{"id":"https://openalex.org/W2341944174","doi":"https://doi.org/10.1109/tsp.2016.2605068","title":"Kernel-Based Sensor Fusion With Application to Audio-Visual Voice Activity Detection","display_name":"Kernel-Based Sensor Fusion With Application to Audio-Visual Voice Activity Detection","publication_year":2016,"publication_date":"2016-09-01","ids":{"openalex":"https://openalex.org/W2341944174","doi":"https://doi.org/10.1109/tsp.2016.2605068","mag":"2341944174"},"language":"en","primary_location":{"id":"doi:10.1109/tsp.2016.2605068","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp.2016.2605068","pdf_url":null,"source":{"id":"https://openalex.org/S168680287","display_name":"IEEE Transactions on Signal Processing","issn_l":"1053-587X","issn":["1053-587X","1941-0476"],"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 Transactions on Signal Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1604.02946","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\u2014Israel Institute of Technology, Haifa, Israel","Department of Electrical Engineering, The Technion\u2014Israel Institute of Technology, Haifa, Israel#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, The Technion\u2014Israel Institute of Technology, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]},{"raw_affiliation_string":"Department of Electrical Engineering, The Technion\u2014Israel 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\u2014Israel Institute of Technology, Haifa, Israel","Department of Electrical Engineering, The Technion\u2014Israel Institute of Technology, Haifa, Israel#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, The Technion\u2014Israel Institute of Technology, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]},{"raw_affiliation_string":"Department of Electrical Engineering, The Technion\u2014Israel 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\u2014Israel Institute of Technology, Haifa, Israel","Department of Electrical Engineering, The Technion\u2014Israel Institute of Technology, Haifa, Israel#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, The Technion\u2014Israel Institute of Technology, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]},{"raw_affiliation_string":"Department of Electrical Engineering, The Technion\u2014Israel 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":4.3018,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.94416562,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"64","issue":"24","first_page":"6406","last_page":"6416"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9980000257492065,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.994700014591217,"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/computer-science","display_name":"Computer science","score":0.7834465503692627},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6424797773361206},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5766127705574036},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5710374116897583},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5432937145233154},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.5089919567108154},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5053723454475403},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5011839866638184},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.47771573066711426},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4669227600097656},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.44353923201560974},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4386565089225769},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4119296073913574},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37478557229042053},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33390378952026367},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.3048931360244751},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.132038414478302},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09242013096809387}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7834465503692627},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6424797773361206},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5766127705574036},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5710374116897583},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5432937145233154},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.5089919567108154},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5053723454475403},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5011839866638184},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.47771573066711426},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4669227600097656},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.44353923201560974},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4386565089225769},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4119296073913574},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37478557229042053},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33390378952026367},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3048931360244751},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.132038414478302},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09242013096809387},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tsp.2016.2605068","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp.2016.2605068","pdf_url":null,"source":{"id":"https://openalex.org/S168680287","display_name":"IEEE Transactions