{"id":"https://openalex.org/W1913419478","doi":"https://doi.org/10.1109/ita.2015.7308991","title":"Offline Voice Activity Detector using speech supergaussianity","display_name":"Offline Voice Activity Detector using speech supergaussianity","publication_year":2015,"publication_date":"2015-02-01","ids":{"openalex":"https://openalex.org/W1913419478","doi":"https://doi.org/10.1109/ita.2015.7308991","mag":"1913419478"},"language":"en","primary_location":{"id":"doi:10.1109/ita.2015.7308991","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ita.2015.7308991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Information Theory and Applications Workshop (ITA)","raw_type":"proceedings-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/A5007425970","display_name":"Ivan Tashev","orcid":"https://orcid.org/0000-0002-2263-2047"},"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"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ivan J. Tashev","raw_affiliation_strings":["Microsoft Research Labs One Microsoft Way, Redmond, WA, USA","Microsoft Research Labs, One Microsoft Way, Redmond, WA 98051, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Labs One Microsoft Way, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research Labs, One Microsoft Way, Redmond, WA 98051, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5007425970"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":0.2872,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.53929571,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"18","issue":null,"first_page":"214","last_page":"219"},"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":0.9991999864578247,"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"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.8008372783660889},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7821182012557983},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7338128685951233},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6657720804214478},{"id":"https://openalex.org/keywords/bin","display_name":"Bin","score":0.5410988926887512},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5373702049255371},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5062481760978699},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5038766264915466},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.49411943554878235},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4519663453102112},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.413013756275177},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38973772525787354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26874423027038574},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08300912380218506}],"concepts":[{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.8008372783660889},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7821182012557983},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7338128685951233},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6657720804214478},{"id":"https://openalex.org/C156273044","wikidata":"https://www.wikidata.org/wiki/Q4913766","display_name":"Bin","level":2,"score":0.5410988926887512},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5373702049255371},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5062481760978699},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5038766264915466},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.49411943554878235},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4519663453102112},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.413013756275177},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38973772525787354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26874423027038574},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08300912380218506},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ita.2015.7308991","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ita.2015.7308991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Information Theory and Applications Workshop (ITA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W3998009","https://openalex.org/W66686753","https://openalex.org/W1574901103","https://openalex.org/W1667165204","https://openalex.org/W1965555277","https://openalex.org/W1985090574","https://openalex.org/W2038750313","https://openalex.org/W2052199757","https://openalex.org/W2103636088","https://openalex.org/W2129120544","https://openalex.org/W2153897396","https://openalex.org/W2619993508","https://openalex.org/W2727420541","https://openalex.org/W2914048585","https://openalex.org/W3127686677","https://openalex.org/W6602803216","https://openalex.org/W6789826613"],"related_works":["https://openalex.org/W2496295964","https://openalex.org/W1546240199","https://openalex.org/W1976952689","https://openalex.org/W2336887028","https://openalex.org/W1984921740","https://openalex.org/W193702574","https://openalex.org/W2070982348","https://openalex.org/W2365485488","https://openalex.org/W642007152","https://openalex.org/W2056066842"],"abstract_inverted_index":{"Voice":[0],"Activity":[1],"Detectors":[2],"(VAD)":[3],"play":[4],"important":[5],"role":[6],"in":[7,23,97,111],"audio":[8,31,113],"processing":[9],"algorithms.":[10,141],"Most":[11],"of":[12,48,71],"the":[13,40,65,72,87,102,115,137],"algorithms":[14],"are":[15],"designed":[16],"to":[17,21,39,136],"be":[18],"causal,":[19],"i.e.":[20],"work":[22],"real":[24],"time":[25],"using":[26,45],"only":[27],"current":[28],"and":[29,74,100,122,130],"past":[30],"samples.":[32],"Off-line":[33],"processing,":[34],"when":[35],"we":[36,56],"have":[37],"access":[38],"entire":[41],"voice":[42],"utterance,":[43],"allows":[44],"different":[46,66],"type":[47],"approaches":[49],"for":[50,60,85,107,119],"increased":[51],"precision.":[52],"In":[53],"this":[54],"paper":[55],"propose":[57],"an":[58],"algorithm":[59,95],"off-line":[61],"VAD":[62,94,140],"based":[63],"on":[64],"probability":[67,106,118],"density":[68],"functions":[69],"(PDFs)":[70],"speech":[73,88,103,116],"noise.":[75],"While":[76],"a":[77,81,125],"Gaussian":[78],"distribution":[79],"is":[80,90],"very":[82],"good":[83],"model":[84],"noise,":[86],"PDF":[89],"peakier.":[91],"The":[92],"proposed":[93],"works":[96],"frequency":[98,109],"domain":[99],"estimates":[101],"signal":[104],"presence":[105,117],"each":[108,112,120],"bin":[110,129],"frame,":[114],"frame":[121],"also":[123],"provides":[124],"binary":[126],"decision":[127],"per":[128],"frame.":[131],"Provides":[132],"improved":[133],"precision":[134],"compared":[135],"streaming":[138],"real-time":[139]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
