{"id":"https://openalex.org/W2140732925","doi":"https://doi.org/10.1109/icassp.2011.5947534","title":"A modified MAP criterion based on hidden Markov model for voice activity detecion","display_name":"A modified MAP criterion based on hidden Markov model for voice activity detecion","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2140732925","doi":"https://doi.org/10.1109/icassp.2011.5947534","mag":"2140732925"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5087019132","display_name":"Shiwen Deng","orcid":"https://orcid.org/0000-0001-8964-3165"},"institutions":[{"id":"https://openalex.org/I134052481","display_name":"Harbin Normal University","ror":"https://ror.org/0270y6950","country_code":"CN","type":"education","lineage":["https://openalex.org/I134052481"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiwen Deng","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, China","School of Mathematical Sciences, Harbin Normal University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Mathematical Sciences, Harbin Normal University, China","institution_ids":["https://openalex.org/I134052481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101508830","display_name":"Jiqing Han","orcid":"https://orcid.org/0000-0002-4297-4300"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiqing Han","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101846141","display_name":"Tieran Zheng","orcid":"https://orcid.org/0009-0006-5179-0278"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tieran Zheng","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041058909","display_name":"Guibin Zheng","orcid":"https://orcid.org/0000-0002-4280-5224"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guibin Zheng","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]}],"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":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5220","last_page":"5223"},"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":0.9994000196456909,"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":0.9959999918937683,"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/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.8576970100402832},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.772087574005127},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5653692483901978},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.559374213218689},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5490404367446899},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.509634256362915},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4820331335067749},{"id":"https://openalex.org/keywords/false-alarm","display_name":"False alarm","score":0.4552135169506073},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4283074140548706},{"id":"https://openalex.org/keywords/likelihood-ratio-test","display_name":"Likelihood-ratio test","score":0.4122953712940216},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.306792676448822},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2711729407310486},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.2286728322505951}],"concepts":[{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.8576970100402832},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.772087574005127},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5653692483901978},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.559374213218689},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5490404367446899},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.509634256362915},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4820331335067749},{"id":"https://openalex.org/C2776836416","wikidata":"https://www.wikidata.org/wiki/Q1364844","display_name":"False alarm","level":2,"score":0.4552135169506073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4283074140548706},{"id":"https://openalex.org/C9483764","wikidata":"https://www.wikidata.org/wiki/Q585740","display_name":"Likelihood-ratio test","level":2,"score":0.4122953712940216},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.306792676448822},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2711729407310486},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.2286728322505951},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/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/icassp.2011.5947534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2345086","https://openalex.org/W2032362923","https://openalex.org/W2032474878","https://openalex.org/W2098265087","https://openalex.org/W2108720302","https://openalex.org/W2121973264","https://openalex.org/W2129120544","https://openalex.org/W2143620343","https://openalex.org/W2149053750","https://openalex.org/W2156038773","https://openalex.org/W2158185319","https://openalex.org/W2159856503","https://openalex.org/W3147539069"],"related_works":["https://openalex.org/W1595191759","https://openalex.org/W2150865841","https://openalex.org/W2010299594","https://openalex.org/W2084680108","https://openalex.org/W2138865713","https://openalex.org/W2169353922","https://openalex.org/W2408444874","https://openalex.org/W2164741877","https://openalex.org/W1968998224","https://openalex.org/W1992932675"],"abstract_inverted_index":{"The":[0],"maximum":[1],"a":[2,41,48,86,88,103],"posteriori":[3],"(MAP)":[4],"criterion":[5,45,142,153],"is":[6,31,70,80,112],"broadly":[7],"used":[8,113],"in":[9,143],"the":[10,19,24,28,56,59,62,63,67,73,77,85,95,101,107,116,119,124,131,134,139,149],"statistical":[11],"model-based":[12],"voice":[13,29,68],"activity":[14,30,69],"detection":[15,122],"(VAD)":[16],"approaches.":[17],"In":[18,36,100],"conventional":[20],"MAP":[21,44,75,141,152],"criterion,":[22,76],"however,":[23],"inter-frame":[25,64,91],"correlation":[26,65,92],"of":[27,58,66,109,121,133],"not":[32],"taken":[33],"into":[34,94],"consideration.":[35],"this":[37],"paper,":[38],"we":[39],"proposes":[40],"novel":[42],"modified":[43],"based":[46,137,147],"on":[47,138,148],"two-state":[49],"hidden":[50],"Markov":[51],"model":[52],"(HMM)":[53],"to":[54,114],"improve":[55],"performance":[57],"VAD,":[60],"and":[61,90,123],"modeled.":[71],"With":[72],"proposed":[74,140],"decision":[78],"rule":[79],"derived":[81],"by":[82],"explicitly":[83],"incorporating":[84],"priori,":[87],"posteriori,":[89],"information":[93],"likelihood":[96],"ratio":[97],"test":[98],"(LRT).":[99],"LRT,":[102],"compensation":[104],"factor":[105],"for":[106],"hypothesis":[108],"speech":[110],"presence":[111],"regulate":[115],"trade-off":[117],"between":[118],"probability":[120],"false":[125],"alarm":[126],"probability.":[127],"Experimental":[128],"results":[129],"show":[130],"superiority":[132],"VAD":[135],"algorithm":[136],"comparison":[144],"with":[145],"that":[146],"recent":[150],"conditional":[151],"(CMAP)":[154],"under":[155],"various":[156],"noise":[157],"conditions.":[158]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}