{"id":"https://openalex.org/W1985242443","doi":"https://doi.org/10.1109/tasl.2012.2229986","title":"Deep Belief Networks Based Voice Activity Detection","display_name":"Deep Belief Networks Based Voice Activity Detection","publication_year":2012,"publication_date":"2012-11-27","ids":{"openalex":"https://openalex.org/W1985242443","doi":"https://doi.org/10.1109/tasl.2012.2229986","mag":"1985242443"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2012.2229986","doi":"https://doi.org/10.1109/tasl.2012.2229986","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2229986","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,"listed_in":["cwts-core"],"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"},"volume":null,"type":"article","is_traditional":true,"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/A5069080329","display_name":"Xiaolei Zhang","orcid":"https://orcid.org/0000-0002-5030-4948","observed_orcids":["https://orcid.org/0000-0002-5030-4948"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-Lei Zhang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China","Dept. of Electron. Eng., TsingHua Univ., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Dept. of Electron. Eng., TsingHua Univ., Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014958566","display_name":"Ji Yi Wu","orcid":"https://orcid.org/0000-0001-6170-726X","observed_orcids":["https://orcid.org/0000-0001-6170-726X"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji Wu","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China","Dept. of Electron. Eng., TsingHua Univ., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Dept. of Electron. Eng., TsingHua Univ., Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":13.0359,"has_fulltext":false,"cited_by_count":316,"citation_normalized_percentile":{"value":0.98813178,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":"21","issue":"4","first_page":"697","last_page":"710"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.625,"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":0.625,"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":0.37130001187324524,"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":0.000699999975040555,"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/voice-activity-detection","display_name":"voice activity detection","score":0.9980000257492065},{"id":"https://openalex.org/keywords/deep-belief-network","display_name":"deep belief network","score":0.9390000104904175},{"id":"https://openalex.org/keywords/feature-fusion","display_name":"feature fusion","score":0.7720000147819519},{"id":"https://openalex.org/keywords/acoustic-characteristics","display_name":"acoustic features","score":0.8619999885559082},{"id":"https://openalex.org/keywords/hierarchical-feature-extraction","display_name":"hierarchical feature extraction","score":0.6460000276565552}],"concepts":[{"id":"https://openalex.org/C97385483","wikidata":"https://www.wikidata.org/wiki/Q16954980","display_name":"Deep belief network","level":3,"score":0.8459910154342651},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8000084161758423},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7174215316772461},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.6648296117782593},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6224536895751953},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5902681946754456},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5655138492584229},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5495737791061401},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.44374847412109375},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4427621364593506},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4323154389858246},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.4142412841320038},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4072456955909729},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.20078715682029724},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0969836413860321},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C103038307","wikidata":"https://www.wikidata.org/wiki/Q6556360","display_name":"Lipid bilayer fusion","level":3,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tasl.2012.2229986","doi":"https://doi.org/10.1109/tasl.2012.2229986","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2229986","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,"listed_in":["cwts-core"],"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:CiteSeerX.psu:10.1.1.338.3383","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.338.3383","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":79,"referenced_works":["https://openalex.org/W44815768","https://openalex.org/W66838807","https://openalex.org/W114565888","https://openalex.org/W153409269","https://openalex.org/W197206975","https://openalex.org/W1915109052","https://openalex.org/W1963970749","https://openalex.org/W1964538581","https://openalex.org/W1989364685","https://openalex.org/W1993882792","https://openalex.org/W2015469795","https://openalex.org/W2025768430","https://openalex.org/W2027804983","https://openalex.org/W2038269275","https://openalex.org/W2051170812