{"id":"https://openalex.org/W2293143352","doi":"https://doi.org/10.1109/icip.2015.7351533","title":"Audiovisual voice activity detection using off-the-shelf cameras","display_name":"Audiovisual voice activity detection using off-the-shelf cameras","publication_year":2015,"publication_date":"2015-09-01","ids":{"openalex":"https://openalex.org/W2293143352","doi":"https://doi.org/10.1109/icip.2015.7351533","mag":"2293143352"},"language":"en","primary_location":{"id":"doi:10.1109/icip.2015.7351533","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2015.7351533","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 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/A5062063819","display_name":"Sergio Montazzolli","orcid":null},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]},{"id":"https://openalex.org/I4210152232","display_name":"Institute of Informatics of the Slovak Academy of Sciences","ror":"https://ror.org/04jgqpc26","country_code":"SK","type":"facility","lineage":["https://openalex.org/I207624831","https://openalex.org/I4210152232"]}],"countries":["BR","SK"],"is_corresponding":false,"raw_author_name":"S. Montazzolli","raw_affiliation_strings":["Institute of Informatics, Federal University of Rio Grande do Sul"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Informatics, Federal University of Rio Grande do Sul","institution_ids":["https://openalex.org/I130442723","https://openalex.org/I4210152232"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012781859","display_name":"Cl\u00e1udio R. Jung","orcid":"https://orcid.org/0000-0002-4711-5783"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. R. Jung","raw_affiliation_strings":["HP Labs, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057034161","display_name":"Dan Gelb","orcid":null},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]},{"id":"https://openalex.org/I4210152232","display_name":"Institute of Informatics of the Slovak Academy of Sciences","ror":"https://ror.org/04jgqpc26","country_code":"SK","type":"facility","lineage":["https://openalex.org/I207624831","https://openalex.org/I4210152232"]}],"countries":["BR","SK"],"is_corresponding":false,"raw_author_name":"Dan Gelb","raw_affiliation_strings":["Institute of Informatics, Federal University of Rio Grande do Sul"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Informatics, Federal University of Rio Grande do Sul","institution_ids":["https://openalex.org/I130442723","https://openalex.org/I4210152232"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7284,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69090197,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"16","issue":null,"first_page":"3886","last_page":"3890"},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9954000115394592,"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":0.9952999949455261,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7699006795883179},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7554177045822144},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7071328163146973},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6821458339691162},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5483825206756592},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.525920033454895},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3623769283294678},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3553144931793213}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7699006795883179},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7554177045822144},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7071328163146973},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6821458339691162},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5483825206756592},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.525920033454895},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3623769283294678},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3553144931793213},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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.2015.7351533","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2015.7351533","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W705233","https://openalex.org/W126779258","https://openalex.org/W1504795754","https://openalex.org/W1511051076","https://openalex.org/W1984813860","https://openalex.org/W1994630425","https://openalex.org/W2003784299","https://openalex.org/W2033571983","https://openalex.org/W2046599127","https://openalex.org/W2063880242","https://openalex.org/W2065257586","https://openalex.org/W2084008764","https://openalex.org/W2084237818","https://openalex.org/W2090088747","https://openalex.org/W2104686155","https://openalex.org/W2108720302","https://openalex.org/W2114661268","https://openalex.org/W2122647985","https://openalex.org/W2129120544","https://openalex.org/W2130103520","https://openalex.org/W2164602770","https://openalex.org/W2169896329","https://openalex.org/W6605165268","https://openalex.org/W6630225631","https://openalex.org/W6671574273","https://openalex.org/W6675851846","https://openalex.org/W6679388247","https://openalex.org/W6684878041"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W4253235840","https://openalex.org/W3151937861"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,15,76,93],"new":[4],"audiovisual":[5,63],"voice":[6],"activity":[7],"detection":[8],"(VAD)":[9],"method":[10,86],"for":[11,71,92],"off-the-shelf":[12],"cameras":[13],"presenting":[14],"color":[16],"sensor":[17],"and":[18,65],"two":[19],"microphones.":[20],"The":[21],"motion":[22],"of":[23,29,61,95],"particles":[24],"in":[25],"the":[26,34,42,47,59,62,67],"mouth":[27],"region":[28],"each":[30,72],"face":[31,74],"detected":[32,73],"by":[33],"camera":[35],"is":[36,51],"used":[37,52],"as":[38,53],"video":[39],"cue,":[40],"while":[41],"Generalized":[43],"Cross":[44],"Correlation":[45],"with":[46],"PHase":[48],"Transform":[49],"(GCC-PHAT)":[50],"audio":[54],"cue.":[55],"We":[56],"then":[57],"estimate":[58],"distribution":[60],"cues":[64],"perform":[66],"final":[68],"VAD":[69],"result":[70],"using":[75],"Hidden":[77],"Markov":[78],"Model":[79],"(HMM).":[80],"Experimental":[81],"results":[82],"indicated":[83],"that":[84],"our":[85],"achieves":[87],"an":[88],"average":[89],"87%":[90],"accuracy":[91],"set":[94],"test":[96],"videos.":[97]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}