{"id":"https://openalex.org/W3015820460","doi":"https://doi.org/10.1109/icassp40776.2020.9054610","title":"Evaluation of Deep-Learning-Based Voice Activity Detectors and Room Impulse Response Models in Reverberant Environments","display_name":"Evaluation of Deep-Learning-Based Voice Activity Detectors and Room Impulse Response Models in Reverberant Environments","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015820460","doi":"https://doi.org/10.1109/icassp40776.2020.9054610","mag":"3015820460"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054610","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054610","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2106.13511","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, Technion City, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Andrew and Erna Viterbi Faculty of Electrical Engineering, Technion - Israel Institute of Technology, Technion City, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","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, Technion City, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Andrew and Erna Viterbi Faculty of Electrical Engineering, Technion - Israel Institute of Technology, Technion City, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","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, Technion City, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Andrew and Erna Viterbi Faculty of Electrical Engineering, Technion - Israel Institute of Technology, Technion City, 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":0.493,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.56927484,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"107","issue":null,"first_page":"406","last_page":"410"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9994000196456909,"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/anechoic-chamber","display_name":"Anechoic chamber","score":0.870283842086792},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7149696350097656},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.6243469715118408},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.585058331489563},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.584272563457489},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5786674618721008},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.547988772392273},{"id":"https://openalex.org/keywords/impulse","display_name":"Impulse (physics)","score":0.5457519888877869},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.509425938129425},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3601911962032318},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.27771109342575073},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09066563844680786},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07065320014953613}],"concepts":[{"id":"https://openalex.org/C149712133","wikidata":"https://www.wikidata.org/wiki/Q332774","display_name":"Anechoic chamber","level":2,"score":0.870283842086792},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7149696350097656},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.6243469715118408},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.585058331489563},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.584272563457489},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5786674618721008},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.547988772392273},{"id":"https://openalex.org/C70836080","wikidata":"https://www.wikidata.org/wiki/Q837940","display_name":"Impulse (physics)","level":2,"score":0.5457519888877869},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.509425938129425},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3601911962032318},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.27771109342575073},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09066563844680786},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07065320014953613},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/icassp40776.2020.9054610","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054610","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2106.13511","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.13511","pdf_url":"https://arxiv.org/pdf/2106.13511","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:2106.13511","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.13511","pdf_url":"https://arxiv.org/pdf/2106.13511","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W46659105","https://openalex.org/W1499999342","https://openalex.org/W1968834101","https://openalex.org/W1992487647","https://openalex.org/W2006129368","https://openalex.org/W2023297907","https://openalex.org/W2043984641","https://openalex.org/W2053636381","https://openalex.org/W2117678320","https://openalex.org/W2150269048","https://openalex.org/W2166547995","https://openalex.org/W2242685705","https://openalex.org/W2400112243","https://openalex.org/W2404892923","https://openalex.org/W2696967604","https://openalex.org/W2734695582","https://openalex.org/W2791616807","https://openalex.org/W2889467522","https://openalex.org/W2917987043","https://openalex.org/W2928746352","https://openalex.org/W6602002561"],"related_works":["https://openalex.org/W2169567031","https://openalex.org/W2001172292","https://openalex.org/W2732511158","https://openalex.org/W2987432963","https://openalex.org/W2053167664","https://openalex.org/W2079152323","https://openalex.org/W2128388559","https://openalex.org/W2082664169","https://openalex.org/W2272518678","https://openalex.org/W2140267235"],"abstract_inverted_index":{"State-of-the-art":[0],"deep-learning-based":[1],"voice":[2],"activity":[3],"detectors":[4,118],"(VADs)":[5],"are":[6,16,86],"often":[7],"trained":[8,87,96],"with":[9,65,88],"anechoic":[10,52,63,124],"data.":[11],"However,":[12],"real":[13,34,101],"acoustic":[14],"environments":[15],"generally":[17],"reverberant,":[18],"which":[19],"causes":[20],"the":[21,62,89,129,137,142,148,152],"performance":[22,135],"to":[23,78,123],"significantly":[24],"deteriorate.":[25],"To":[26],"mitigate":[27],"this":[28],"mismatch":[29],"between":[30],"training":[31,40,91],"data":[32],"and":[33,54,81,114,119],"data,":[35],"we":[36],"simulate":[37],"an":[38],"augmented":[39,90],"set":[41],"that":[42,85],"contains":[43],"nearly":[44],"five":[45,75,82],"million":[46],"utterances.":[47],"This":[48],"extension":[49],"comprises":[50],"of":[51,61,68,128,147],"utterances":[53,64],"their":[55],"reverberant":[56,102],"modifications,":[57],"generated":[58],"by":[59],"convolutions":[60],"a":[66],"variety":[67],"room":[69],"impulse":[70],"responses":[71],"(RIRs).":[72],"We":[73,93],"consider":[74],"different":[76,83,100],"models":[77,131],"generate":[79],"RIRs,":[80],"VADs":[84,149,154],"set.":[92],"test":[94],"all":[95,117,141,156],"systems":[97],"in":[98,111,155],"three":[99],"environments.":[103],"Experimental":[104],"results":[105],"show":[106],"20%":[107],"increase":[108],"on":[109],"average":[110],"accuracy,":[112],"precision":[113],"recall":[115],"for":[116,140],"response":[120],"models,":[121,139],"compared":[122],"training.":[125],"Furthermore,":[126],"one":[127,146],"RIR":[130],"consistently":[132,150],"yields":[133],"better":[134],"than":[136],"other":[138,153],"tested":[143],"VADs.":[144],"Additionally,":[145],"outperformed":[151],"experiments.":[157]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}