","https://openalex.org/W2072128103","https://openalex.org/W2088361146","https://openalex.org/W2093866254","https://openalex.org/W2095755195","https://openalex.org/W2096496615","https://openalex.org/W2096873754","https://openalex.org/W2098265087","https://openalex.org/W2100495367","https://openalex.org/W2100555417","https://openalex.org/W2101357962","https://openalex.org/W2106869737","https://openalex.org/W2108819501","https://openalex.org/W2109943925","https://openalex.org/W2110622865","https://openalex.org/W2110798204","https://openalex.org/W2113640225","https://openalex.org/W2115129089","https://openalex.org/W2115717467","https://openalex.org/W2117130368","https://openalex.org/W2119573952","https://openalex.org/W2119599673","https://openalex.org/W2120480077","https://openalex.org/W2120480179","https://openalex.org/W2120933697","https://openalex.org/W2120979206","https://openalex.org/W2122647985","https://openalex.org/W2122982914","https://openalex.org/W2129120544","https://openalex.org/W2130770109","https://openalex.org/W2136922672","https://openalex.org/W2137449599","https://openalex.org/W2138456300","https://openalex.org/W2138857742","https://openalex.org/W2138939691","https://openalex.org/W2139451965","https://openalex.org/W2141778357","https://openalex.org/W2142170306","https://openalex.org/W2143885887","https://openalex.org/W2144680614","https://openalex.org/W2144792281","https://openalex.org/W2145030715","https://openalex.org/W2147768505","https://openalex.org/W2148632119","https://openalex.org/W2149053750","https://openalex.org/W2149425615","https://openalex.org/W2151251521","https://openalex.org/W2151484683","https://openalex.org/W2158146178","https://openalex.org/W2159202424","https://openalex.org/W2160815625","https://openalex.org/W2165698076","https://openalex.org/W2167516348","https://openalex.org/W2171875099","https://openalex.org/W2183703731","https://openalex.org/W2253807446","https://openalex.org/W2295582178","https://openalex.org/W2315268655","https://openalex.org/W2561557072","https://openalex.org/W2606321545","https://openalex.org/W2616180702","https://openalex.org/W2950789693","https://openalex.org/W4231109964","https://openalex.org/W4233392025","https://openalex.org/W6676194229"],"related_works":["https://openalex.org/W2017854128","https://openalex.org/W2395964874","https://openalex.org/W2109000787","https://openalex.org/W2294745040","https://openalex.org/W1612048585","https://openalex.org/W2984203607","https://openalex.org/W2551314165","https://openalex.org/W2997046480","https://openalex.org/W2197404611","https://openalex.org/W2513345070"],"abstract_inverted_index":{"Fusing":[0],"the":[1,10,18,44,48,86,89,93,98,121,124,144,148,167,172,185,196,201],"advantages":[2,202],"of":[3,12,47,88,101,123,189,203],"multiple":[4,29,57,94,114,204],"acoustic":[5],"features":[6,58,96,112,157,205],"is":[7,69,140],"important":[8],"for":[9,75,160],"robustness":[11],"voice":[13],"activity":[14],"detection":[15,187],"(VAD).":[16],"Recently,":[17],"machine-learning-based":[19,35,149],"VADs":[20,27,36],"have":[21],"shown":[22],"a":[23,60,70,106,128,136],"superiority":[24],"to":[25,55],"traditional":[26],"on":[28,166],"feature":[30,76,108,126],"fusion":[31],"tasks.":[32],"However,":[33],"existing":[34],"only":[37,176],"utilize":[38],"shallow":[39],"models,":[40],"which":[41],"cannot":[42],"explore":[43],"underlying":[45],"manifold":[46,87],"features.":[49,90],"In":[50,151],"this":[51],"paper,":[52],"we":[53,119],"propose":[54],"fuse":[56,200],"via":[59],"deep":[61,64],"model,":[62],"called":[63],"belief":[65,138],"network":[66,139],"(DBN).":[67],"DBN":[68],"powerful":[71,142],"hierarchical":[72],"generative":[73],"model":[74],"extraction.":[77],"It":[78],"can":[79,183,199],"describe":[80],"highly":[81],"variant":[82],"functions":[83],"and":[84,103],"discover":[85],"We":[91,131],"take":[92],"serially-concatenated":[95],"as":[97,141,143],"input":[99],"layer":[100],"DBN,":[102],"then":[104],"extract":[105],"new":[107,125],"by":[109,127],"transferring":[110],"these":[111],"through":[113],"nonlinear":[115],"hidden":[116],"layers.":[117],"Finally,":[118],"predict":[120],"class":[122],"linear":[129],"classifier.":[130],"further":[132],"analyze":[133],"that":[134,171,195],"even":[135],"single-hidden-layer-based":[137],"state-of-the-art":[145],"models":[146],"in":[147],"VADs.":[150],"our":[152],"empirical":[153],"comparison,":[154],"ten":[155],"common":[156],"are":[158],"used":[159],"performance":[161],"analysis.":[162],"Extensive":[163],"experimental":[164],"results":[165,192],"AURORA2":[168],"corpus":[169],"show":[170,194],"DBN-based":[173,197],"VAD":[174,198],"not":[175],"outperforms":[177],"eleven":[178],"referenced":[179],"VADs,":[180],"but":[181],"also":[182,193],"meet":[184],"real-time":[186],"demand":[188],"VAD.":[190],"The":[191],"effectively.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":35},{"year":2020,"cited_by_count":30},{"year":2019,"cited_by_count":32},{"year":2018,"cited_by_count":46},{"year":2017,"cited_by_count":37},{"year":2016,"cited_by_count":29},{"year":2015,"cited_by_count":24},{"year":2014,"cited_by_count":21},{"year":2013,"cited_by_count":3}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2016-06-24T00:00:00"}