on Signal Processing","issn_l":"1053-587X","issn":["1053-587X","1941-0476"],"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 Transactions on Signal Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1604.02946","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1604.02946","pdf_url":"https://arxiv.org/pdf/1604.02946","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1604.02946","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1604.02946","pdf_url":"https://arxiv.org/pdf/1604.02946","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[{"score":0.5699999928474426,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W15066456","https://openalex.org/W82246966","https://openalex.org/W115769679","https://openalex.org/W1514579074","https://openalex.org/W1560013842","https://openalex.org/W1563939609","https://openalex.org/W1828732994","https://openalex.org/W1857178381","https://openalex.org/W1963586106","https://openalex.org/W1991167541","https://openalex.org/W1993583497","https://openalex.org/W1999322688","https://openalex.org/W2002979515","https://openalex.org/W2009228073","https://openalex.org/W2025168213","https://openalex.org/W2033571983","https://openalex.org/W2034356580","https://openalex.org/W2044002329","https://openalex.org/W2053101950","https://openalex.org/W2053186076","https://openalex.org/W2055671711","https://openalex.org/W2063880242","https://openalex.org/W2084237818","https://openalex.org/W2093402979","https://openalex.org/W2097308346","https://openalex.org/W2097469960","https://openalex.org/W2101324110","https://openalex.org/W2108759471","https://openalex.org/W2109935156","https://openalex.org/W2116529913","https://openalex.org/W2116810533","https://openalex.org/W2121947440","https://openalex.org/W2123576058","https://openalex.org/W2132914434","https://openalex.org/W2136294701","https://openalex.org/W2140831887","https://openalex.org/W2147278762","https://openalex.org/W2152322845","https://openalex.org/W2154057601","https://openalex.org/W2154415691","https://openalex.org/W2154504070","https://openalex.org/W2156838815","https://openalex.org/W2164637175","https://openalex.org/W2167023131","https://openalex.org/W2169278871","https://openalex.org/W2179941082","https://openalex.org/W2196564739","https://openalex.org/W2271518208","https://openalex.org/W2404397424","https://openalex.org/W2406066324","https://openalex.org/W2963888716","https://openalex.org/W2964197745","https://openalex.org/W2984776367","https://openalex.org/W4213367101","https://openalex.org/W4249022109","https://openalex.org/W4255209084","https://openalex.org/W4298220951","https://openalex.org/W6600593648","https://openalex.org/W6603377551","https://openalex.org/W6638654962","https://openalex.org/W6639298783","https://openalex.org/W6671574273","https://openalex.org/W6675134712","https://openalex.org/W6677131165","https://openalex.org/W6681738144","https://openalex.org/W6682991666","https://openalex.org/W6685409915","https://openalex.org/W6687739572","https://openalex.org/W6693697572","https://openalex.org/W6714222705"],"related_works":["https://openalex.org/W2496295964","https://openalex.org/W2294333436","https://openalex.org/W1976952689","https://openalex.org/W2336887028","https://openalex.org/W3211091508","https://openalex.org/W1984921740","https://openalex.org/W2070982348","https://openalex.org/W2373767407","https://openalex.org/W2365485488","https://openalex.org/W2653598178"],"abstract_inverted_index":{"In":[0,183],"this":[1,23,50,94],"paper,":[2],"we":[3,48,70,85,100,126,185],"address":[4,127],"the":[5,13,65,75,78,91,102,120,123,128,135,143,165,172,192],"problem":[6,24],"of":[7,15,34,46,77,93,104,122,130,137,145,191],"multiple":[8],"view":[9],"data":[10,68],"fusion":[11,51,95,103,177],"in":[12,53,142],"presence":[14,144],"noise":[16],"and":[17,113,139,152,178],"interferences.":[18,98],"Recent":[19],"studies":[20],"have":[21],"approached":[22],"using":[25],"kernel":[26,79,193],"methods,":[27],"by":[28,109,114],"relying":[29],"particularly":[30],"on":[31,60,90,164],"a":[32,42,54,61,81,110,115,188],"product":[33],"kernels":[35],"constructed":[36],"separately":[37],"for":[38,64,74,159],"each":[39],"view.":[40],"From":[41],"graph":[43],"theory":[44],"point":[45],"view,":[47],"analyze":[49],"approach":[52,96],"discrete":[55],"setting.":[56],"More":[57],"specifically,":[58],"based":[59,163],"statistical":[62],"model":[63],"connectivity":[66],"between":[67],"points,":[69],"propose":[71,156],"an":[72,157],"algorithm":[73,158,174],"selection":[76,190],"bandwidth,":[80],"parameter":[82],"that,":[83],"as":[84,149],"show,":[86],"has":[87],"important":[88],"implications":[89],"robustness":[92],"to":[97,119,197],"Then,":[99],"consider":[101],"audio-visual":[105,166],"speech":[106,138],"signals":[107],"measured":[108],"single":[111],"microphone":[112],"video":[116],"camera":[117],"pointed":[118],"face":[121],"speaker.":[124],"Specifically,":[125],"task":[129],"voice":[131,160,179],"activity":[132,161,180],"detection,":[133],"i.e.,":[134],"detection":[136,162,181],"nonspeech":[140],"segments,":[141],"structured":[146],"interferences":[147],"such":[148],"keyboard":[150],"taps":[151],"office":[153],"noise.":[154],"We":[155],"signal.":[167],"Simulation":[168],"results":[169],"show":[170],"that":[171,187],"proposed":[173],"outperforms":[175],"competing":[176],"approaches.":[182],"addition,":[184],"demonstrate":[186],"proper":[189],"bandwidth":[194],"indeed":[195],"leads":[196],"improved":[198],"performance.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}