{"id":"https://openalex.org/W2970250044","doi":"https://doi.org/10.1109/icip.2019.8803248","title":"Toward Visual Voice Activity Detection for Unconstrained Videos","display_name":"Toward Visual Voice Activity Detection for Unconstrained Videos","publication_year":2019,"publication_date":"2019-08-26","ids":{"openalex":"https://openalex.org/W2970250044","doi":"https://doi.org/10.1109/icip.2019.8803248","mag":"2970250044"},"language":"en","primary_location":{"id":"doi:10.1109/icip.2019.8803248","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2019.8803248","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103065972","display_name":"Rahul Sharma","orcid":"https://orcid.org/0000-0003-1697-3897"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rahul Sharma","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008305849","display_name":"Krishna Somandepalli","orcid":"https://orcid.org/0000-0002-2845-1079"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krishna Somandepalli","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2991","last_page":"2995"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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/T11448","display_name":"Face recognition and analysis","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8673645257949829},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.674648642539978},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.589342474937439},{"id":"https://openalex.org/keywords/face-detection","display_name":"Face detection","score":0.5880329608917236},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5575531125068665},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5345975756645203},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5303277373313904},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5093887448310852},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5059418082237244},{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.5056400299072266},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4884578287601471},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4753161072731018},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.44506949186325073},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.41147202253341675},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.359180212020874},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.26244068145751953},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.1439952850341797}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8673645257949829},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.674648642539978},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.589342474937439},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.5880329608917236},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5575531125068665},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5345975756645203},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5303277373313904},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5093887448310852},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5059418082237244},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.5056400299072266},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4884578287601471},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4753161072731018},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.44506949186325073},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.41147202253341675},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.359180212020874},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.26244068145751953},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.1439952850341797},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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":1,"locations":[{"id":"doi:10.1109/icip.2019.8803248","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2019.8803248","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W7746136","https://openalex.org/W1514579074","https://openalex.org/W1522301498","https://openalex.org/W1600744878","https://openalex.org/W1924770834","https://openalex.org/W1947481528","https://openalex.org/W1986769338","https://openalex.org/W2065980576","https://openalex.org/W2098923380","https://openalex.org/W2122647985","https://openalex.org/W2169896329","https://openalex.org/W2194775991","https://openalex.org/W2295107390","https://openalex.org/W2323437298","https://openalex.org/W2400392957","https://openalex.org/W2613718673","https://openalex.org/W2735559731","https://openalex.org/W2749694333","https://openalex.org/W2757184610","https://openalex.org/W2765793020","https://openalex.org/W2962858109","https://openalex.org/W2962960500","https://openalex.org/W2963483561","https://openalex.org/W2964121744","https://openalex.org/W2990138404","https://openalex.org/W4236965008","https://openalex.org/W6600313631","https://openalex.org/W6620707391","https://openalex.org/W6630633036","https://openalex.org/W6631190155","https://openalex.org/W6640212811","https://openalex.org/W6647036751","https://openalex.org/W6684878041","https://openalex.org/W6687483927","https://openalex.org/W6713128720","https://openalex.org/W6743327199","https://openalex.org/W6750391026"],"related_works":["https://openalex.org/W2056853153","https://openalex.org/W2057559274","https://openalex.org/W2336272890","https://openalex.org/W4308999381","https://openalex.org/W3183843611","https://openalex.org/W4312238398","https://openalex.org/W3211418293","https://openalex.org/W4308999963","https://openalex.org/W4312081214","https://openalex.org/W325114128"],"abstract_inverted_index":{"The":[0,27,111],"prevalent":[1],"audio-based":[2,45],"Voice":[3],"Activity":[4],"Detection":[5],"(VAD)":[6],"systems":[7,49,132],"are":[8,17],"challenged":[9],"by":[10],"the":[11,22,25,32,42,56,73,169,178,196],"presence":[12],"of":[13,24,29,41,44,153,158,168,195,198],"ambient":[14],"noise":[15],"and":[16,67,105,119,142,186],"sensitive":[18],"to":[19,115,129,181],"variations":[20],"in":[21,94,123],"type":[23],"noise.":[26],"use":[28],"information":[30,122],"from":[31,72,172],"visual":[33,164],"modality,":[34],"when":[35],"available,":[36],"can":[37,98,148],"help":[38],"overcome":[39],"some":[40],"problems":[43],"VAD.":[46],"Existing":[47],"visual-VAD":[48,90,131,174],"however":[50],"do":[51],"not":[52,137],"operate":[53],"directly":[54],"on":[55,139,155,183],"whole":[57],"image":[58],"but":[59],"require":[60],"intermediate":[61],"face":[62,64,140,199],"detection,":[63],"landmark":[65],"detection":[66,141],"subsequent":[68,143],"facial":[69,144],"feature":[70,145],"extraction":[71],"lip":[74],"region.":[75],"In":[76,127],"this":[77],"work":[78],"we":[79],"present":[80],"an":[81],"end-to-end":[82],"trainable":[83],"Hierarchical":[84],"Context":[85],"Aware":[86],"(HiCA)":[87],"architecture":[88],"for":[89,91,117,211],"videos":[92,102,161],"obtained":[93],"unconstrained":[95,212],"environments":[96],"which":[97],"be":[99],"trained":[100],"with":[101,163],"as":[103,109],"input":[104],"audio":[106],"speech":[107],"labels":[108],"output.":[110],"network":[112,179],"is":[113],"designed":[114,210],"account":[116],"local":[118],"global":[120],"temporal":[121],"a":[124,150,156],"video":[125],"sequence.":[126],"contrast":[128],"existing":[130],"our":[133,173,203],"proposed":[134],"approach":[135],"does":[136],"rely":[138],"extraction.":[146],"It":[147],"obtain":[149],"VAD":[151],"accuracy":[152],"66%":[154],"dataset":[157],"Hollywood":[159],"movie":[160],"just":[162],"information.":[165],"Further":[166],"analysis":[167,194],"representations":[170],"learned":[171],"system":[175,204],"shows":[176,201],"that":[177,202],"learns":[180],"localize":[182],"human":[184,189],"faces,":[185],"sometimes":[187],"speaking":[188],"faces":[190],"specifically.":[191],"Our":[192],"quantitative":[193],"effectiveness":[197],"localization":[200],"performs":[205],"better":[206],"than":[207],"sound-localization":[208],"networks":[209],"videos.":[213]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}