{"id":"https://openalex.org/W2066148499","doi":"https://doi.org/10.1109/waspaa.2013.6701893","title":"Acoustic scene classification using sparse feature learning and event-based pooling","display_name":"Acoustic scene classification using sparse feature learning and event-based pooling","publication_year":2013,"publication_date":"2013-10-01","ids":{"openalex":"https://openalex.org/W2066148499","doi":"https://doi.org/10.1109/waspaa.2013.6701893","mag":"2066148499"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa.2013.6701893","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2013.6701893","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics","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/A5088852010","display_name":"Kyogu Lee","orcid":"https://orcid.org/0000-0002-4210-0312"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Kyogu Lee","raw_affiliation_strings":["Seoul National University, Music and Audio Research Group","Seoul National Univ"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Music and Audio Research Group","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Seoul National Univ","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090638243","display_name":"Ziwon Hyung","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ziwon Hyung","raw_affiliation_strings":["Seoul National University, Music and Audio Research Group","Seoul National Univ"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Music and Audio Research Group","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Seoul National Univ","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056437111","display_name":"Juhan Nam","orcid":"https://orcid.org/0000-0003-2664-2119"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juhan Nam","raw_affiliation_strings":["CCRMA, Stanford University","Stanford University"],"affiliations":[{"raw_affiliation_string":"CCRMA, Stanford University","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088852010"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":1.9152,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.86341806,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"22","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":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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.9923999905586243,"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/pooling","display_name":"Pooling","score":0.9320892095565796},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7628304958343506},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6634042859077454},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6176970601081848},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.609178900718689},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5957387685775757},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5129923224449158},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4460846483707428},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.43108686804771423},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4200245141983032},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35347574949264526}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.9320892095565796},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7628304958343506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6634042859077454},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6176970601081848},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.609178900718689},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5957387685775757},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5129923224449158},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4460846483707428},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.43108686804771423},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4200245141983032},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35347574949264526},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/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":1,"locations":[{"id":"doi:10.1109/waspaa.2013.6701893","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2013.6701893","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1966273763","https://openalex.org/W2107789863","https://openalex.org/W2133257461","https://openalex.org/W2136922672","https://openalex.org/W2150040608","https://openalex.org/W2188492526","https://openalex.org/W2293924895","https://openalex.org/W2395945925","https://openalex.org/W6676071220","https://openalex.org/W6679718588","https://openalex.org/W6686925444","https://openalex.org/W6711949533"],"related_works":["https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W4293232884","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870","https://openalex.org/W2138847091","https://openalex.org/W3044690502","https://openalex.org/W4309346246","https://openalex.org/W2786094008"],"abstract_inverted_index":{"Recently":[0],"unsupervised":[1],"learning":[2,21,50],"algorithms":[3,22],"have":[4,23],"been":[5],"successfully":[6],"used":[7,194],"to":[8,52,63],"represent":[9,73],"data":[10,35,71,75],"in":[11,76,137],"many":[12,39],"of":[13,134,184],"machine":[14,62],"recognition":[15],"tasks.":[16],"In":[17,42],"particular,":[18],"sparse":[19,48,59,79],"feature":[20,49,80,102],"shown":[24],"that":[25,167],"they":[26],"can":[27],"not":[28],"only":[29,126],"discover":[30],"meaningful":[31],"structures":[32,68],"from":[33,69],"raw":[34],"but":[36],"also":[37],"outperform":[38,170],"hand-engineered":[40],"features.":[41],"this":[43],"paper,":[44],"we":[45,89,111],"apply":[46],"the":[47,74,83,91,101,131,143,147,185],"approach":[51],"acoustic":[53,67,138],"scene":[54,87,98,139],"classification.":[55],"We":[56,141],"use":[57],"a":[58,77,113,156,182],"restricted":[60],"Boltzmann":[61],"capture":[64],"manyfold":[65],"local":[66,92],"audio":[70,97,120,135],"and":[72,122],"high-dimensional":[78],"space":[81],"given":[82],"learned":[84,144,168],"structures.":[85],"For":[86],"classification,":[88],"summarize":[90],"features":[93,145,169],"by":[94],"pooling":[95,103,115,125,173,179],"over":[96,107,127],"data.":[99,140],"While":[100],"is":[104],"typically":[105],"performed":[106],"uniformly":[108],"divided":[109],"segments,":[110],"suggest":[112],"new":[114],"method,":[116],"which":[117],"first":[118],"detects":[119],"events":[121,136],"then":[123],"performs":[124,188],"detected":[128],"events,":[129],"considering":[130],"irregular":[132],"occurrence":[133],"evaluate":[142],"on":[146],"IEEE":[148],"AASP":[149],"Challenge":[150],"development":[151],"set,":[152],"comparing":[153],"them":[154],"with":[155],"baseline":[157],"model":[158],"using":[159],"mel-frequency":[160],"cepstral":[161],"coefficients":[162],"(MFCCs).":[163],"The":[164],"results":[165],"show":[166],"MFCCs,":[171],"event-based":[172],"achieves":[174],"higher":[175],"accuracy":[176],"than":[177,191],"uniform":[178],"and,":[180],"furthermore,":[181],"combination":[183],"two":[186],"methods":[187],"even":[189],"better":[190],"either":[192],"one":[193],"alone.":[195]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}