{"id":"https://openalex.org/W2928746352","doi":"https://doi.org/10.1109/jstsp.2019.2909472","title":"Voice Activity Detection for Transient Noisy Environment Based on Diffusion Nets","display_name":"Voice Activity Detection for Transient Noisy Environment Based on Diffusion Nets","publication_year":2019,"publication_date":"2019-04-04","ids":{"openalex":"https://openalex.org/W2928746352","doi":"https://doi.org/10.1109/jstsp.2019.2909472","mag":"2928746352"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2019.2909472","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2019.2909472","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"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 Journal of Selected Topics in 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/2106.13763","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080988947","display_name":"Amir Ivry","orcid":"https://orcid.org/0000-0002-9043-7040"},"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":"Amir Ivry","raw_affiliation_strings":["Andrew and Erna Viterbi Faculty of Electrical Engineering, Technion-Israel Institute of Technology, Haifa, Israel"],"raw_orcid":"https://orcid.org/0000-0002-9043-7040","affiliations":[{"raw_affiliation_string":"Andrew and Erna Viterbi Faculty of Electrical Engineering, Technion-Israel Institute of Technology, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087178413","display_name":"Baruch Berdugo","orcid":null},"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":"Baruch Berdugo","raw_affiliation_strings":["Andrew and Erna Viterbi Faculty of Electrical Engineering, Technion-Israel Institute of Technology, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Andrew and Erna Viterbi Faculty of Electrical Engineering, 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":["Andrew and Erna Viterbi Faculty of Electrical Engineering, Technion-Israel Institute of Technology, Haifa, Israel"],"raw_orcid":"https://orcid.org/0000-0002-2556-3972","affiliations":[{"raw_affiliation_string":"Andrew and Erna Viterbi Faculty of Electrical Engineering, 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":3.2444,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.92640101,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"13","issue":"2","first_page":"254","last_page":"264"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9993000030517578,"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"}},{"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6647866368293762},{"id":"https://openalex.org/keywords/transient","display_name":"Transient (computer programming)","score":0.5798463225364685},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5039703249931335},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4206628203392029},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3382965624332428},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09962239861488342}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6647866368293762},{"id":"https://openalex.org/C2780799671","wikidata":"https://www.wikidata.org/wiki/Q17087362","display_name":"Transient (computer programming)","level":2,"score":0.5798463225364685},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5039703249931335},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4206628203392029},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3382965624332428},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09962239861488342},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/jstsp.2019.2909472","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2019.2909472","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"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 Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2106.13763","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.13763","pdf_url":"https://arxiv.org/pdf/2106.13763","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:2106.13763","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.13763","pdf_url":"https://arxiv.org/pdf/2106.13763","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":[],"awards":[{"id":"https://openalex.org/G3043769438","display_name":null,"funder_award_id":"2514/17","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3892960400","display_name":null,"funder_award_id":"576/16","funder_id":"https://openalex.org/F4320322252","funder_display_name":"Israel Science Foundation"},{"id":"https://openalex.org/G6578510685","display_name":null,"funder_award_id":"2514/17","funder_id":"https://openalex.org/F4320313643","funder_display_name":"Iowa Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320313643","display_name":"Iowa Science Foundation","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322252","display_name":"Israel Science Foundation","ror":"https://ror.org/04sazxf24"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W15066456","https://openalex.org/W82246966","https://openalex.org/W183625566","https://openalex.org/W1484721950","https://openalex.org/W1532436422","https://openalex.org/W1583001605","https://openalex.org/W1963586106","https://openalex.org/W1963766113","https://openalex.org/W1971553366","https://openalex.org/W1993583497","https://openalex.org/W2011975968","https://openalex.org/W2014569347","https://openalex.org/W2025168213","https://openalex.org/W2044002329","https://openalex.org/W2048497537","https://openalex.org/W2053603770","https://openalex.org/W2072219999","https://openalex.org/W2090857812","https://openalex.org/W2095705004","https://openalex.org/W2103749544","https://openalex.org/W2108289863","https://openalex.org/W2108759471","https://openalex.org/W2108819501","https://openalex.org/W2115717467","https://openalex.org/W2120480179","https://openalex.org/W2126942983","https://openalex.org/W2129111551","https://openalex.org/W2129120544","https://openalex.org/W2131833400","https://openalex.org/W2143612262","https://openalex.org/W2146324387","https://openalex.org/W2148154194","https://openalex.org/W2150125142","https://openalex.org/W2152322845","https://openalex.org/W2158146178","https://openalex.org/W2326151537","https://openalex.org/W2404397424","https://openalex.org/W2405774341","https://openalex.org/W2734695582","https://openalex.org/W3103521248","https://openalex.org/W3137491246","https://openalex.org/W4210942470","https://openalex.org/W4213367101","https://openalex.org/W4245923654","https://openalex.org/W6600593648","https://openalex.org/W6603377551","https://openalex.org/W6631903231","https://openalex.org/W6661168634","https://openalex.org/W6713658392","https://openalex.org/W6779582393"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"We":[0,19,154],"address":[1],"voice":[2,124],"activity":[3,125],"detection":[4,126],"in":[5,16,132,142],"acoustic":[6],"environments":[7],"of":[8,24],"transients":[9],"and":[10,26,136,146],"stationary":[11],"noises,":[12],"which":[13,64,92],"often":[14],"occur":[15],"real-life":[17],"scenarios.":[18],"exploit":[20],"unique":[21],"spatial":[22],"patterns":[23],"speech":[25,97],"non-speech":[27,99],"audio":[28],"frames":[29],"by":[30,67,103],"independently":[31],"learning":[32],"their":[33,61],"underlying":[34],"geometric":[35],"structure.":[36],"This":[37,48],"process":[38],"is":[39,93,101,130],"done":[40],"through":[41],"a":[42,76,143,157],"deep":[43,89],"encoder-decoder-based":[44],"neural":[45,90],"network":[46],"architecture.":[47,115],"structure":[49],"involves":[50],"an":[51,162],"encoder":[52,74],"that":[53,78,160],"maps":[54,71,79],"spectral":[55],"features":[56],"with":[57],"temporal":[58],"information":[59],"to":[60,95,107,122],"low-dimensional":[62],"representations,":[63],"are":[65],"generated":[66],"applying":[68],"the":[69,80,85,105,108,111],"diffusion":[70,113],"method.":[72],"The":[73,128],"feeds":[75],"decoder":[77,106],"embedded":[81],"data":[82],"back":[83],"into":[84,150],"high-dimensional":[86],"space.":[87],"A":[88],"network,":[91],"trained":[94],"separate":[96],"from":[98],"frames,":[100],"obtained":[102],"concatenating":[104],"encoder,":[109],"resembling":[110],"known":[112],"nets":[114],"Experimental":[116],"results":[117],"show":[118],"enhanced":[119],"performance":[120],"compared":[121],"competing":[123],"methods.":[127],"improvement":[129],"achieved":[131],"both":[133],"accuracy,":[134],"robustness,":[135],"generalization":[137],"ability.":[138],"Our":[139],"model":[140],"performs":[141],"real-time":[144],"manner":[145],"can":[147],"be":[148],"integrated":[149],"audio-based":[151],"communication":[152],"systems.":[153],"also":[155],"present":[156],"batch":[158],"algorithm":[159],"obtains":[161],"even":[163],"higher":[164],"accuracy":[165],"for":[166],"offline":[167],"applications.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2019-04-11T00:00:00"}