{"id":"https://openalex.org/W3130435173","doi":"https://doi.org/10.23919/eusipco54536.2021.9616082","title":"On training targets for noise-robust voice activity detection","display_name":"On training targets for noise-robust voice activity detection","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W3130435173","doi":"https://doi.org/10.23919/eusipco54536.2021.9616082","mag":"3130435173"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9616082","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616082","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.07445","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055277441","display_name":"Sebastian Braun","orcid":"https://orcid.org/0000-0001-9060-223X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":true,"raw_author_name":"Sebastian Braun","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","(Microsoft)"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007425970","display_name":"Ivan Tashev","orcid":"https://orcid.org/0000-0002-2263-2047"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]},{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Ivan Tashev","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","(Microsoft)"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5055277441"],"corresponding_institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":0.3442,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.49663526,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"421","last_page":"425"},"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":0.9998000264167786,"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":0.9997000098228455,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8065921068191528},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.7872967720031738},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7460280656814575},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6781048774719238},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6744340062141418},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6362046003341675},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5250353813171387},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.45230889320373535},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3600701093673706},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3580305576324463},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10071465373039246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8065921068191528},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.7872967720031738},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7460280656814575},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6781048774719238},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6744340062141418},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6362046003341675},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5250353813171387},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.45230889320373535},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3600701093673706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3580305576324463},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10071465373039246},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9616082","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616082","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.07445","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.07445","pdf_url":"https://arxiv.org/pdf/2102.07445","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"","raw_type":"text"},{"id":"mag:3130435173","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2102.07445","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2102.07445","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2102.07445","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2102.07445","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.07445","pdf_url":"https://arxiv.org/pdf/2102.07445","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3130435173.pdf"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W48610814","https://openalex.org/W217932999","https://openalex.org/W1503398984","https://openalex.org/W1580555281","https://openalex.org/W1987048275","https://openalex.org/W1999454387","https://openalex.org/W2023582935","https://openalex.org/W2048497537","https://openalex.org/W2051428568","https://openalex.org/W2062335243","https://openalex.org/W2086381917","https://openalex.org/W2113751256","https://openalex.org/W2129120544","https://openalex.org/W2148030532","https://openalex.org/W2158336491","https://openalex.org/W2181253919","https://openalex.org/W2252254117","https://openalex.org/W2486913545","https://openalex.org/W2551314165","https://openalex.org/W2616492649","https://openalex.org/W2618825466","https://openalex.org/W2791616807","https://openalex.org/W2889442120","https://openalex.org/W2908510526","https://openalex.org/W2964199361","https://openalex.org/W3093964892","https://openalex.org/W3095173690","https://openalex.org/W3160129476","https://openalex.org/W3163464523","https://openalex.org/W6686245266","https://openalex.org/W6691726237","https://openalex.org/W6738603831","https://openalex.org/W6757817989"],"related_works":["https://openalex.org/W3193786050","https://openalex.org/W2309434858","https://openalex.org/W3094189801","https://openalex.org/W3048911900","https://openalex.org/W3198413490","https://openalex.org/W3088315586","https://openalex.org/W3160984956","https://openalex.org/W191108438","https://openalex.org/W2119564743","https://openalex.org/W2922358226","https://openalex.org/W3164223074","https://openalex.org/W2765164841","https://openalex.org/W2810852753","https://openalex.org/W3149225678","https://openalex.org/W3122264812","https://openalex.org/W3206706278","https://openalex.org/W2797972631","https://openalex.org/W3021188327","https://openalex.org/W2892204792","https://openalex.org/W3029282897"],"abstract_inverted_index":{"The":[0],"task":[1],"of":[2],"voice":[3],"activity":[4],"detection":[5],"(VAD)":[6],"is":[7,77],"an":[8],"often":[9,31],"required":[10],"module":[11],"in":[12],"various":[13],"speech":[14,88],"processing,":[15],"analysis":[16],"and":[17,35,68,80],"classification":[18],"tasks.":[19],"While":[20],"state-of-the-art":[21,52],"neural":[22],"network":[23,49],"based":[24,90],"VADs":[25],"can":[26],"achieve":[27],"great":[28],"results,":[29],"they":[30],"exceed":[32],"computational":[33],"budgets":[34],"real-time":[36,47],"operating":[37],"requirements.":[38],"In":[39],"this":[40],"work,":[41],"we":[42],"propose":[43],"a":[44,78],"computationally":[45],"efficient":[46],"VAD":[48,67],"that":[50,70,95],"achieves":[51],"results":[53],"on":[54],"several":[55],"public":[56],"real":[57],"recording":[58],"datasets.":[59],"We":[60,92],"investigate":[61],"different":[62],"training":[63,83,97],"targets":[64],"for":[65],"the":[66,72,86,99],"show":[69,94],"using":[71],"segmental":[73],"voice-to-noise":[74],"ratio":[75],"(VNR)":[76],"better":[79],"more":[81],"noise-robust":[82],"target":[84],"than":[85],"clean":[87],"level":[89],"VAD.":[91],"also":[93],"multi-target":[96],"improves":[98],"performance":[100],"further.":[101]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}