{"id":"https://openalex.org/W2032596349","doi":"https://doi.org/10.1109/ijcnn.2014.6889403","title":"Hybrid SVM/HMM architectures for statistical model-based voice activity detection","display_name":"Hybrid SVM/HMM architectures for statistical model-based voice activity detection","publication_year":2014,"publication_date":"2014-07-01","ids":{"openalex":"https://openalex.org/W2032596349","doi":"https://doi.org/10.1109/ijcnn.2014.6889403","mag":"2032596349"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2014.6889403","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2014.6889403","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Joint Conference on Neural Networks (IJCNN)","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/A5011663086","display_name":"Ying-Wei Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ying-Wei Tan","raw_affiliation_strings":["Department of National Laboratory of Pattern Recognition, Chinese Academy of Sciences","Dept. of Nat. Lab. of Pattern Recognition, Inst. of Autom., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of National Laboratory of Pattern Recognition, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Dept. of Nat. Lab. of Pattern Recognition, Inst. of Autom., Beijing, China","institution_ids":["https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039635290","display_name":"Wenju Liu","orcid":"https://orcid.org/0000-0001-9088-8282"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen-Ju Liu","raw_affiliation_strings":["Department of National Laboratory of Pattern Recognition, Chinese Academy of Sciences","Dept. of Nat. Lab. of Pattern Recognition, Inst. of Autom., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of National Laboratory of Pattern Recognition, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Dept. of Nat. Lab. of Pattern Recognition, Inst. of Autom., Beijing, China","institution_ids":["https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063083038","display_name":"Wei Jiang","orcid":"https://orcid.org/0000-0003-4316-880X"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Jiang","raw_affiliation_strings":["Department of National Laboratory of Pattern Recognition, Chinese Academy of Sciences","Dept. of Nat. Lab. of Pattern Recognition, Inst. of Autom., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of National Laboratory of Pattern Recognition, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Dept. of Nat. Lab. of Pattern Recognition, Inst. of Autom., Beijing, China","institution_ids":["https://openalex.org/I4210094879"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064778924","display_name":"Hao Zheng","orcid":"https://orcid.org/0000-0001-6786-7950"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Zheng","raw_affiliation_strings":["Department of National Laboratory of Pattern Recognition, Chinese Academy of Sciences","Dept. of Nat. Lab. of Pattern Recognition, Inst. of Autom., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of National Laboratory of Pattern Recognition, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Dept. of Nat. Lab. of Pattern Recognition, Inst. of Autom., Beijing, China","institution_ids":["https://openalex.org/I4210094879"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5011663086"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"],"apc_list":null,"apc_paid":null,"fwci":0.2911,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.5515625,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"107","issue":null,"first_page":"2875","last_page":"2878"},"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":0.9976000189781189,"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":0.9962999820709229,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.876640796661377},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8159219026565552},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.78618323802948},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7160941362380981},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.642215371131897},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.64188152551651},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.577545166015625},{"id":"https://openalex.org/keywords/inter-frame","display_name":"Inter frame","score":0.49208348989486694},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.47365912795066833},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4379594326019287},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.42834270000457764},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3462953567504883},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.19514134526252747}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.876640796661377},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8159219026565552},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.78618323802948},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7160941362380981},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.642215371131897},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.64188152551651},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.577545166015625},{"id":"https://openalex.org/C39394851","wikidata":"https://www.wikidata.org/wiki/Q921594","display_name":"Inter frame","level":4,"score":0.49208348989486694},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.47365912795066833},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4379594326019287},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.42834270000457764},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3462953567504883},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.19514134526252747},{"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},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2014.6889403","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2014.6889403","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1618905105","https://openalex.org/W1974387177","https://openalex.org/W1977602661","https://openalex.org/W1985456342","https://openalex.org/W2003662620","https://openalex.org/W2081671587","https://openalex.org/W2101357962","https://openalex.org/W2129120544","https://openalex.org/W2140732925","https://openalex.org/W2149298154","https://openalex.org/W2158146178","https://openalex.org/W2158185319","https://openalex.org/W2167516348","https://openalex.org/W3141736179","https://openalex.org/W3147539069","https://openalex.org/W6636501900"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W1482209366","https://openalex.org/W2110523656","https://openalex.org/W2167155152","https://openalex.org/W2101357962"],"abstract_inverted_index":{"The":[0],"decision":[1,31],"function":[2],"of":[3,37,42,61,91,109,112],"support":[4],"vector":[5],"machine":[6],"(SVM)":[7],"using":[8],"the":[9,39,43,46,58,62,83,95,106,110,113,119],"likelihood":[10],"ratios":[11],"(LRs)":[12],"is":[13,24,65],"successfully":[14],"used":[15],"for":[16,45,54,82],"statistical":[17],"model-based":[18],"voice":[19,63],"activity":[20,64],"detection":[21],"(VAD).":[22],"It":[23],"known":[25],"to":[26],"incorporate":[27],"an":[28],"optimised":[29],"nonlinear":[30,89],"over":[32],"two":[33],"different":[34],"classes,":[35],"instead":[36],"comparing":[38],"geometric":[40],"mean":[41],"LRs":[44],"individual":[47],"frequency":[48],"bands":[49],"with":[50,118],"a":[51,75,100],"given":[52],"threshold":[53],"speech":[55],"detection.":[56],"However,":[57],"inter-frame":[59],"correlation":[60,97],"not":[66],"taken":[67],"into":[68],"consideration.":[69],"In":[70],"this":[71],"paper,":[72],"we":[73],"explore":[74],"hybrid":[76],"SVM/hidden":[77],"Markov":[78],"model":[79],"(HMM)":[80],"approach":[81],"VAD,":[84],"which":[85],"retains":[86],"discriminative":[87],"and":[88],"properties":[90],"SVM,":[92],"while":[93],"modeling":[94],"interframe":[96],"powerfully":[98],"through":[99],"first-order":[101],"HMM.":[102],"Experimental":[103],"results":[104],"show":[105],"significant":[107],"improvement":[108],"performance":[111],"proposed":[114],"VAD":[115],"in":[116],"comparison":[117],"SVM-based":[120],"VAD.":[121]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}