":[310],"ReadMe.txt":[313],"Features":[316],"README.txt":[317],"files.</em>":[318],"<strong>When":[319],"this":[321],"your":[324,332],"research,":[325],"please":[326],"cite":[327],"following":[329],"paper":[330],"publication:</strong>":[333],"C.":[334],"Beyan,":[335],"M.":[336],"Shahid":[337],"V.":[339],"Murino,":[340],"\"RealVAD:":[341],"Method":[347],"Body":[353],"Motion":[354],"Analysis\",":[355],"IEEE":[357],"Transactions":[358],"Multimedia,":[360],"2020.":[361]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}