{"id":"https://openalex.org/W2119573952","doi":"https://doi.org/10.1109/tasl.2011.2131131","title":"Convex Combination of Multiple Statistical Models With Application to VAD","display_name":"Convex Combination of Multiple Statistical Models With Application to VAD","publication_year":2011,"publication_date":"2011-03-22","ids":{"openalex":"https://openalex.org/W2119573952","doi":"https://doi.org/10.1109/tasl.2011.2131131","mag":"2119573952"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2011.2131131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2011.2131131","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/3435001","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111541329","display_name":"Theodoros Petsatodis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210162098","display_name":"Athens Information Technology","ror":"https://ror.org/05eqt7s39","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210162098"]},{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK","GR"],"is_corresponding":false,"raw_author_name":"Theodoros Petsatodis","raw_affiliation_strings":["Autonomic and Grid Computing Group, Athens Information Technology Center, Athens, Greece","Center for TeleInFrastruktur (CTIF), University of Aalborg, Aalborg, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autonomic and Grid Computing Group, Athens Information Technology Center, Athens, Greece","institution_ids":["https://openalex.org/I4210162098"]},{"raw_affiliation_string":"Center for TeleInFrastruktur (CTIF), University of Aalborg, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057850203","display_name":"Christos Boukis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210162098","display_name":"Athens Information Technology","ror":"https://ror.org/05eqt7s39","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210162098"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Christos Boukis","raw_affiliation_strings":["Autonomic and Grid Computing Group, Athens Information Technology Center, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autonomic and Grid Computing Group, Athens Information Technology Center, Athens, Greece","institution_ids":["https://openalex.org/I4210162098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109239522","display_name":"Fotios Talantzis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210162098","display_name":"Athens Information Technology","ror":"https://ror.org/05eqt7s39","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210162098"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB","GR"],"is_corresponding":false,"raw_author_name":"Fotios Talantzis","raw_affiliation_strings":["Autonomic and Grid Computing Group, Athens Information Technology Center, Athens, Greece","Imperial College London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autonomic and Grid Computing Group, Athens Information Technology Center, Athens, Greece","institution_ids":["https://openalex.org/I4210162098"]},{"raw_affiliation_string":"Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090108098","display_name":"Zheng\u2010Hua Tan","orcid":"https://orcid.org/0000-0001-6856-8928"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Zheng-Hua Tan","raw_affiliation_strings":["Electronic Systems Department, University of Aalborg, Aalborg, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronic Systems Department, University of Aalborg, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110426463","display_name":"Ramjee Prasad","orcid":null},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Ramjee Prasad","raw_affiliation_strings":["Center for TeleInFrastruktur (CTIF), University of Aalborg, Aalborg, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for TeleInFrastruktur (CTIF), University of Aalborg, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0735,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.92222517,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"19","issue":"8","first_page":"2314","last_page":"2327"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"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":0.7263630628585815},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6001194715499878},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5994082093238831},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5031744837760925},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4985790252685547},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.44434720277786255},{"id":"https://openalex.org/keywords/gamma-distribution","display_name":"Gamma