{"id":"https://openalex.org/W1993583497","doi":"https://doi.org/10.1109/taslp.2015.2405481","title":"Audio-Visual Voice Activity Detection Using Diffusion Maps","display_name":"Audio-Visual Voice Activity Detection Using Diffusion Maps","publication_year":2015,"publication_date":"2015-02-19","ids":{"openalex":"https://openalex.org/W1993583497","doi":"https://doi.org/10.1109/taslp.2015.2405481","mag":"1993583497"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2015.2405481","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2405481","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/3506067","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041324347","display_name":"David Dov","orcid":"https://orcid.org/0000-0003-4013-8306"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"David Dov","raw_affiliation_strings":["Department of Electrical Engineering, The Technion-Israel Institute of Technology, Haifa, Israel","Department of Electrical Engineering, The Technion - Israel Institute of Technology, Haifa Israel#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, The Technion-Israel Institute of Technology, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]},{"raw_affiliation_string":"Department of Electrical Engineering, The Technion - Israel Institute of Technology, Haifa Israel#TAB#","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020330914","display_name":"Ronen Talmon","orcid":"https://orcid.org/0000-0002-6838-1423"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ronen Talmon","raw_affiliation_strings":["Department of Electrical Engineering, The Technion-Israel Institute of Technology, Haifa, Israel","Department of Electrical Engineering, The Technion - Israel Institute of Technology, Haifa Israel#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, The Technion-Israel Institute of Technology, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]},{"raw_affiliation_string":"Department of Electrical Engineering, The Technion - Israel Institute of Technology, Haifa Israel#TAB#","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080194185","display_name":"Israel Cohen","orcid":"https://orcid.org/0000-0002-2556-3972"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Israel Cohen","raw_affiliation_strings":["Department of Electrical Engineering, The Technion-Israel Institute of Technology, Haifa, Israel","Department of Electrical Engineering, The Technion - Israel Institute of Technology, Haifa Israel#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, The Technion-Israel Institute of Technology, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]},{"raw_affiliation_string":"Department of Electrical Engineering, The Technion - Israel Institute of Technology, Haifa Israel#TAB#","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I174306211"],"apc_list":null,"apc_paid":null,"fwci":5.6848,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":{"value":0.96551927,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"23","issue":"4","first_page":"732","last_page":"745"},"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.9991000294685364,"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":0.7643457651138306},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.6390942335128784},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6255546808242798},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5807052850723267},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4948527216911316},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4680708646774292},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4609912037849426},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.444945365190506},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4207497239112854},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4181833267211914},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.41489261388778687},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38217905163764954},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.23847031593322754},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.15378183126449585}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7643457651138306},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.6390942335128784},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6255546808242798},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5807052850723267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4948527216911316},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4680708646774292},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4609912037849426},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.444945365190506},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4207497239112854},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4181833267211914},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.41489261388778687},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38217905163764954},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.23847031593322754},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.15378183126449585},