{"id":"https://openalex.org/W2527564651","doi":"https://doi.org/10.1587/transinf.2016slp0004","title":"Acoustic Scene Analysis Based on Hierarchical Generative Model of Acoustic Event Sequence","display_name":"Acoustic Scene Analysis Based on Hierarchical Generative Model of Acoustic Event Sequence","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2527564651","doi":"https://doi.org/10.1587/transinf.2016slp0004","mag":"2527564651"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2016slp0004","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2016slp0004","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E99.D/10/E99.D_2016SLP0004/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E99.D/10/E99.D_2016SLP0004/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009991655","display_name":"Keisuke Imoto","orcid":"https://orcid.org/0000-0002-0703-8293"},"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":"Keisuke IMOTO","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074250128","display_name":"Suehiro Shimauchi","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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Suehiro SHIMAUCHI","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":2.7508,"has_fulltext":true,"cited_by_count":31,"citation_normalized_percentile":{"value":0.9149553,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"E99.D","issue":"10","first_page":"2539","last_page":"2549"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9930999875068665,"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/computer-science","display_name":"Computer science","score":0.733778715133667},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6634902954101562},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5873857140541077},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5637722611427307},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5246803164482117},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4927518665790558},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4523809552192688},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.45139145851135254},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.45004165172576904},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4477793276309967},{"id":"https://openalex.org/keywords/acoustic-shadow","display_name":"Acoustic shadow","score":0.4410557746887207},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35157281160354614},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.08440175652503967}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.733778715133667},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6634902954101562},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5873857140541077},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5637722611427307},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5246803164482117},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4927518665790558},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4523809552192688},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.45139145851135254},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.45004165172576904},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4477793276309967},{"id":"https://openalex.org/C47070683","wikidata":"https://www.wikidata.org/wiki/Q1906457","display_name":"Acoustic shadow","level":3,"score":0.4410557746887207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35157281160354614},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.08440175652503967},{"id":"https://openalex.org/C143753070","wikidata":"https://www.wikidata.org/wiki/Q162564","display_name":"Ultrasound","level":2,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2016slp0004","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2016slp0004","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E99.D/10/E99.D_2016SLP0004/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2016slp0004","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2016slp0004","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E99.D/10/E99.D_2016SLP0004/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2527564651.pdf","grobid_xml":"https://content.openalex.org/works/W2527564651.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W195465510","https://openalex.org/W1533561824","https://openalex.org/W1540550673","https://openalex.org/W1601404343","https://openalex.org/W1822987211","https://openalex.org/W1965387202","https://openalex.org/W1977834503","https://openalex.org/W2001082470","https://openalex.org/W2049633694","https://openalex.org/W2103235956","https://openalex.org/W2105068979","https://openalex.org/W2127639136","https://openalex.org/W2130428211","https://openalex.org/W2137343183","https://openalex.org/W2140124448","https://openalex.org/W2144037622","https://openalex.org/W2146078527","https://openalex.org/W2160860215","https://openalex.org/W2161353674","https://openalex.org/W2172085063","https://openalex.org/W2200782450","https://openalex.org/W2801754206","https://openalex.org/W3103385400"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W2280377497","https://openalex.org/W4387506531","https://openalex.org/W4238433571","https://openalex.org/W3174044702","https://openalex.org/W2967848559","https://openalex.org/W4283803360"],"abstract_inverted_index":{"We":[0],"propose":[1,92],"a":[2,27,46,100,135,153],"novel":[3],"method":[4,97,170],"for":[5,40],"estimating":[6,41],"acoustic":[7,34,42,49,53,62,83,86,94,107,116,122,130,148,157,177],"scenes":[8,43],"such":[9],"as":[10,134,152],"user":[11],"activities,":[12],"e.g.,":[13,20,64,73],"\u201ccooking,\u201d":[14,65],"\u201cvacuuming,\u201d":[15],"\u201cwatching":[16],"TV,\u201d":[17],"or":[18,76],"situations,":[19],"\u201cbeing":[21,25],"on":[22,99],"the":[23,31,56,113,126,168],"bus,\u201d":[24],"in":[26],"park,\u201d":[28],"\u201cmeeting,\u201d":[29],"utilizing":[30],"information":[32],"of":[33,48,105,176],"events.":[35,158],"There":[36],"are":[37],"some":[38],"methods":[39,58],"that":[44,66,167],"associate":[45,82],"combination":[47],"events":[50,84],"with":[51,85,163],"an":[52,93,106],"scene.":[54],"However,":[55],"existing":[57],"cannot":[59],"adequately":[60],"express":[61],"scenes,":[63,117],"have":[67],"more":[68],"than":[69],"one":[70],"subordinate":[71,119,141,174],"category,":[72],"\u201cfrying":[74],"ingredients\u201d":[75],"\u201cplating":[77],"food,\u201d":[78],"because":[79],"they":[80],"directly":[81],"scenes.":[87,178],"In":[88,125],"this":[89],"paper,":[90],"we":[91],"scene":[95,131,160],"estimation":[96,161],"based":[98],"hierarchical":[101],"probabilistic":[102],"generative":[103],"model":[104],"event":[108,123],"sequence":[109],"taking":[110],"into":[111],"account":[112],"relation":[114],"among":[115],"their":[118,139],"categories,":[120,142],"and":[121,146],"sequences.":[124],"proposed":[127,169],"model,":[128],"each":[129,147],"is":[132,150],"represented":[133,151],"probability":[136,154],"distribution":[137,155],"over":[138,156],"unsupervised":[140],"called":[143],"\u201cacoustic":[144],"sub-topics,\u201d":[145],"sub-topic":[149],"Acoustic":[159],"experiments":[162],"real-life":[164],"sounds":[165],"showed":[166],"could":[171],"correctly":[172],"extract":[173],"categories":[175]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
