{"id":"https://openalex.org/W1580555281","doi":"https://doi.org/10.1109/taslp.2015.2476762","title":"Formant-Based Robust Voice Activity Detection","display_name":"Formant-Based Robust Voice Activity Detection","publication_year":2015,"publication_date":"2015-09-03","ids":{"openalex":"https://openalex.org/W1580555281","doi":"https://doi.org/10.1109/taslp.2015.2476762","mag":"1580555281"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2015.2476762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2476762","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","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/A5068783691","display_name":"In-Chul Yoo","orcid":"https://orcid.org/0000-0001-7129-047X"},"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":"In-Chul Yoo","raw_affiliation_strings":["Department of Computer Science and Engineering, Korea University, Seoul, Republic of Korea","[Speech Information Processing Laboratory, Department of Computer Science and Engineering, Korea University, Seoul, Republic of Korea]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"[Speech Information Processing Laboratory, Department of Computer Science and Engineering, Korea University, Seoul, Republic of Korea]","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050218314","display_name":"Hyeontaek Lim","orcid":null},"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":"Hyeontaek Lim","raw_affiliation_strings":["Department of Computer Science and Engineering, Korea University, Seoul, Republic of Korea","Speech Information Processing Laboratory, Department of Computer Science and Engineering, Korea University, Seoul, Korea#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Speech Information Processing Laboratory, Department of Computer Science and Engineering, Korea University, Seoul, Korea#TAB#","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039833822","display_name":"Dongsuk Yook","orcid":"https://orcid.org/0000-0003-2445-2354"},"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":"Dongsuk Yook","raw_affiliation_strings":["Department of Computer Science and Engineering, Korea University, Seoul, Republic of Korea","[Speech Information Processing Laboratory, Department of Computer Science and Engineering, Korea University, Seoul, Republic of Korea]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"[Speech Information Processing Laboratory, Department of Computer Science and Engineering, Korea University, Seoul, Republic of Korea]","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":5.6848,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.9652843,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"23","issue":"12","first_page":"2238","last_page":"2245"},"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9994999766349792,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.9555062055587769},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7216233015060425},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.7177431583404541},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.713363766670227},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6320382356643677},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.5896466970443726},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4530066251754761},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.429085910320282},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4193209707736969},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.4191704988479614},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.410776823759079},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32395443320274353},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27589115500450134},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.27271348237991333},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14669868350028992},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13907471299171448}],"concepts":[{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.9555062055587769},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7216233015060425},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.7177431583404541},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.713363766670227},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6320382356643677},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.5896466970443726},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4530066251754761},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.429085910320282},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4193209707736969},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.4191704988479614},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.410776823759079},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32395443320274353},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27589115500450134},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.27271348237991333},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14669868350028992},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13907471299171448},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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":1,"locations":[{"id":"doi:10.1109/taslp.2015.2476762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2476762","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8199999928474426,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W100158151","https://openalex.org/W104146226","https://openalex.org/W1499159714","https://openalex.org/W1985242443","https://openalex.org/W1992153276","https://openalex.org/W1993449980","https://openalex.org/W2009422037","https://openalex.org/W2020969069","https://openalex.org/W2032474878","https://openalex.org/W2039851008","https://openalex.org/W2045920613","https://openalex.org/W2055144209","https://openalex.org/W2072219999","https://openalex.org/W2074724747","https://openalex.org/W2097036989","https://openalex.org/W2108367224","https://openalex.org/W2126693545","https://openalex.org/W2129120544","https://openalex.org/W2142283335","https://openalex.org/W2151484683","https://openalex.org/W2152395643","https://openalex.org/W2156038773","https://openalex.org/W2170116036","https://openalex.org/W2170644918","https://openalex.org/W2179460223","https://openalex.org/W2619993508","https://openalex.org/W3127686677","https://openalex.org/W4285719527","https://openalex.org/W6604254391","https://openalex.org/W6660565398","https://openalex.org/W6789826613"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W2248536413","https://openalex.org/W2383417046","https://openalex.org/W4386336391","https://openalex.org/W3217417050","https://openalex.org/W2187296505"],"abstract_inverted_index":{"Voice":[0],"activity":[1,142],"detection":[2,143],"(VAD)":[3],"can":[4,17],"be":[5],"used":[6],"to":[7,64,107,124,154,177],"distinguish":[8,108],"human":[9,41,100],"speech":[10,21,24,42],"from":[11,19,158],"other":[12],"sounds,":[13],"and":[14,23,57,102,134,198,217],"various":[15,204,213,230],"applications":[16],"benefit":[18],"VAD-including":[20],"coding":[22],"recognition.":[25],"To":[26],"accurately":[27,155],"detect":[28],"voice":[29,141],"activity,":[30],"the":[31,37,66,94,99,114,179],"algorithm":[32,176],"must":[33],"take":[34],"into":[35],"account":[36],"characteristic":[38],"features":[39,139],"of":[40,68,98,113,181,215],"and/or":[43],"background":[44,162],"noise.":[45,188],"In":[46],"many":[47],"real-life":[48,90],"applications,":[49],"noise":[50,69,85,163,205,216],"frequently":[51],"occurs":[52],"in":[53,58,126,229],"an":[54],"unexpected":[55],"manner,":[56],"such":[59,118],"situations,":[60],"it":[61,151,224],"is":[62,152,210,225],"difficult":[63,153],"determine":[65],"characteristics":[67,112],"with":[70,186],"sufficient":[71],"accuracy.":[72],"As":[73],"a":[74,127,172,193,219],"result,":[75],"robust":[76,211],"VAD":[77,175,201],"algorithms":[78,202],"that":[79],"depend":[80],"less":[81],"on":[82],"making":[83],"correct":[84],"estimates":[86],"are":[87,93,104,117,122,137],"desirable":[88],"for":[89,140,227],"applications.":[91,231],"Formants":[92],"major":[95],"spectral":[96,115,166],"peaks":[97,116,121],"voice,":[101],"these":[103,120],"highly":[105],"useful":[106],"vowel":[109],"sounds.":[110],"The":[111,189,207],"that,":[119],"likely":[123],"survive":[125],"signal":[128],"after":[129],"severe":[130,187],"corruption":[131],"by":[132],"noise,":[133],"so":[135,223],"formants":[136,157,183],"attractive":[138],"under":[144,184,203],"low":[145],"signal-to-noise":[146],"ratio":[147],"(SNR)":[148],"conditions.":[149,206],"However,":[150],"extract":[156],"noisy":[159],"signals":[160],"when":[161],"introduces":[164],"unrelated":[165],"peaks.":[167],"Therefore,":[168],"this":[169],"paper":[170],"proposes":[171],"simple":[173],"formant-based":[174],"overcome":[178],"problem":[180],"detecting":[182],"conditions":[185],"proposed":[190,208],"method":[191,209],"achieves":[192],"much":[194],"faster":[195],"processing":[196],"time":[197],"outperforms":[199],"standard":[200],"against":[212],"types":[214],"produces":[218],"light":[220],"computational":[221],"load,":[222],"suitable":[226],"use":[228]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":9},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}