{"id":"https://openalex.org/W2404397424","doi":"https://doi.org/10.1109/taslp.2016.2566919","title":"Kernel Method for Voice Activity Detection in the Presence of Transients","display_name":"Kernel Method for Voice Activity Detection in the Presence of Transients","publication_year":2016,"publication_date":"2016-05-16","ids":{"openalex":"https://openalex.org/W2404397424","doi":"https://doi.org/10.1109/taslp.2016.2566919","mag":"2404397424"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2016.2566919","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2566919","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"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"],"raw_orcid":"https://orcid.org/0000-0003-4013-8306","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, The Technion-Israel Institute of Technology, Haifa, Israel","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"],"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"]}]},{"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"],"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"]}]}],"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":3.0009,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.92081421,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"24","issue":"12","first_page":"2313","last_page":"2326"},"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":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/metric","display_name":"Metric (unit)","score":0.6938717365264893},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6336787939071655},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6115403175354004},{"id":"https://openalex.org/keywords/euclidean-distance","display_name":"Euclidean distance","score":0.5912667512893677},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5550395846366882},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5394888520240784},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.530657172203064},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5261496901512146},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.49953722953796387},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.49055594205856323},{"id":"https://openalex.org/keywords/transient","display_name":"Transient (computer programming)","score":0.42702239751815796},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.41821280121803284},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37131360173225403},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34523439407348633},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2562568485736847},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.24091079831123352},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.22692513465881348},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0736134946346283}],"concepts":[{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6938717365264893},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6336787939071655},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6115403175354004},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.5912667512893677},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5550395846366882},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5394888520240784},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.530657172203064},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5261496901512146},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.49953722953796387},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.49055594205856323},{"id":"https://openalex.org/C2780799671","wikidata":"https://www.wikidata.org/wiki/Q17087362","display_name":"Transient (computer programming)","level":2,"score":0.42702239751815796},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.41821280121803284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37131360173225403},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34523439407348633},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2562568485736847},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.24091079831123352},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.22692513465881348},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0736134946346283},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2016.2566919","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2566919","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320308258","display_name":"Qualcomm","ror":"https://ror.org/002zrf773"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W15066456","https://openalex.org/W86846425","https://openalex.org/W1540596182","https://openalex.org/W1971071952","https://openalex.org/W1971375620","https://openalex.org/W1972265435","https://openalex.org/W1988147465","https://openalex.org/W1991167541","https://openalex.org/W1993583497","https://openalex.org/W1993911116","https://openalex.org/W2022186940","https://openalex.org/W2025168213","https://openalex.org/W2035395798","https://openalex.org/W2044002329","https://openalex.org/W2044359900","https://openalex.org/W2053186076","https://openalex.org/W2055671711","https://openalex.org/W2072195714","https://openalex.org/W2072219999","https://openalex.org/W2093402979","https://openalex.org/W2097308346","https://openalex.org/W2108819501","https://openalex.org/W2115717467","https://openalex.org/W2116810533","https://openalex.org/W2121292390","https://openalex.org/W2121947440","https://openalex.org/W2125027820","https://openalex.org/W2125290066","https://openalex.org/W2126942983","https://openalex.org/W2129120544","https://openalex.org/W2135780429","https://openalex.org/W2146324387","https://openalex.org/W2148154194","https://openalex.org/W2151484683","https://openalex.org/W2153309059","https://openalex.org/W2156838815","https://openalex.org/W2159856503","https://openalex.org/W2167023131","https://openalex.org/W2169147844","https://openalex.org/W2341944174","https://openalex.org/W2405672565","https://openalex.org/W2406066324","https://openalex.org/W4213367101","https://openalex.org/W4297792493","https://openalex.org/W6600593648","https://openalex.org/W6603527495","https://openalex.org/W6632267817","https://openalex.org/W6678885645","https://openalex.org/W6680237693","https://openalex.org/W6713782309","https://openalex.org/W6714222705"],"related_works":["https://openalex.org/W2349769824","https://openalex.org/W2914532148","https://openalex.org/W4313178214","https://openalex.org/W2372625757","https://openalex.org/W3093766508","https://openalex.org/W2012393389","https://openalex.org/W2159531755","https://openalex.org/W2893964920","https://openalex.org/W2888457666","https://openalex.org/W2953493266"],"abstract_inverted_index":{"Voice":[0],"activity":[1,47,185],"detection":[2,48,192],"in":[3,37,42,83,104],"the":[4,39,70,77,99,102,132,135,143,146,155,159,165],"presence":[5],"of":[6,101,134,145,183],"transient":[7],"interferences":[8],"is":[9,49,162],"a":[10,34,51,95,174,181],"challenging":[11],"problem":[12],"since":[13],"transients":[14,64,116],"are":[15],"often":[16,66],"detected":[17],"incorrectly":[18],"as":[19,138],"speech":[20,57,62,85,114,149],"by":[21,76,112,117,164,169],"existing":[22],"detectors.":[23,197],"In":[24],"this":[25,89,171],"paper,":[26],"we":[27,91,179],"deviate":[28],"from":[29],"traditional":[30],"approaches":[31],"and":[32,58,63,108,115,186],"take":[33],"geometric":[35],"standpoint,":[36],"which":[38],"key":[40],"element":[41],"obtaining":[43],"an":[44],"accurate":[45],"voice":[46,184],"finding":[50],"metric":[52,96,172],"that":[53,154],"appropriately":[54],"distinguishes":[55],"between":[56,158],"transients.":[59],"For":[60],"example,":[61],"may":[65,125],"appear":[67],"similar":[68],"through":[69],"Euclidean":[71,156],"distance":[72,157],"when":[73],"represented,":[74],"e.g.,":[75],"Mel-frequency":[78],"cepstral":[79],"coefficients,":[80],"thereby":[81],"resulting":[82],"incorrect":[84],"detection.":[86],"To":[87],"address":[88],"challenge,":[90],"propose":[92],"to":[93,128,190],"use":[94,111],"based":[97],"on":[98],"statistics":[100],"signal":[103,147],"short":[105],"temporal":[106],"windows":[107],"justify":[109],"its":[110],"modeling":[113],"their":[118],"latent":[119,123,160],"generating":[120],"variables.":[121],"These":[122],"variables":[124,161],"be":[126],"related":[127],"physical":[129],"constraints":[130],"controlling":[131],"generation":[133],"signal,":[136],"and,":[137],"such,":[139],"they":[140],"accurately":[141],"represent":[142],"content":[144],"-":[148],"or":[150],"transient.":[151],"We":[152],"show":[153,187],"approximated":[163],"proposed":[166],"metric.":[167],"Then,":[168],"incorporating":[170],"into":[173],"kernel-based":[175],"manifold":[176],"learning":[177],"method,":[178],"devise":[180],"measure":[182],"it":[188],"leads":[189],"improved":[191],"scores":[193],"compared":[194],"with":[195],"competing":[196]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}