{"id":"https://openalex.org/W2462337303","doi":"https://doi.org/10.1109/iwssip.2016.7502768","title":"Multi-speaker voice activity detection using a camera-assisted microphone array","display_name":"Multi-speaker voice activity detection using a camera-assisted microphone array","publication_year":2016,"publication_date":"2016-05-01","ids":{"openalex":"https://openalex.org/W2462337303","doi":"https://doi.org/10.1109/iwssip.2016.7502768","mag":"2462337303"},"language":"en","primary_location":{"id":"doi:10.1109/iwssip.2016.7502768","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwssip.2016.7502768","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Conference on Systems, Signals and Image Processing (IWSSIP)","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/A5058312356","display_name":"Trond F. Bergh","orcid":"https://orcid.org/0000-0003-0743-5659"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]},{"id":"https://openalex.org/I4210141079","display_name":"SquareHead Technology (Norway)","ror":"https://ror.org/04xxxy475","country_code":"NO","type":"company","lineage":["https://openalex.org/I4210141079"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Trond F. Bergh","raw_affiliation_strings":["Department of Informatics, University of Oslo, Oslo, Norway","Squarehead Technology AS, Oslo, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]},{"raw_affiliation_string":"Squarehead Technology AS, Oslo, Norway","institution_ids":["https://openalex.org/I4210141079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054986093","display_name":"Ines Hafizovic","orcid":null},"institutions":[{"id":"https://openalex.org/I4210141079","display_name":"SquareHead Technology (Norway)","ror":"https://ror.org/04xxxy475","country_code":"NO","type":"company","lineage":["https://openalex.org/I4210141079"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Ines Hafizovic","raw_affiliation_strings":["Squarehead Technology AS, Oslo, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Squarehead Technology AS, Oslo, Norway","institution_ids":["https://openalex.org/I4210141079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005880668","display_name":"Sverre Holm","orcid":"https://orcid.org/0000-0002-2273-705X"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Sverre Holm","raw_affiliation_strings":["Department of Informatics, University of Oslo, Oslo, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9977999925613403,"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/microphone-array","display_name":"Microphone array","score":0.7713750600814819},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7302476167678833},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7013705968856812},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6474138498306274},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.5228539109230042},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4506171941757202},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4320530891418457},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3779733180999756},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.359498530626297},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.246060311794281}],"concepts":[{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.7713750600814819},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7302476167678833},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7013705968856812},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6474138498306274},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.5228539109230042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4506171941757202},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4320530891418457},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3779733180999756},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.359498530626297},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.246060311794281},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwssip.2016.7502768","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwssip.2016.7502768","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Conference on Systems, Signals and Image Processing (IWSSIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323299","display_name":"Norges Forskningsr\u00e5d","ror":"https://ror.org/00epmv149"},{"id":"https://openalex.org/F4320324236","display_name":"DNV GL","ror":"https://ror.org/04c235406"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W126779258","https://openalex.org/W1583773829","https://openalex.org/W1755205674","https://openalex.org/W1946893126","https://openalex.org/W2046317813","https://openalex.org/W2074640119","https://openalex.org/W2081841744","https://openalex.org/W2083569472","https://openalex.org/W2090711167","https://openalex.org/W2103387126","https://openalex.org/W2115175902","https://openalex.org/W2115717467","https://openalex.org/W2116529913","https://openalex.org/W2124256571","https://openalex.org/W2124894749","https://openalex.org/W2129866629","https://openalex.org/W2130103520","https://openalex.org/W2139212933","https://openalex.org/W2148154194","https://openalex.org/W2152395643","https://openalex.org/W2156038773","https://openalex.org/W2157363431","https://openalex.org/W2159531755","https://openalex.org/W2164598857","https://openalex.org/W2164637175","https://openalex.org/W2167206042","https://openalex.org/W2169896329","https://openalex.org/W2170116036","https://openalex.org/W2170644918","https://openalex.org/W2171875099","https://openalex.org/W2397741330","https://openalex.org/W2988057920","https://openalex.org/W6605165268","https://openalex.org/W6677131165","https://openalex.org/W6679388247","https://openalex.org/W6683747465","https://openalex.org/W6684878041","https://openalex.org/W6712278672"],"related_works":["https://openalex.org/W2896203542","https://openalex.org/W201299990","https://openalex.org/W876328409","https://openalex.org/W4319068615","https://openalex.org/W107154053","https://openalex.org/W1879255185","https://openalex.org/W2148473678","https://openalex.org/W3004719695","https://openalex.org/W2120442551","https://openalex.org/W2769861442"],"abstract_inverted_index":{"We":[0,85],"present":[1],"a":[2,13,41,78,101],"method":[3,19],"for":[4,50,107],"voice":[5,48],"activity":[6,49,54],"detection":[7,22,44],"of":[8,26,73,80,95,104,114],"multiple":[9],"concurrent":[10],"speakers":[11],"using":[12,57],"camera-assisted":[14],"microphone":[15],"array.":[16],"The":[17],"proposed":[18,97],"uses":[20,31],"face":[21],"to":[23,39,46,91],"identify":[24,47],"locations":[25],"potential":[27],"speech":[28],"sources,":[29],"and":[30,83,99],"this":[32],"information":[33],"in":[34],"an":[35],"adaptive":[36],"beamforming":[37],"procedure":[38],"form":[40],"spatially":[42],"directed":[43],"algorithm":[45],"individual":[51],"speakers.":[52,119],"Voice":[53],"is":[55],"classified":[56],"support":[58],"vector":[59],"machines":[60],"with":[61,110,116],"mel-frequency":[62],"cepstrum":[63],"coefficients":[64],"as":[65],"features.":[66],"To":[67],"increase":[68],"the":[69,74,93,96],"spatial":[70],"filtering":[71],"ability":[72],"array":[75],"we":[76],"use":[77],"combination":[79],"Dolph-Chebyshev":[81],"weighting":[82],"null-steering.":[84],"have":[86],"carried":[87],"out":[88],"two":[89,117],"experiments":[90],"gauge":[92],"accuracy":[94,103,115],"method,":[98],"obtain":[100],"representative":[102],"around":[105,111],"95%":[106],"single":[108],"speakers,":[109],"1%":[112],"loss":[113],"simultaneous":[118]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}