{"id":"https://openalex.org/W2027625247","doi":"https://doi.org/10.1109/iscslp.2014.6936602","title":"Efficient voice activity detection algorithm based on sub-band temporal envelope and sub-band long-term signal variability","display_name":"Efficient voice activity detection algorithm based on sub-band temporal envelope and sub-band long-term signal variability","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W2027625247","doi":"https://doi.org/10.1109/iscslp.2014.6936602","mag":"2027625247"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2014.6936602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th International Symposium on Chinese Spoken Language 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/A5100395443","display_name":"Bin Liu","orcid":"https://orcid.org/0000-0001-8800-7239"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Liu","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Chinese Academy of Sciences, Beijing","National Laboratory of Pattern Recognition,  Institute of Automation,  Chinese Academy of Sciences,  Beijing 100190,  China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Chinese Academy of Sciences, Beijing","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition,  Institute of Automation,  Chinese Academy of Sciences,  Beijing 100190,  China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Chinese Academy of Sciences, Beijing","National Laboratory of Pattern Recognition,  Institute of Automation,  Chinese Academy of Sciences,  Beijing 100190,  China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Chinese Academy of Sciences, Beijing","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition,  Institute of Automation,  Chinese Academy of Sciences,  Beijing 100190,  China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070168391","display_name":"Fuyuan Mo","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuyuan Mo","raw_affiliation_strings":["Institute of Acoustics, Chinese Academy of Sciences, Beijing","Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190 (China)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, Chinese Academy of Sciences, Beijing","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190 (China)","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343662","display_name":"Ya Li","orcid":"https://orcid.org/0000-0002-6284-5039"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ya Li","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Chinese Academy of Sciences, Beijing","National Laboratory of Pattern Recognition,  Institute of Automation,  Chinese Academy of Sciences,  Beijing 100190,  China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Chinese Academy of Sciences, Beijing","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition,  Institute of Automation,  Chinese Academy of Sciences,  Beijing 100190,  China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111856667","display_name":"Zhengqi Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengqi Wen","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Chinese Academy of Sciences, Beijing","National Laboratory of Pattern Recognition,  Institute of Automation,  Chinese Academy of Sciences,  Beijing 100190,  China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Chinese Academy of Sciences, Beijing","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition,  Institute of Automation,  Chinese Academy of Sciences,  Beijing 100190,  China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023219303","display_name":"Shanfeng Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanfeng Liu","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Chinese Academy of Sciences, Beijing","National Laboratory of Pattern Recognition,  Institute of Automation,  Chinese Academy of Sciences,  Beijing 100190,  China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Chinese Academy of Sciences, Beijing","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition,  Institute of Automation,  Chinese Academy of Sciences,  Beijing 100190,  China","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"531","last_page":"535"},"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":0.9983000159263611,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980000257492065,"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/computer-science","display_name":"Computer science","score":0.7483648657798767},{"id":"https://openalex.org/keywords/envelope","display_name":"Envelope (radar)","score":0.6466469764709473},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.6420555710792542},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.630752682685852},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6109991669654846},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5846419930458069},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5281251072883606},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5118052363395691},{"id":"https://openalex.org/keywords/detection-theory","display_name":"Detection theory","score":0.4198296070098877},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4143454134464264},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32770657539367676},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10354134440422058},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.09631392359733582}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7483648657798767},{"id":"https://openalex.org/C65155139","wikidata":"https://www.wikidata.org/wiki/Q5380912","display_name":"Envelope (radar)","level":3,"score":0.6466469764709473},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6420555710792542},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.630752682685852},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6109991669654846},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5846419930458069},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5281251072883606},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5118052363395691},{"id":"https://openalex.org/C137270730","wikidata":"https://www.wikidata.org/wiki/Q120811","display_name":"Detection theory","level":3,"score":0.4198296070098877},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4143454134464264},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32770657539367676},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10354134440422058},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.09631392359733582},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2014.6936602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8299999833106995,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W172214757","https://openalex.org/W1510519335","https://openalex.org/W1591492847","https://openalex.org/W1673191017","https://openalex.org/W1905983571","https://openalex.org/W1946893126","https://openalex.org/W1999454387","https://openalex.org/W2003662252","https://openalex.org/W2032362923","https://openalex.org/W2070176749","https://openalex.org/W2099145922","https://openalex.org/W2109622017","https://openalex.org/W2116764165","https://openalex.org/W2119393553","https://openalex.org/W2126693545","https://openalex.org/W2129120544","https://openalex.org/W2130426352","https://openalex.org/W2138029428","https://openalex.org/W2145370087","https://openalex.org/W2149053750","https://openalex.org/W2402212287","https://openalex.org/W2403186097","https://openalex.org/W2619993508","https://openalex.org/W3127686677","https://openalex.org/W6630581095","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/W2103239478","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2168417340","https://openalex.org/W4229451372"],"abstract_inverted_index":{"Voice":[0],"activity":[1,23],"detection":[2,24],"(VAD)":[3],"is":[4,12,78,97],"widely":[5],"used":[6],"for":[7],"various":[8],"speech-based":[9,125],"systems":[10],"which":[11,51],"an":[13,79],"important":[14],"pre-processing":[15],"step.":[16],"This":[17],"paper":[18],"proposes":[19],"a":[20,65,107,113],"robust":[21,66],"voice":[22],"algorithm.":[25],"In":[26],"the":[27,30,35,44,71,94,100],"proposed":[28,75,95,120],"algorithm,":[29],"sub-band":[31,36],"temporal":[32],"envelope":[33],"and":[34,55,83,104],"long-term":[37],"signal":[38],"variability":[39],"are":[40,61],"considered":[41],"to":[42,63,70,99,124],"distinguish":[43],"speech":[45],"from":[46],"all":[47],"kinds":[48],"of":[49,109,116],"non-speech":[50],"include":[52],"stationary":[53],"noise":[54,110],"non-stationary":[56],"noise.":[57],"The":[58,74,89,119],"two":[59],"features":[60],"combined":[62],"make":[64],"VAD":[67],"decision":[68],"according":[69],"fusion":[72],"decision.":[73],"algorithm":[76,82,96,121],"also":[77],"unsupervised":[80],"low-complexity":[81],"can":[84,105],"operate":[85],"without":[86],"pre-train":[87],"models.":[88],"experiments":[90],"results":[91],"show":[92],"that":[93],"prior":[98],"different":[101],"baseline":[102],"algorithms":[103],"handle":[106],"variety":[108],"environments":[111],"over":[112],"wide":[114],"range":[115],"signal-to-noise":[117],"ratios.":[118],"could":[122],"apply":[123],"systems.":[126]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
