{"id":"https://openalex.org/W2995588677","doi":"https://doi.org/10.1109/lsp.2019.2959917","title":"Spectro-Temporal Attention-Based Voice Activity Detection","display_name":"Spectro-Temporal Attention-Based Voice Activity Detection","publication_year":2019,"publication_date":"2019-12-17","ids":{"openalex":"https://openalex.org/W2995588677","doi":"https://doi.org/10.1109/lsp.2019.2959917","mag":"2995588677"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2019.2959917","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2019.2959917","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","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/A5024990167","display_name":"Younglo Lee","orcid":"https://orcid.org/0000-0002-0725-3444"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Younglo Lee","raw_affiliation_strings":["School of Electrical Engineering, Korea University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103015610","display_name":"Jeongki Min","orcid":"https://orcid.org/0000-0001-5995-7200"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jeongki Min","raw_affiliation_strings":["School of Electrical Engineering, Korea University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102000970","display_name":"David K. Han","orcid":"https://orcid.org/0000-0001-5055-5408"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David K. Han","raw_affiliation_strings":["Information Science Division, US Army Research Laboratory, Adelphi, MD, USA"],"affiliations":[{"raw_affiliation_string":"Information Science Division, US Army Research Laboratory, Adelphi, MD, USA","institution_ids":["https://openalex.org/I166416128"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026204977","display_name":"Hanseok Ko","orcid":"https://orcid.org/0000-0002-8744-4514"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hanseok Ko","raw_affiliation_strings":["School of Electrical Engineering, Korea University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5024990167"],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":2.4879,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.90450473,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"27","issue":null,"first_page":"131","last_page":"135"},"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":0.9997000098228455,"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":0.9994999766349792,"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":0.7764005064964294},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.734907329082489},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6127752065658569},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5491011142730713},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5480981469154358},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.5280968546867371},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5054492950439453},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.4867537021636963},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4487916827201843},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.413438081741333},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39677876234054565},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3340719938278198},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.18514129519462585},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0786028504371643}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7764005064964294},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.734907329082489},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6127752065658569},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5491011142730713},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5480981469154358},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.5280968546867371},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5054492950439453},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.4867537021636963},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4487916827201843},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.413438081741333},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39677876234054565},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3340719938278198},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.18514129519462585},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0786028504371643},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2019.2959917","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2019.2959917","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5199999809265137}],"awards":[],"funders":[{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1495679096","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1635512741","https://openalex.org/W1836465849","https://openalex.org/W1974387177","https://openalex.org/W1985242443","https://openalex.org/W1999454387","https://openalex.org/W2007119422","https://openalex.org/W2048497537","https://openalex.org/W2095705004","https://openalex.org/W2133564696","https://openalex.org/W2151484683","https://openalex.org/W2197404611","https://openalex.org/W2519091744","https://openalex.org/W2567070169","https://openalex.org/W2727244960","https://openalex.org/W2738707637","https://openalex.org/W2767895109","https://openalex.org/W2791616807","https://openalex.org/W2792351646","https://openalex.org/W2892300106","https://openalex.org/W2917987043","https://openalex.org/W2919115771","https://openalex.org/W2949382160","https://openalex.org/W2954930777","https://openalex.org/W2963403868","https://openalex.org/W2963970792","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2964308564","https://openalex.org/W3101648800","https://openalex.org/W4253928870","https://openalex.org/W4385245566","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6679434410","https://openalex.org/W6731370813","https://openalex.org/W6739901393","https://openalex.org/W6785749098"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2373767407","https://openalex.org/W4200596008","https://openalex.org/W1585241115","https://openalex.org/W2248536413","https://openalex.org/W2383417046","https://openalex.org/W4386336391","https://openalex.org/W4206754781","https://openalex.org/W3217417050","https://openalex.org/W2187296505"],"abstract_inverted_index":{"Voice":[0],"Activity":[1],"Detection":[2],"(VAD)":[3],"systems":[4],"suffer":[5],"from":[6],"unexpected":[7,128],"and":[8,60,75,99],"non-stationary":[9],"background":[10,42],"noises":[11],"at":[12],"magnitudes":[13],"sufficiently":[14],"high":[15],"to":[16,36],"mask":[17],"the":[18,25,38,41,86,89,107,111,116],"speech":[19],"signal.Although":[20],"several":[21,78],"methods":[22,82,113],"of":[23,27,40,85,125],"increasing":[24],"performance":[26],"VAD":[28,51],"have":[29,34],"been":[30],"proposed,":[31],"their":[32],"approaches":[33],"yet":[35],"mitigate":[37],"influence":[39],"noise":[43],"itself.":[44],"This":[45],"letter":[46],"proposes":[47],"an":[48],"effective":[49],"noise-robust":[50],"system":[52],"approach.":[53],"The":[54,70,103],"proposed":[55,71,108],"method":[56,72,109],"uses":[57],"spectral":[58],"attention":[59,62,68],"temporal":[61],"through":[63],"applying":[64],"a":[65],"deep":[66,80],"learning-based":[67,81],"mechanism.":[69],"is":[73],"demonstrated":[74],"compared":[76],"with":[77,93],"other":[79,112],"in":[83,91,114,123],"terms":[84],"area":[87],"under":[88],"curve":[90],"experiments":[92],"either":[94],"known":[95],"or":[96,127],"unknown":[97,126],"noise-added,":[98],"real-world":[100],"noisy":[101],"data.":[102],"results":[104],"show":[105],"that":[106],"outperforms":[110],"all":[115],"scenarios":[117],"considered,":[118],"but":[119],"moreover":[120],"generalizes":[121],"well":[122],"environments":[124],"noise.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}