{"id":"https://openalex.org/W2086151712","doi":"https://doi.org/10.1109/wiamis.2013.6616152","title":"A nested infinite Gaussian mixture model for identifying known and unknown audio events","display_name":"A nested infinite Gaussian mixture model for identifying known and unknown audio events","publication_year":2013,"publication_date":"2013-07-01","ids":{"openalex":"https://openalex.org/W2086151712","doi":"https://doi.org/10.1109/wiamis.2013.6616152","mag":"2086151712"},"language":"en","primary_location":{"id":"doi:10.1109/wiamis.2013.6616152","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wiamis.2013.6616152","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 14th International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS)","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/A5102748358","display_name":"Yoko Sasaki","orcid":"https://orcid.org/0000-0002-1220-6124"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yoko Sasaki","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology, Japan","Nat. Inst. of Adv. Ind. Sci. & Technol., AIST, Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology, Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Nat. Inst. of Adv. Ind. Sci. & Technol., AIST, Tsukuba, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067956319","display_name":"Kazuyoshi Yoshii","orcid":"https://orcid.org/0000-0001-8387-8609"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuyoshi Yoshii","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology, Japan","Nat. Inst. of Adv. Ind. Sci. & Technol., AIST, Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology, Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Nat. Inst. of Adv. Ind. Sci. & Technol., AIST, Tsukuba, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113822737","display_name":"Satoshi Kagami","orcid":null},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Kagami","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology, Japan","Nat. Inst. of Adv. Ind. Sci. & Technol., AIST, Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology, Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Nat. Inst. of Adv. Ind. Sci. & Technol., AIST, Tsukuba, Japan","institution_ids":["https://openalex.org/I73613424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102748358"],"corresponding_institution_ids":["https://openalex.org/I73613424"],"apc_list":null,"apc_paid":null,"fwci":0.9647,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.76287114,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"2","issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9922999739646912,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9685999751091003,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/mixture-model","display_name":"Mixture model","score":0.7505390048027039},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6791408658027649},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6465920805931091},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5853046178817749},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.49095991253852844},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.47939085960388184},{"id":"https://openalex.org/keywords/nonparametric-statistics","display_name":"Nonparametric statistics","score":0.4590458273887634},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4378500282764435},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4353760778903961},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4271446764469147},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4137602746486664},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.38309866189956665},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36934351921081543},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35172781348228455},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3298228979110718},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.27467501163482666},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2544543147087097},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.13598158955574036},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09979408979415894}],"concepts":[{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.7505390048027039},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6791408658027649},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6465920805931091},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5853046178817749},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.49095991253852844},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.47939085960388184},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.4590458273887634},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4378500282764435},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4353760778903961},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4271446764469147},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4137602746486664},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.38309866189956665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36934351921081543},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35172781348228455},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3298228979110718},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.27467501163482666},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2544543147087097},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.13598158955574036},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09979408979415894},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/wiamis.2013.6616152","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wiamis.2013.6616152","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 14th International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.717.4241","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.717.4241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://winnie.kuis.kyoto-u.ac.jp/%7Eyoshii/papers/wiamis-2013-sasaki.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W42422348","https://openalex.org/W222076935","https://openalex.org/W1533561824","https://openalex.org/W1560013842","https://openalex.org/W1966273763","https://openalex.org/W1988030566","https://openalex.org/W1999949665","https://openalex.org/W2015293542","https://openalex.org/W2069429561","https://openalex.org/W2074764925","https://openalex.org/W2151967501","https://openalex.org/W2156839033","https://openalex.org/W3140968660","https://openalex.org/W6608730375","https://openalex.org/W6632323398","https://openalex.org/W6682569104"],"related_works":["https://openalex.org/W1992295166","https://openalex.org/W2289868279","https://openalex.org/W2545529375","https://openalex.org/W2143508933","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4315836293","https://openalex.org/W4243888788","https://openalex.org/W2769884427","https://openalex.org/W2088690926"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,25,55,82],"novel":[4],"statistical":[5],"method":[6,80],"that":[7,50,103],"can":[8],"classify":[9],"given":[10,143],"audio":[11,35,64,108,129,144],"events":[12,36,65],"into":[13,71],"known":[14,72],"classes":[15,59,93],"or":[16],"recognize":[17],"them":[18],"as":[19],"an":[20],"unknown":[21],"class.":[22],"We":[23],"propose":[24],"nested":[26,114],"infinite":[27,83],"Gaussian":[28,84],"mixture":[29,85],"model":[30,86],"(iGMM)":[31,87],"to":[32,53,68,96,122,140],"represent":[33,141],"varied":[34],"in":[37,60,88],"real":[38],"environment.":[39],"One":[40],"of":[41,45,58,92,106,127],"the":[42,76,78,90,104,113,124,134,142],"main":[43],"problems":[44,139],"conventional":[46],"classification":[47],"methods":[48],"is":[49,102,110,120],"we":[51],"need":[52],"specify":[54],"fixed":[56],"number":[57,91],"advance.":[61],"Therefore,":[62],"all":[63],"are":[66,94],"forced":[67],"be":[69],"classified":[70],"classes.":[73],"To":[74],"solve":[75],"problem,":[77],"proposed":[79],"formulates":[81],"which":[89],"allowed":[95],"increase":[97],"without":[98],"bound.":[99],"Another":[100],"problem":[101],"complexity":[105],"each":[107,128],"event":[109],"different.":[111],"Then,":[112],"iGMM":[115],"using":[116],"nonparametric":[117],"Bayesian":[118],"approach":[119],"applied":[121],"adjust":[123],"needed":[125],"dimension":[126],"model.":[130],"Experimental":[131],"results":[132],"show":[133],"effectiveness":[135],"for":[136],"these":[137],"two":[138],"events.":[145]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}