{"id":"https://openalex.org/W2791616807","doi":"https://doi.org/10.1109/lsp.2018.2811740","title":"Voice Activity Detection Using an Adaptive Context Attention Model","display_name":"Voice Activity Detection Using an Adaptive Context Attention Model","publication_year":2018,"publication_date":"2018-03-08","ids":{"openalex":"https://openalex.org/W2791616807","doi":"https://doi.org/10.1109/lsp.2018.2811740","mag":"2791616807"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2018.2811740","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2018.2811740","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/A5100710223","display_name":"Juntae Kim","orcid":"https://orcid.org/0000-0003-3344-4591"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Juntae Kim","raw_affiliation_strings":["School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046372250","display_name":"Minsoo Hahn","orcid":"https://orcid.org/0000-0003-1953-6078"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minsoo Hahn","raw_affiliation_strings":["School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100710223"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":8.4826,"has_fulltext":false,"cited_by_count":100,"citation_normalized_percentile":{"value":0.98365992,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"25","issue":"8","first_page":"1181","last_page":"1185"},"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":0.9987999796867371,"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":0.8328406810760498},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7352514266967773},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.7266984581947327},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6662402153015137},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6480851173400879},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.45756179094314575},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4542678892612457},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4469199478626251},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41000449657440186},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.37466201186180115},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3679323196411133},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3287196755409241},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.29825359582901}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8328406810760498},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7352514266967773},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.7266984581947327},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6662402153015137},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6480851173400879},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.45756179094314575},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4542678892612457},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4469199478626251},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41000449657440186},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.37466201186180115},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3679323196411133},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3287196755409241},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.29825359582901},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2018.2811740","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2018.2811740","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":[{"display_name":"Peace, Justice and strong institutions","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1365554128","display_name":null,"funder_award_id":"10076757","funder_id":"https://openalex.org/F4320321681","funder_display_name":"Ministry of Trade, Industry and Energy"}],"funders":[{"id":"https://openalex.org/F4320321681","display_name":"Ministry of Trade, Industry and Energy","ror":"https://ror.org/008nkqk13"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W149260027","https://openalex.org/W854541894","https://openalex.org/W1484210532","https://openalex.org/W1522301498","https://openalex.org/W1580555281","https://openalex.org/W1646152356","https://openalex.org/W1836465849","https://openalex.org/W1905983571","https://openalex.org/W1974387177","https://openalex.org/W1999454387","https://openalex.org/W2009450152","https://openalex.org/W2020969069","https://openalex.org/W2022186940","https://openalex.org/W2023582935","https://openalex.org/W2048497537","https://openalex.org/W2059203007","https://openalex.org/W2062335243","https://openalex.org/W2081345242","https://openalex.org/W2095705004","https://openalex.org/W2097998348","https://openalex.org/W2113751256","https://openalex.org/W2117468249","https://openalex.org/W2126693545","https://openalex.org/W2129120544","https://openalex.org/W2142170306","https://openalex.org/W2149053750","https://openalex.org/W2156876426","https://openalex.org/W2197404611","https://openalex.org/W2240641835","https://openalex.org/W2337024056","https://openalex.org/W2405388169","https://openalex.org/W2406262283","https://openalex.org/W2510670092","https://openalex.org/W2513345070","https://openalex.org/W2551314165","https://openalex.org/W2578422401","https://openalex.org/W2727244960","https://openalex.org/W2951527505","https://openalex.org/W2963980515","https://openalex.org/W3007258144","https://openalex.org/W3127686677","https://openalex.org/W6606116054","https://openalex.org/W6623517193","https://openalex.org/W6628927728","https://openalex.org/W6631190155","https://openalex.org/W6636774829","https://openalex.org/W6638667902","https://openalex.org/W6674330103","https://openalex.org/W6674385629","https://openalex.org/W6682137061","https://openalex.org/W6683161558","https://openalex.org/W6713752823","https://openalex.org/W6780226713","https://openalex.org/W6789826613"],"related_works":["https://openalex.org/W2294333436","https://openalex.org/W2653598178","https://openalex.org/W2747006289","https://openalex.org/W2072884270","https://openalex.org/W4252682934","https://openalex.org/W2356426224","https://openalex.org/W2734909224","https://openalex.org/W2124849039","https://openalex.org/W2851491717","https://openalex.org/W2550583663"],"abstract_inverted_index":{"Voice":[0],"activity":[1],"detection":[2],"(VAD)":[3],"classifies":[4],"incoming":[5],"signal":[6],"segments":[7],"into":[8],"speech":[9],"or":[10],"background":[11],"noise;":[12],"its":[13,29,37],"performance":[14],"is":[15,24],"crucial":[16,75],"in":[17,32,84],"various":[18],"speech-related":[19],"applications.":[20],"Although":[21],"speech-signal":[22],"context":[23,53,59,79],"a":[25,64],"relevant":[26],"VAD":[27,92,97],"asset,":[28],"usefulness":[30],"varies":[31],"unpredictable":[33],"noise":[34,45],"environments.":[35],"Therefore,":[36],"usage":[38],"should":[39],"be":[40],"adaptively":[41],"adjustable":[42],"to":[43],"the":[44,50,73,78,89,94],"type.":[46],"This":[47],"letter":[48],"improves":[49],"use":[51],"of":[52,77],"information":[54],"by":[55],"using":[56],"an":[57],"adaptive":[58],"attention":[60],"model":[61],"(ACAM)":[62],"with":[63],"novel":[65],"training":[66],"strategy":[67],"for":[68,80],"effective":[69],"attention,":[70],"which":[71],"weights":[72],"most":[74],"parts":[76],"proper":[81],"classification.":[82],"Experiments":[83],"real-world":[85],"scenarios":[86],"demonstrate":[87],"that":[88],"proposed":[90],"ACAM-based":[91],"outperforms":[93],"other":[95],"baseline":[96],"methods.":[98]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}