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2015.2405481","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2405481","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:zenodo.org:3506067","is_oa":true,"landing_page_url":"https://zenodo.org/record/3506067","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:3506067","is_oa":true,"landing_page_url":"https://zenodo.org/record/3506067","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5}],"awards":[{"id":"https://openalex.org/G7168796923","display_name":null,"funder_award_id":"1130/11","funder_id":"https://openalex.org/F4320322252","funder_display_name":"Israel Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321449","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495"},{"id":"https://openalex.org/F4320322252","display_name":"Israel Science Foundation","ror":"https://ror.org/04sazxf24"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W15066456","https://openalex.org/W82246966","https://openalex.org/W149260027","https://openalex.org/W281336856","https://openalex.org/W1486632395","https://openalex.org/W1514579074","https://openalex.org/W1971071952","https://openalex.org/W1974783905","https://openalex.org/W2009450152","https://openalex.org/W2022186940","https://openalex.org/W2025168213","https://openalex.org/W2033571983","https://openalex.org/W2034356580","https://openalex.org/W2035395798","https://openalex.org/W2044002329","https://openalex.org/W2055671711","https://openalex.org/W2059759076","https://openalex.org/W2063880242","https://openalex.org/W2072195714","https://openalex.org/W2072219999","https://openalex.org/W2078639319","https://openalex.org/W2108759471","https://openalex.org/W2108819501","https://openalex.org/W2115717467","https://openalex.org/W2116810533","https://openalex.org/W2121973264","https://openalex.org/W2126942983","https://openalex.org/W2129111551","https://openalex.org/W2129120544","https://openalex.org/W2135035670","https://openalex.org/W2136155127","https://openalex.org/W2140831887","https://openalex.org/W2145030715","https://openalex.org/W2146324387","https://openalex.org/W2153309059","https://openalex.org/W2154278880","https://openalex.org/W2154504070","https://openalex.org/W2158275940","https://openalex.org/W2164637175","https://openalex.org/W2167023131","https://openalex.org/W2406066324","https://openalex.org/W3003662786","https://openalex.org/W3147539069","https://openalex.org/W4213367101","https://openalex.org/W4249022109","https://openalex.org/W4298870604","https://openalex.org/W6600593648","https://openalex.org/W6628849183","https://openalex.org/W6714222705","https://openalex.org/W6843883022"],"related_works":["https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870","https://openalex.org/W2888457666","https://openalex.org/W2953493266","https://openalex.org/W2555630001","https://openalex.org/W4316036082","https://openalex.org/W2103924733"],"abstract_inverted_index":{"The":[0,95,112,176],"performance":[1,203],"of":[2,12,82,140,178,204],"traditional":[3],"voice":[4,36,74,92,158,186],"activity":[5,37,75,93,159,187],"detectors":[6,38,49],"significantly":[7],"deteriorates":[8],"in":[9,62,174],"the":[10,31,41,55,58,63,80,120,138,150,169,179,192,195,201,205],"presence":[11],"highly":[13,89],"nonstationary":[14],"noise":[15],"and":[16,57,77,85,104,135,143,168,194],"transient":[17],"interferences.":[18],"One":[19],"solution":[20],"is":[21,28,88,97,110,132,161],"to":[22,30,65,124,137,184,209],"incorporate":[23],"a":[24,100,105,115,145,155,164],"video":[25,42,59,86,196],"signal":[26,43],"which":[27,50,160],"invariant":[29],"acoustic":[32],"environment.":[33],"Although":[34],"several":[35],"based":[39,52,98,162,189],"on":[40,53,99,163,190],"were":[44],"recently":[45],"presented,":[46],"merely":[47],"few":[48],"are":[51,122,182],"both":[54,83,191],"audio":[56,84,193],"signals":[60,87],"exist":[61],"literature":[64],"date.":[66],"In":[67],"this":[68],"paper,":[69],"we":[70,153],"present":[71],"an":[72],"audio-visual":[73],"detector":[76],"show":[78],"that":[79],"incorporation":[81],"beneficial":[90],"for":[91,157],"detection.":[94],"algorithm":[96,113,207],"supervised":[101,165],"learning":[102,166],"procedure,":[103,118],"labeled":[106],"training":[107],"data":[108],"set":[109],"considered.":[111],"comprises":[114],"feature":[116],"extraction":[117],"where":[119],"features":[121,139],"designed":[123],"separate":[125],"speech":[126],"from":[127],"nonspeech":[128],"frames.":[129],"Diffusion":[130],"maps":[131],"applied":[133],"separately":[134],"similarly":[136],"each":[141],"modality":[142],"builds":[144],"low":[146],"dimensional":[147],"representation.":[148],"Using":[149],"new":[151],"representation,":[152],"propose":[154],"measure":[156],"procedure":[167],"variability":[170],"between":[171],"adjacent":[172],"frames":[173],"time.":[175],"measures":[177],"two":[180],"modalities":[181],"merged":[183],"provide":[185],"detection":[188],"signals.":[197],"Experimental":[198],"results":[199],"demonstrate":[200],"improved":[202],"proposed":[206],"compared":[208],"state-of-the-art":[210],"detectors.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}