{"id":"https://openalex.org/W3005055971","doi":"https://doi.org/10.1109/icassp40776.2020.9053171","title":"Multimodal Active Speaker Detection and Virtual Cinematography for Video Conferencing","display_name":"Multimodal Active Speaker Detection and Virtual Cinematography for Video Conferencing","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3005055971","doi":"https://doi.org/10.1109/icassp40776.2020.9053171","mag":"3005055971"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053171","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053171","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2002.03977","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068040769","display_name":"Ross Cutler","orcid":"https://orcid.org/0000-0002-2004-3003"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":true,"raw_author_name":"Ross Cutler","raw_affiliation_strings":["Microsoft Corp, Redmond, WA","(Microsoft)"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086119397","display_name":"Ramin Mehran","orcid":null},"institutions":[{"id":"https://openalex.org/I4210149135","display_name":"Zillow Group (United States)","ror":"https://ror.org/03n86v874","country_code":"US","type":"company","lineage":["https://openalex.org/I4210149135"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Ramin Mehran","raw_affiliation_strings":["Zillow, Seattle, WA","(Microsoft)"],"affiliations":[{"raw_affiliation_string":"Zillow, Seattle, WA","institution_ids":["https://openalex.org/I4210149135"]},{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014529218","display_name":"P. Sam Johnson","orcid":"https://orcid.org/0000-0003-3461-5380"},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sam Johnson","raw_affiliation_strings":["Facebook, Menlo Park, CA"],"affiliations":[{"raw_affiliation_string":"Facebook, Menlo Park, CA","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103551927","display_name":"Cha Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cha Zhang","raw_affiliation_strings":["Microsoft Corp, Redmond, WA","Microsoft Corporation, Redmond, WA;;"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA;;","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008360511","display_name":"Adam G. Kirk","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adam Kirk","raw_affiliation_strings":["Omnivor, Seattle, WA","Omnivor,Seattle,WA"],"affiliations":[{"raw_affiliation_string":"Omnivor, Seattle, WA","institution_ids":[]},{"raw_affiliation_string":"Omnivor,Seattle,WA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059620912","display_name":"Oliver Whyte","orcid":"https://orcid.org/0000-0002-7029-9410"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oliver Whyte","raw_affiliation_strings":["Omnivor, Seattle, WA","Omnivor,Seattle,WA"],"affiliations":[{"raw_affiliation_string":"Omnivor, Seattle, WA","institution_ids":[]},{"raw_affiliation_string":"Omnivor,Seattle,WA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067691489","display_name":"Adarsh Kowdle","orcid":"https://orcid.org/0000-0002-4428-889X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adarsh Kowdle","raw_affiliation_strings":["perceptiveIO, San Francisco, CA","perceptiveIO,San Francisco,CA"],"affiliations":[{"raw_affiliation_string":"perceptiveIO, San Francisco, CA","institution_ids":[]},{"raw_affiliation_string":"perceptiveIO,San Francisco,CA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5068040769"],"corresponding_institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01459138,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4527","last_page":"4531"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8109148740768433},{"id":"https://openalex.org/keywords/panning","display_name":"Panning (audio)","score":0.7961519956588745},{"id":"https://openalex.org/keywords/cinematography","display_name":"Cinematography","score":0.7103047966957092},{"id":"https://openalex.org/keywords/zoom","display_name":"Zoom","score":0.6929198503494263},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48153501749038696},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4788655936717987},{"id":"https://openalex.org/keywords/frame-rate","display_name":"Frame rate","score":0.4706137776374817},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3493148684501648},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.33165669441223145},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07767456769943237}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8109148740768433},{"id":"https://openalex.org/C108944566","wikidata":"https://www.wikidata.org/wiki/Q1524510","display_name":"Panning (audio)","level":4,"score":0.7961519956588745},{"id":"https://openalex.org/C100991257","wikidata":"https://www.wikidata.org/wiki/Q590870","display_name":"Cinematography","level":2,"score":0.7103047966957092},{"id":"https://openalex.org/C124913957","wikidata":"https://www.wikidata.org/wiki/Q1232548","display_name":"Zoom","level":3,"score":0.6929198503494263},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48153501749038696},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4788655936717987},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.4706137776374817},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3493148684501648},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.33165669441223145},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07767456769943237},{"id":"https://openalex.org/C78762247","wikidata":"https://www.wikidata.org/wiki/Q1273174","display_name":"Petroleum engineering","level":1,"score":0.0},{"id":"https://openalex.org/C15336307","wikidata":"https://www.wikidata.org/wiki/Q1766051","display_name":"Lens (geology)","level":2,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053171","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053171","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:2002.03977","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.03977","pdf_url":"https://arxiv.org/pdf/2002.03977","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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:3005055971","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2002.03977.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2002.03977","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2002.03977","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"},{"id":"doi:10.17023/7s8c-ps65","is_oa":true,"landing_page_url":"https://doi.org/10.17023/7s8c-ps65","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2002.03977","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.03977","pdf_url":"https://arxiv.org/pdf/2002.03977","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3005055971.pdf","grobid_xml":"https://content.openalex.org/works/W3005055971.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2000466020","https://openalex.org/W2035090801","https://openalex.org/W2104804886","https://openalex.org/W2132920253","https://openalex.org/W2154636774","https://openalex.org/W2330149154","https://openalex.org/W2586878855","https://openalex.org/W2604379605","https://openalex.org/W2734695582","https://openalex.org/W2772736377","https://openalex.org/W2954458766","https://openalex.org/W2959980708","https://openalex.org/W2991853946","https://openalex.org/W3016098309","https://openalex.org/W6757716108","https://openalex.org/W6765195009"],"related_works":["https://openalex.org/W3015222335","https://openalex.org/W2114667027","https://openalex.org/W2145906742","https://openalex.org/W3142228643","https://openalex.org/W3139947266","https://openalex.org/W2208835638","https://openalex.org/W2093189944","https://openalex.org/W2122264073","https://openalex.org/W3125481318","https://openalex.org/W3147971527","https://openalex.org/W2173925781","https://openalex.org/W3143243221","https://openalex.org/W2101636524","https://openalex.org/W2277500885","https://openalex.org/W1924152592","https://openalex.org/W2836717509","https://openalex.org/W2387043790","https://openalex.org/W3090763778","https://openalex.org/W2060058620","https://openalex.org/W2863221301"],"abstract_inverted_index":{"Active":[0],"speaker":[1],"detection":[2],"(ASD)":[3],"and":[4,21,45,74,83,97,127,138,144],"virtual":[5],"cinematography":[6],"(VC)":[7],"can":[8],"significantly":[9,33],"improve":[10],"the":[11,36,112,115,122,129],"experience":[12],"of":[13,23,52],"a":[14,24,41,61,67,71,75,147],"video":[15,31,132],"conference":[16],"by":[17,125],"automatically":[18],"panning,":[19],"tilting":[20],"zooming":[22,128],"camera:":[25],"subjectively":[26],"users":[27],"rate":[28],"an":[29,53,85,88],"expert":[30,54],"cinematographer":[32,55],"higher":[34],"than":[35],"unedited":[37],"video.":[38],"We":[39],"describe":[40],"new":[42],"automated":[43],"ASD":[44,86],"VC":[46,102,123],"that":[47,93],"performs":[48],"within":[49],"0.3":[50],"MOS":[51],"based":[56],"on":[57,146],"subjective":[58],"ratings":[59],"with":[60,149],"1-5":[62],"scale.":[63],"This":[64],"system":[65,92,116,135,148],"uses":[66],"4K":[68,130],"wide-FOV":[69,131],"camera,":[70,73],"depth":[72],"microphone":[76],"array,":[77],"extracts":[78],"features":[79],"from":[80],"each":[81,152],"modality":[82],"trains":[84],"using":[87,106,140],"AdaBoost":[89],"machine":[90,107],"learning":[91],"is":[94,103],"very":[95],"efficient":[96],"runs":[98],"in":[99,155],"real-time.":[100],"A":[101],"similarly":[104],"trained":[105],"learning.":[108],"To":[109],"avoid":[110],"distracting":[111],"room":[113],"participants":[114],"has":[117],"no":[118],"moving":[119],"parts":[120],"-":[121],"works":[124],"cropping":[126],"stream.":[133],"The":[134],"was":[136],"tuned":[137],"evaluated":[139,145],"extensive":[141],"crowdsourcing":[142],"techniques":[143],"N=100":[150],"meetings,":[151],"25":[153],"minutes":[154],"length.":[156]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
