{"id":"https://openalex.org/W2095755195","doi":"https://doi.org/10.1109/jstsp.2010.2080821","title":"Online Unsupervised Classification With Model Comparison in the Variational Bayes Framework for Voice Activity Detection","display_name":"Online Unsupervised Classification With Model Comparison in the Variational Bayes Framework for Voice Activity Detection","publication_year":2010,"publication_date":"2010-09-29","ids":{"openalex":"https://openalex.org/W2095755195","doi":"https://doi.org/10.1109/jstsp.2010.2080821","mag":"2095755195"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2010.2080821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2010.2080821","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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 Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repository.kulib.kyoto-u.ac.jp/dspace/bitstream/2433/131746/1/JSTSP.2010.2080821.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023051838","display_name":"David Cournapeau","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"David Cournapeau","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","School of Informatics, Kyoto University, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018620798","display_name":"Atsushi Nakamura","orcid":"https://orcid.org/0000-0003-0788-2221"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsushi Nakamura","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["School of Informatics, Kyoto University, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5023051838"],"corresponding_institution_ids":["https://openalex.org/I22299242","https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":1.6909,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.8480249,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"4","issue":"6","first_page":"1071","last_page":"1083"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9994999766349792,"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":0.7953940629959106},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.7204567790031433},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.599698543548584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.557174801826477},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.5125677585601807},{"id":"https://openalex.org/keywords/expectation\u2013maximization-algorithm","display_name":"Expectation\u2013maximization algorithm","score":0.4939301609992981},{"id":"https://openalex.org/keywords/online-model","display_name":"Online model","score":0.48387610912323},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.47509706020355225},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4683881103992462},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.453808069229126},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.45119401812553406},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4382707178592682},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.4280136823654175},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4279814660549164},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4271096885204315},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3319453001022339},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.29310327768325806},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.2287648618221283},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.21319106221199036},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09892261028289795},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.096873939037323},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09416994452476501}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7953940629959106},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.7204567790031433},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.599698543548584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.557174801826477},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.5125677585601807},{"id":"https://openalex.org/C182081679","wikidata":"https://www.wikidata.org/wiki/Q1275153","display_name":"Expectation\u2013maximization algorithm","level":3,"score":0.4939301609992981},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.48387610912323},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.47509706020355225},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4683881103992462},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.453808069229126},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.45119401812553406},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4382707178592682},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.4280136823654175},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4279814660549164},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4271096885204315},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3319453001022339},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.29310327768325806},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.2287648618221283},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.21319106221199036},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09892261028289795},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.096873939037323},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09416994452476501},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/jstsp.2010.2080821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2010.2080821","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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 Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},{"id":"pmh:oai:repository.kulib.kyoto-u.ac.jp:2433/131746","is_oa":true,"landing_page_url":"http://hdl.handle.net/2433/131746","pdf_url":"https://repository.kulib.kyoto-u.ac.jp/dspace/bitstream/2433/131746/1/JSTSP.2010.2080821.pdf","source":{"id":"https://openalex.org/S4306401454","display_name":"Kyoto University Research Information Repository (Kyoto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I22299242","host_organization_name":"Kyoto University","host_organization_lineage":["https://openalex.org/I22299242"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:repository.kulib.kyoto-u.ac.jp:2433/131746","is_oa":true,"landing_page_url":"http://hdl.handle.net/2433/131746","pdf_url":"https://repository.kulib.kyoto-u.ac.jp/dspace/bitstream/2433/131746/1/JSTSP.2010.2080821.pdf","source":{"id":"https://openalex.org/S4306401454","display_name":"Kyoto University Research Information Repository (Kyoto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I22299242","host_organization_name":"Kyoto University","host_organization_lineage":["https://openalex.org/I22299242"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"},"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2095755195.pdf","grobid_xml":"https://content.openalex.org/works/W2095755195.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W94160366","https://openalex.org/W629338568","https://openalex.org/W1499021337","https://openalex.org/W1560013842","https://openalex.org/W1570770495","https://openalex.org/W1607198972","https://openalex.org/W1618600317","https://openalex.org/W1663973292","https://openalex.org/W1686266550","https://openalex.org/W2049633694","https://openalex.org/W2053742104","https://openalex.org/W2096753136","https://openalex.org/W2101357962","https://openalex.org/W2115979064","https://openalex.org/W2119072456","https://openalex.org/W2119535101","https://openalex.org/W2121973264","https://openalex.org/W2129120544","https://openalex.org/W2132214951","https://openalex.org/W2138561666","https://openalex.org/W2163634074","https://openalex.org/W2166607750","https://openalex.org/W2167270514","https://openalex.org/W2170644918","https://openalex.org/W2171155529","https://openalex.org/W2171911691","https://openalex.org/W2911546748","https://openalex.org/W3102754772","https://openalex.org/W3140968660","https://openalex.org/W3147539069","https://openalex.org/W4212863985","https://openalex.org/W6603842662","https://openalex.org/W6633833189","https://openalex.org/W6636504819","https://openalex.org/W6679862768"],"related_works":["https://openalex.org/W2394466068","https://openalex.org/W1987683558","https://openalex.org/W2726838704","https://openalex.org/W4220802396","https://openalex.org/W2393473353","https://openalex.org/W2373790322","https://openalex.org/W2171665309","https://openalex.org/W1599183102","https://openalex.org/W2537862391","https://openalex.org/W2417174640"],"abstract_inverted_index":{"A":[0],"new":[1],"online,":[2],"unsupervised":[3],"method":[4,32],"for":[5,70,77,142],"Voice":[6],"Activity":[7],"Detection":[8],"(VAD)":[9],"is":[10,33,107,125,167],"proposed.":[11],"The":[12,29,91],"conventional":[13,157],"VAD":[14,31,143,158],"methods":[15],"often":[16],"rely":[17],"on":[18,35,137],"heuristics":[19],"to":[20,25,41,109,121,170,176],"adapt":[21,52],"the":[22,26,36,42,53,57,61,71,75,88,100,111,114,138,146,149,152,156,162,179],"decision":[23,54],"threshold":[24],"estimated":[27],"SNR.":[28],"proposed":[30,153],"based":[34],"Variational":[37],"Bayes":[38],"(VB)":[39],"approach":[40],"online":[43,86,118],"Expectation":[44],"Maximization":[45],"(EM),":[46],"so":[47],"that":[48],"it":[49],"can":[50],"automatically":[51],"level":[55],"and":[56,74,85,120],"statistical":[58],"model":[59,124,150],"at":[60,128],"same":[62],"time.":[63],"We":[64],"consider":[65],"two":[66],"parallel":[67],"classifiers,":[68],"one":[69],"noise-only":[72],"case,":[73],"other":[76],"speech-and-noise":[78],"case.":[79],"Both":[80],"models":[81],"are":[82],"trained":[83],"concurrently":[84],"using":[87],"VB":[89,92],"framework.":[90],"framework":[93],"also":[94,168],"provides":[95],"an":[96,117],"explicit":[97],"approximation":[98],"of":[99,113,148,178],"log":[101],"evidence":[102],"called":[103],"free":[104],"energy.":[105],"It":[106,166],"used":[108],"assess":[110],"reliability":[112],"classifier":[115],"in":[116,161],"fashion,":[119],"decide":[122],"which":[123],"more":[126,172],"appropriate":[127],"a":[129],"given":[130],"time":[131],"frame.":[132],"Experimental":[133],"evaluations":[134],"were":[135],"conducted":[136],"CENSREC-1-C":[139],"database":[140],"designed":[141],"evaluations.":[144],"With":[145],"effect":[147],"comparison,":[151],"scheme":[154],"outperforms":[155],"algorithms,":[159],"especially":[160],"remote":[163],"recording":[164],"condition.":[165],"shown":[169],"be":[171],"robust":[173],"with":[174],"respect":[175],"changes":[177],"noise":[180],"type.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}