distribution","score":0.4393773376941681},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.4321712851524353},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.42852461338043213},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4274926483631134},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27711886167526245},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16698956489562988},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.11682045459747314},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09186485409736633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7263630628585815},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6001194715499878},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5994082093238831},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5031744837760925},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4985790252685547},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.44434720277786255},{"id":"https://openalex.org/C149717495","wikidata":"https://www.wikidata.org/wiki/Q117806","display_name":"Gamma distribution","level":2,"score":0.4393773376941681},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4321712851524353},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.42852461338043213},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4274926483631134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27711886167526245},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16698956489562988},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.11682045459747314},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09186485409736633},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tasl.2011.2131131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2011.2131131","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:publications/7c386252-54a7-492d-8e05-5d31ba630ddb","is_oa":false,"landing_page_url":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5737769","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Petsatodis, T, Boukis, C, Talantzis, F, Tan, Z-H & Prasad, R 2011, 'Convex Combination of Multiple Statistical Models with Application to VAD', I E E E Transactions on Audio, Speech and Language Processing, vol. 19, no. 8, pp. 2314-2327. https://doi.org/10.1109/TASL.2011.2131131","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:zenodo.org:3435001","is_oa":true,"landing_page_url":"https://zenodo.org/record/3435001","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:3435001","is_oa":true,"landing_page_url":"https://zenodo.org/record/3435001","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W55930003","https://openalex.org/W159356774","https://openalex.org/W1964627937","https://openalex.org/W1965559434","https://openalex.org/W1974387177","https://openalex.org/W1985090574","https://openalex.org/W2024665095","https://openalex.org/W2100555417","https://openalex.org/W2103636088","https://openalex.org/W2104316150","https://openalex.org/W2108819501","https://openalex.org/W2117678320","https://openalex.org/W2121973264","https://openalex.org/W2129120544","https://openalex.org/W2133938994","https://openalex.org/W2133969391","https://openalex.org/W2135780429","https://openalex.org/W2149053750","https://openalex.org/W2152395643","https://openalex.org/W2159856503","https://openalex.org/W2162520685","https://openalex.org/W2215838893","https://openalex.org/W3140535038","https://openalex.org/W3145636786","https://openalex.org/W3147539069","https://openalex.org/W4233343816","https://openalex.org/W4285719527","https://openalex.org/W6602294394","https://openalex.org/W6680237693"],"related_works":["https://openalex.org/W1978572805","https://openalex.org/W2383807498","https://openalex.org/W1997992934","https://openalex.org/W1987225439","https://openalex.org/W4238188170","https://openalex.org/W2125114371","https://openalex.org/W2019977573","https://openalex.org/W2149980199","https://openalex.org/W3125766170","https://openalex.org/W2040641410"],"abstract_inverted_index":{"This":[0,59],"paper":[1],"proposes":[2],"a":[3,36,45,47,50,106],"robust":[4],"voice":[5],"activity":[6],"detector":[7],"(VAD)":[8],"based":[9,82],"on":[10,26,83],"the":[11,14,27,84,88,95,98,111,123],"observation":[12],"that":[13],"distribution":[15,74],"of":[16,72,87,97,114,126],"speech":[17,115],"captured":[18,57],"with":[19],"far-field":[20],"microphones":[21],"is":[22,79,103],"highly":[23],"varying,":[24],"depending":[25],"noise":[28],"and":[29,49,133],"reverberation":[30],"conditions.":[31],"The":[32,70],"proposed":[33,124],"VAD":[34],"employs":[35],"convex":[37,77],"combination":[38,78],"scheme":[39,60,108],"comprising":[40],"three":[41],"statistical":[42,85],"distributions":[43],"-":[44,53],"Gaussian,":[46],"Laplacian,":[48],"two-sided":[51],"Gamma":[52],"to":[54,64,66,75,110],"effectively":[55],"model":[56],"speech.":[58],"shows":[61],"increased":[62,131],"ability":[63],"adapt":[65],"dynamic":[67],"acoustic":[68],"environments.":[69],"contribution":[71],"each":[73],"this":[76],"automatically":[80],"adjusted":[81],"characteristics":[86],"instantaneous":[89],"audio":[90],"input.":[91],"To":[92],"further":[93],"improve":[94],"performance":[96],"system,":[99],"an":[100],"adaptive":[101],"threshold":[102],"introduced,":[104],"while":[105],"decision-smoothing":[107],"caters":[109],"intra-frame":[112],"correlation":[113],"signals.":[116],"Extensive":[117],"experiments":[118],"under":[119],"realistic":[120],"scenarios":[121],"support":[122],"approach":[125],"combining":[127],"several":[128],"models":[129],"for":[130],"adaptation":[132],"performance.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
