{"id":"https://openalex.org/W2406758277","doi":"https://doi.org/10.1109/icassp.2016.7472701","title":"Dual-microphone voice activity detection based on using optimally weighted maximum a posteriori probabilities","display_name":"Dual-microphone voice activity detection based on using optimally weighted maximum a posteriori probabilities","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2406758277","doi":"https://doi.org/10.1109/icassp.2016.7472701","mag":"2406758277"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472701","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5039746498","display_name":"Seng Hyun Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Seng Hyun Huang","raw_affiliation_strings":["Department of Electronics Engineering, Hanyang University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electronics Engineering, Hanyang University, Seoul, Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049243328","display_name":"Jihwan Park","orcid":"https://orcid.org/0000-0001-9817-0953"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jihwan Park","raw_affiliation_strings":["Department of Electronics Engineering, Hanyang University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electronics Engineering, Hanyang University, Seoul, Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002418613","display_name":"Joon\u2010Hyuk Chang","orcid":"https://orcid.org/0000-0003-2610-2323"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon-Hyuk Chang","raw_affiliation_strings":["Department of Electronics Engineering, Hanyang University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electronics Engineering, Hanyang University, Seoul, Korea","institution_ids":["https://openalex.org/I4575257"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5039746498"],"corresponding_institution_ids":["https://openalex.org/I4575257"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0398952,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"20","issue":null,"first_page":"5360","last_page":"5364"},"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":0.9986000061035156,"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":0.9979000091552734,"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/microphone","display_name":"Microphone","score":0.7847219705581665},{"id":"https://openalex.org/keywords/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.740433931350708},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7356796264648438},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7146562337875366},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.6306940317153931},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5761817693710327},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5383425951004028},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5080063939094543},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49740245938301086},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.4802558720111847},{"id":"https://openalex.org/keywords/phase-coherence","display_name":"Phase coherence","score":0.43328022956848145},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21161720156669617},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.19205796718597412},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10285913944244385}],"concepts":[{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7847219705581665},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.740433931350708},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7356796264648438},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7146562337875366},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.6306940317153931},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5761817693710327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5383425951004028},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5080063939094543},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49740245938301086},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.4802558720111847},{"id":"https://openalex.org/C2987132901","wikidata":"https://www.wikidata.org/wiki/Q193147","display_name":"Phase coherence","level":2,"score":0.43328022956848145},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21161720156669617},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.19205796718597412},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10285913944244385},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C26873012","wikidata":"https://www.wikidata.org/wiki/Q214781","display_name":"Condensed matter physics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472701","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.75}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W86289693","https://openalex.org/W1974387177","https://openalex.org/W1985456342","https://openalex.org/W2028111967","https://openalex.org/W2028929783","https://openalex.org/W2123599635","https://openalex.org/W2129120544","https://openalex.org/W2133515443","https://openalex.org/W2134901501","https://openalex.org/W2143885887","https://openalex.org/W2147271331","https://openalex.org/W2165563588","https://openalex.org/W2169147844","https://openalex.org/W6657603347"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W2146049072","https://openalex.org/W2118877323","https://openalex.org/W2150865841","https://openalex.org/W2143264198","https://openalex.org/W2138865713","https://openalex.org/W2169353922"],"abstract_inverted_index":{"In":[0,28],"this":[1],"paper,":[2],"we":[3,31,57],"propose":[4],"to":[5,22,69],"improve":[6],"the":[7,34,41,46,63,83,92,100],"dual-microphone":[8,85,94],"voice":[9],"activity":[10],"detection":[11],"(VAD)":[12],"technique":[13],"for":[14],"which":[15,97],"a":[16,36,76],"discriminative":[17],"weight":[18],"training":[19],"is":[20],"applied":[21],"achieve":[23],"optimally":[24],"weighted":[25],"spatial":[26,42],"features.":[27],"our":[29],"approach,":[30],"first":[32],"derive":[33],"maximum":[35],"posteriori":[37],"(MAP)":[38],"probabilities":[39],"from":[40],"features":[43],"such":[44],"as":[45],"power":[47],"level":[48],"difference":[49],"ratio":[50],"(PLDR),":[51],"phase":[52],"vector,":[53],"and":[54,103],"coherence.":[55,105],"Then,":[56],"combine":[58],"each":[59],"MAP":[60],"probability":[61],"within":[62],"minimum":[64],"classification":[65],"error":[66],"(MCE)":[67],"framework":[68],"offer":[70],"an":[71],"optimal":[72],"VAD":[73,86,95],"decision":[74],"in":[75],"spectral":[77,104],"domain.":[78],"Experimental":[79],"results":[80],"show":[81],"that":[82],"proposed":[84],"algorithm":[87],"shows":[88],"better":[89],"performances":[90],"than":[91],"conventional":[93],"methods,":[96],"solely":[98],"utilize":[99],"PLDR,":[101],"phase,":[102]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}