{"id":"https://openalex.org/W3146364008","doi":"https://doi.org/10.1109/ieeeconf49454.2021.9382632","title":"An unsupervised auditory scene analysis system using incremental low-dimensional embedding","display_name":"An unsupervised auditory scene analysis system using incremental low-dimensional embedding","publication_year":2021,"publication_date":"2021-01-11","ids":{"openalex":"https://openalex.org/W3146364008","doi":"https://doi.org/10.1109/ieeeconf49454.2021.9382632","mag":"3146364008"},"language":"en","primary_location":{"id":"doi:10.1109/ieeeconf49454.2021.9382632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf49454.2021.9382632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/SICE International Symposium on System Integration (SII)","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/A5085244312","display_name":"Kenta Shinzato","orcid":null},"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":true,"raw_author_name":"Kenta Shinzato","raw_affiliation_strings":["Undergraduate School of Informatics and Mathematical Science Undergraduate Course Program of Applied Mathematics and Physics, Kyoto University, 54 Kawahara-cho, Shogoin, Sakyo-ku, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Undergraduate School of Informatics and Mathematical Science Undergraduate Course Program of Applied Mathematics and Physics, Kyoto University, 54 Kawahara-cho, Shogoin, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013489463","display_name":"Ryosuke Kojima","orcid":"https://orcid.org/0000-0003-1095-8864"},"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":"Ryosuke Kojima","raw_affiliation_strings":["Department of Biomedical Data Intelligence, Graduate School of Medicine, Kyoto University, 54 Kawahara-cho, Shogoin, Sakyo-ku, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Biomedical Data Intelligence, Graduate School of Medicine, Kyoto University, 54 Kawahara-cho, Shogoin, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5085244312"],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02608696,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":null,"first_page":"375","last_page":"381"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9972000122070312,"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/embedding","display_name":"Embedding","score":0.8212735652923584},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7906407117843628},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6310617923736572},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.569703221321106},{"id":"https://openalex.org/keywords/viewpoints","display_name":"Viewpoints","score":0.568523645401001},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5293905138969421},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5196515321731567},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5124600529670715},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.42389047145843506},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4181652367115021},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34267657995224},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33339744806289673},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3246407210826874},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10843834280967712},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08488312363624573}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8212735652923584},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7906407117843628},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6310617923736572},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.569703221321106},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.568523645401001},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5293905138969421},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5196515321731567},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5124600529670715},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.42389047145843506},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4181652367115021},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34267657995224},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33339744806289673},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3246407210826874},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10843834280967712},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08488312363624573},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ieeeconf49454.2021.9382632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf49454.2021.9382632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/SICE International Symposium on System Integration (SII)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1572146192","https://openalex.org/W1997822529","https://openalex.org/W2021850176","https://openalex.org/W2061074721","https://openalex.org/W2121065047","https://openalex.org/W2139047213","https://openalex.org/W2172536019","https://openalex.org/W2187089797","https://openalex.org/W2190506272","https://openalex.org/W2293488548","https://openalex.org/W2408744528","https://openalex.org/W2542768043","https://openalex.org/W2594166949","https://openalex.org/W2594538140","https://openalex.org/W2757154355","https://openalex.org/W2786672974","https://openalex.org/W2889326414","https://openalex.org/W2909977939","https://openalex.org/W2963425185","https://openalex.org/W2977823614","https://openalex.org/W2989747508","https://openalex.org/W2995445642","https://openalex.org/W2995891495","https://openalex.org/W3041102365","https://openalex.org/W4288098430","https://openalex.org/W6678139903","https://openalex.org/W6696754740","https://openalex.org/W6748816842","https://openalex.org/W6768378539","https://openalex.org/W6772119380"],"related_works":["https://openalex.org/W2385368906","https://openalex.org/W2902924992","https://openalex.org/W2626642044","https://openalex.org/W2619807045","https://openalex.org/W2388758053","https://openalex.org/W93537448","https://openalex.org/W2949734191","https://openalex.org/W2017333877","https://openalex.org/W4233821346","https://openalex.org/W2282742543"],"abstract_inverted_index":{"This":[0],"paper":[1,89],"addresses":[2],"the":[3,80,91,94,100,160],"low-dimensional":[4,20,37,59,65,141],"embedding":[5,38,43,66,142],"of":[6,55,76,93,102,122,170],"sounds":[7],"towards":[8],"unsupervised":[9],"auditory":[10],"scene":[11,95],"analysis.":[12],"Summarizing":[13],"long-time":[14,27,47,81,116],"recordings":[15],"by":[16],"mapping":[17],"them":[18],"into":[19],"space":[21],"is":[22,83],"an":[23,41,51,127],"essential":[24],"task":[25],"in":[26,115,145],"environmental":[28,176],"monitoring.":[29,177],"In":[30,105],"this":[31,88,103,106],"paper,":[32,107],"we":[33,49,108,130,148,166],"propose":[34],"a":[35,140],"novel":[36],"system":[39,53,97,151,172],"using":[40,163],"incremental":[42,52,118,128],"algorithm.":[44],"To":[45,125],"analyze":[46],"recordings,":[48],"design":[50],"consisting":[54],"recording,":[56],"feature":[57],"extraction,":[58],"embedding,":[60],"and":[61,98,120,173],"visualization.":[62],"Recently,":[63],"many":[64],"methods":[67,78,119],"for":[68],"acoustic":[69],"scenes":[70],"have":[71],"been":[72],"studied;":[73],"however,":[74],"applicability":[75,174],"these":[77],"to":[79,152,175],"recording":[82],"not":[84],"adequately":[85],"evaluated.":[86],"Thus,":[87],"describes":[90],"construction":[92],"analysis":[96,155],"evaluates":[99],"performance":[101],"system.":[104],"especially":[109],"focus":[110],"on":[111],"two":[112],"important":[113],"viewpoints":[114],"monitoring:":[117],"effects":[121],"noisy":[123],"data.":[124],"realize":[126],"system,":[129],"use":[131],"Self-Organizing":[132],"Nebulous":[133],"Growths":[134],"(SONG),":[135],"which":[136],"can":[137],"incrementally":[138],"construct":[139],"space.":[143],"Also,":[144],"our":[146,150,171],"experiments,":[147],"apply":[149],"bird":[153],"song":[154],"under":[156],"noise":[157,168],"conditions.":[158],"By":[159],"preliminary":[161],"experiments":[162],"benchmark":[164],"datasets,":[165],"discover":[167],"sensitivity":[169]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}