{"id":"https://openalex.org/W2164637175","doi":"https://doi.org/10.1109/icassp.2006.1660092","title":"An Analysis of Visual Speech Information Applied to Voice Activity Detection","display_name":"An Analysis of Visual Speech Information Applied to Voice Activity Detection","publication_year":2006,"publication_date":"2006-08-02","ids":{"openalex":"https://openalex.org/W2164637175","doi":"https://doi.org/10.1109/icassp.2006.1660092","mag":"2164637175"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2006.1660092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660092","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","raw_type":"proceedings-article"},"type":"preprint","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/A5087166091","display_name":"David Sodoyer","orcid":"https://orcid.org/0000-0001-9081-3950"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"D. Sodoyer","raw_affiliation_strings":["Speech Communication Institute, INPG, U3, UMR 5009 CNRS, Grenoble, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Communication Institute, INPG, U3, UMR 5009 CNRS, Grenoble, France","institution_ids":["https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071156904","display_name":"Bertrand Rivet","orcid":"https://orcid.org/0000-0003-4901-5302"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"B. Rivet","raw_affiliation_strings":["Speech Communication Institute, INPG, U3, UMR 5009 CNRS, Grenoble, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Communication Institute, INPG, U3, UMR 5009 CNRS, Grenoble, France","institution_ids":["https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020392160","display_name":"Laurent Girin","orcid":"https://orcid.org/0000-0002-9214-8760"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"L. Girin","raw_affiliation_strings":["Speech Communication Institute, INPG, U3, UMR 5009 CNRS, Grenoble, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Communication Institute, INPG, U3, UMR 5009 CNRS, Grenoble, France","institution_ids":["https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001142101","display_name":"Jean\u2010Luc Schwartz","orcid":"https://orcid.org/0000-0001-8969-9185"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"J.-L. Schwartz","raw_affiliation_strings":["Speech Communication Institute, INPG, U3, UMR 5009 CNRS, Grenoble, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Communication Institute, INPG, U3, UMR 5009 CNRS, Grenoble, France","institution_ids":["https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055562421","display_name":"Christian Jutten","orcid":"https://orcid.org/0000-0002-4477-4847"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210124956","display_name":"GIPSA-Lab","ror":"https://ror.org/02wrme198","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"C. Jutten","raw_affiliation_strings":["Image and Signal Processing Laboratory, UMR 5083 CNRS, Grenoble, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Image and Signal Processing Laboratory, UMR 5083 CNRS, Grenoble, France","institution_ids":["https://openalex.org/I4210124956","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.527,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":{"value":0.95207226,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"601"},"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":0.9988999962806702,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9987999796867371,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.9092262983322144},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8011784553527832},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7124561071395874},{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.5432194471359253},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5030733942985535},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.4853586256504059},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.47147229313850403},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4491010010242462},{"id":"https://openalex.org/keywords/voice-analysis","display_name":"Voice analysis","score":0.44812649488449097},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.44246453046798706},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.43572309613227844},{"id":"https://openalex.org/keywords/activity-detection","display_name":"Activity detection","score":0.4243663251399994},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3488372564315796},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.22800302505493164},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0641559362411499}],"concepts":[{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.9092262983322144},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8011784553527832},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7124561071395874},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.5432194471359253},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5030733942985535},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.4853586256504059},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.47147229313850403},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4491010010242462},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.44812649488449097},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.44246453046798706},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.43572309613227844},{"id":"https://openalex.org/C2988656282","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity detection","level":2,"score":0.4243663251399994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3488372564315796},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.22800302505493164},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0641559362411499},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2006.1660092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660092","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-00361750v1","is_oa":false,"landing_page_url":"https://hal.science/hal-00361750","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2006 - IEEE International Conference on Acoustics, Speech, and Signal Processing, May 2006, Toulouse, France. pp.1","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5299999713897705,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1573024203","https://openalex.org/W1985456342","https://openalex.org/W2038010270","https://openalex.org/W2096391593","https://openalex.org/W2098717567","https://openalex.org/W2127211243","https://openalex.org/W2129120544","https://openalex.org/W2166847868","https://openalex.org/W2169896329","https://openalex.org/W2405539902","https://openalex.org/W6634352053","https://openalex.org/W6684878041"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W2069501481","https://openalex.org/W2164637175","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W2103239478","https://openalex.org/W4294771049","https://openalex.org/W1523214805"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,50,65],"new":[3],"approach":[4],"to":[5,29,71],"the":[6,26,37,40,45,73,80,91,103,106],"voice":[7,31,85,108],"activity":[8,32,86,109],"detection":[9,81,92],"(VAD)":[10],"problem":[11],"for":[12,79,90],"speech":[13,41,58,101],"signals":[14],"embedded":[15],"in":[16],"non-stationary":[17],"noise.":[18],"The":[19],"method":[20],"is":[21,28],"based":[22],"on":[23,99],"automatic":[24],"lipreading:":[25],"objective":[27],"detect":[30],"or":[33,87],"non-activity":[34],"by":[35],"exploiting":[36],"coherence":[38],"between":[39],"acoustic":[42],"signal":[43],"and":[44,59],"speaker's":[46],"lip":[47,54,74],"movements.":[48],"From":[49],"comprehensive":[51],"analysis":[52],"of":[53,82,84,93,105],"shape":[55],"parameters":[56],"during":[57],"non-speech":[60],"events,":[61],"we":[62],"show":[63],"that":[64],"single":[66],"appropriate":[67],"visual":[68,107],"parameter,":[69],"defined":[70],"characterize":[72],"movements,":[75],"can":[76],"be":[77],"used":[78],"sections":[83],"more":[88],"precisely,":[89],"silence":[94],"sections.":[95],"Detection":[96],"scores":[97],"obtained":[98],"spontaneous":[100],"confirm":[102],"efficiency":[104],"detector":[110],"(VVAD)":[111]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":6},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}