{"id":"https://openalex.org/W2007119422","doi":"https://doi.org/10.1109/icassp.2013.6639066","title":"A practical, self-adaptive voice activity detector for speaker verification with noisy telephone and microphone data","display_name":"A practical, self-adaptive voice activity detector for speaker verification with noisy telephone and microphone data","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2007119422","doi":"https://doi.org/10.1109/icassp.2013.6639066","mag":"2007119422"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5043168931","display_name":"Tomi Kinnunen","orcid":"https://orcid.org/0000-0002-4371-7322"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tomi Kinnunen","raw_affiliation_strings":["School of Computing, University of Eastern Finland, Joensuu, Finland","Sch. of Comput., Univ. of Eastern Finland (UEF), Joensuu, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, University of Eastern Finland, Joensuu, Finland","institution_ids":["https://openalex.org/I175532246"]},{"raw_affiliation_string":"Sch. of Comput., Univ. of Eastern Finland (UEF), Joensuu, Finland","institution_ids":["https://openalex.org/I175532246"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078300199","display_name":"P.K. Rajan","orcid":"https://orcid.org/0000-0002-9178-3885"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Padmanabhan Rajan","raw_affiliation_strings":["School of Computing, University of Eastern Finland, Joensuu, Finland","Sch. of Comput., Univ. of Eastern Finland (UEF), Joensuu, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, University of Eastern Finland, Joensuu, Finland","institution_ids":["https://openalex.org/I175532246"]},{"raw_affiliation_string":"Sch. of Comput., Univ. of Eastern Finland (UEF), Joensuu, Finland","institution_ids":["https://openalex.org/I175532246"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I175532246"],"apc_list":null,"apc_paid":null,"fwci":8.4534,"has_fulltext":false,"cited_by_count":105,"citation_normalized_percentile":{"value":0.98533043,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":"34","issue":null,"first_page":"7229","last_page":"7233"},"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":0.9991999864578247,"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/speech-recognition","display_name":"Speech recognition","score":0.8148316740989685},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8068028092384338},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7095596790313721},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7060736417770386},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6830921173095703},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5677194595336914},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.5571296215057373},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5105503797531128},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4974963963031769},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.473394513130188},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43075665831565857},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.4237721562385559},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35877618193626404},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2671521008014679},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2041817605495453},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07645046710968018},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0728178322315216}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8148316740989685},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8068028092384338},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7095596790313721},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7060736417770386},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6830921173095703},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5677194595336914},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.5571296215057373},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5105503797531128},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4974963963031769},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.473394513130188},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43075665831565857},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.4237721562385559},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35877618193626404},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2671521008014679},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2041817605495453},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07645046710968018},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0728178322315216},{"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/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2013.6639066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.299.3984","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.299.3984","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.joensuu.fi/pages/tkinnu/webpage/pdf/adaptive_vad.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W90546637","https://openalex.org/W110483337","https://openalex.org/W1540327379","https://openalex.org/W1582867372","https://openalex.org/W1601795611","https://openalex.org/W1903422462","https://openalex.org/W1967332585","https://openalex.org/W2051428568","https://openalex.org/W2097464745","https://openalex.org/W2118097082","https://openalex.org/W2121750345","https://openalex.org/W2129120544","https://openalex.org/W2132498366","https://openalex.org/W2149053750","https://openalex.org/W2149535104","https://openalex.org/W2150769028","https://openalex.org/W2154278880","https://openalex.org/W2156798212","https://openalex.org/W2158336491","https://openalex.org/W2159786793","https://openalex.org/W2395750323","https://openalex.org/W2407342067","https://openalex.org/W4297989434","https://openalex.org/W6632370842"],"related_works":["https://openalex.org/W2557377817","https://openalex.org/W2012540220","https://openalex.org/W2088699022","https://openalex.org/W2548243992","https://openalex.org/W2189089965","https://openalex.org/W2189022995","https://openalex.org/W2309686023","https://openalex.org/W2010378435","https://openalex.org/W110044914","https://openalex.org/W236686179"],"abstract_inverted_index":{"A":[0],"voice":[1],"activity":[2],"detector":[3],"(VAD)":[4],"plays":[5],"a":[6,116],"vital":[7],"role":[8],"in":[9,24,29],"robust":[10],"speaker":[11,101],"verification,":[12],"where":[13],"energy":[14,73,112],"VAD":[15,21,50,97,113],"is":[16,37],"most":[17],"commonly":[18],"used.":[19],"Energy":[20],"works":[22],"well":[23],"noise-free":[25],"conditions":[26],"but":[27],"deteriorates":[28],"noisy":[30],"conditions.":[31],"One":[32],"way":[33],"to":[34,38,95],"tackle":[35],"this":[36],"introduce":[39],"speech":[40,53,77],"enhancement":[41],"preprocessing.":[42],"We":[43,119],"study":[44],"an":[45,58],"alternative,":[46],"likelihood":[47],"ratio":[48],"based":[49],"that":[51],"trains":[52],"and":[54,78,100],"nonspeech":[55,79],"models":[56,80],"on":[57],"utterance-by-utterance":[59],"basis":[60],"from":[61,71],"mel-frequency":[62],"cepstral":[63],"coefficients":[64],"(MFCCs).":[65],"The":[66],"training":[67],"labels":[68],"are":[69,81,92],"obtained":[70],"enhanced":[72],"VAD.":[74],"As":[75],"the":[76,89,108,124],"re-trained":[82],"for":[83],"each":[84],"utterance,":[85],"minimum":[86],"assumptions":[87],"of":[88,123],"background":[90],"noise":[91],"made.":[93],"According":[94],"both":[96],"error":[98],"analysis":[99],"verification":[102],"results":[103],"utilizing":[104],"state-of-the-art":[105],"i-vector":[106],"system,":[107],"proposed":[109],"method":[110],"outperforms":[111],"variants":[114],"by":[115],"wide":[117],"margin.":[118],"provide":[120],"open-source":[121],"implementation":[122],"method.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":21},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}