{"id":"https://openalex.org/W3161638288","doi":"https://doi.org/10.1109/icassp39728.2021.9414406","title":"DCASENET: An Integrated Pretrained Deep Neural Network for Detecting and Classifying Acoustic Scenes and Events","display_name":"DCASENET: An Integrated Pretrained Deep Neural Network for Detecting and Classifying Acoustic Scenes and Events","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161638288","doi":"https://doi.org/10.1109/icassp39728.2021.9414406","mag":"3161638288"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414406","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414406","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5091834525","display_name":"Jee-weon Jung","orcid":"https://orcid.org/0000-0003-0505-2988"},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]},{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jee-weon Jung","raw_affiliation_strings":["University of Seoul,School of Computer Science","School of Computer Science, University of Seoul","Naver Corporation"],"affiliations":[{"raw_affiliation_string":"University of Seoul,School of Computer Science","institution_ids":["https://openalex.org/I124633538"]},{"raw_affiliation_string":"School of Computer Science, University of Seoul","institution_ids":["https://openalex.org/I124633538"]},{"raw_affiliation_string":"Naver Corporation","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103211980","display_name":"Hye-jin Shim","orcid":null},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hye-jin Shim","raw_affiliation_strings":["University of Seoul,School of Computer Science","School of Computer Science, University of Seoul"],"affiliations":[{"raw_affiliation_string":"University of Seoul,School of Computer Science","institution_ids":["https://openalex.org/I124633538"]},{"raw_affiliation_string":"School of Computer Science, University of Seoul","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101866564","display_name":"Ju-ho Kim","orcid":"https://orcid.org/0009-0001-4055-4564"},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ju-ho Kim","raw_affiliation_strings":["University of Seoul,School of Computer Science","School of Computer Science, University of Seoul"],"affiliations":[{"raw_affiliation_string":"University of Seoul,School of Computer Science","institution_ids":["https://openalex.org/I124633538"]},{"raw_affiliation_string":"School of Computer Science, University of Seoul","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030475312","display_name":"Ha-Jin Yu","orcid":"https://orcid.org/0000-0003-3657-0665"},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ha-Jin Yu","raw_affiliation_strings":["University of Seoul,School of Computer Science","School of Computer Science, University of Seoul"],"affiliations":[{"raw_affiliation_string":"University of Seoul,School of Computer Science","institution_ids":["https://openalex.org/I124633538"]},{"raw_affiliation_string":"School of Computer Science, University of Seoul","institution_ids":["https://openalex.org/I124633538"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5091834525"],"corresponding_institution_ids":["https://openalex.org/I124633538","https://openalex.org/I60922564"],"apc_list":null,"apc_paid":null,"fwci":2.8949,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.91528059,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"621","last_page":"625"},"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":0.9969000220298767,"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":0.9839000105857849,"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":0.8174562454223633},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6917113065719604},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6634234189987183},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.562056303024292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5490936040878296},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5454472303390503},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5363166928291321},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5286954641342163},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.49212807416915894},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4822959899902344},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.44140422344207764},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3883606791496277},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3582829236984253},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.06642857193946838}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8174562454223633},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6917113065719604},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6634234189987183},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.562056303024292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5490936040878296},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5454472303390503},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5363166928291321},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5286954641342163},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.49212807416915894},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4822959899902344},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.44140422344207764},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3883606791496277},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3582829236984253},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.06642857193946838},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"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/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/icassp39728.2021.9414406","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414406","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W343636949","https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W2029960962","https://openalex.org/W2095705004","https://openalex.org/W2103235956","https://openalex.org/W2108598243","https://openalex.org/W2302255633","https://openalex.org/W2403172465","https://openalex.org/W2765407302","https://openalex.org/W2885782501","https://openalex.org/W2900315145","https://openalex.org/W2913340405","https://openalex.org/W2942551338","https://openalex.org/W2957789971","https://openalex.org/W2963399829","https://openalex.org/W2964121744","https://openalex.org/W2982461124","https://openalex.org/W2982480602","https://openalex.org/W2987999870","https://openalex.org/W2995348821","https://openalex.org/W2997308807","https://openalex.org/W3009927332","https://openalex.org/W3015700860","https://openalex.org/W3023371261","https://openalex.org/W3083146453","https://openalex.org/W3096083178","https://openalex.org/W3098454764","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6674330103","https://openalex.org/W6745136726","https://openalex.org/W6753511437","https://openalex.org/W6765212446"],"related_works":["https://openalex.org/W4375867731","https://openalex.org/W2611989081","https://openalex.org/W4230611425","https://openalex.org/W2731899572","https://openalex.org/W4304166257","https://openalex.org/W4294635752","https://openalex.org/W4377865163","https://openalex.org/W3193857078","https://openalex.org/W2888956734","https://openalex.org/W3208304128"],"abstract_inverted_index":{"Although":[0],"acoustic":[1,32,76],"scenes":[2],"and":[3,12,37,105,192],"events":[4,68],"include":[5],"many":[6],"related":[7],"tasks,":[8],"their":[9],"combined":[10],"detection":[11],"classification":[13,60],"have":[14],"been":[15],"scarcely":[16],"investigated.":[17],"We":[18],"propose":[19],"three":[20,153,158],"architectures":[21,44],"of":[22,61,85,99,174,187],"deep":[23],"neural":[24],"networks":[25],"that":[26,69,124,143,161],"are":[27,45,70,196],"integrated":[28,141],"to":[29,73,120,138,150,183],"simultaneously":[30],"perform":[31,126,151],"scene":[33,59],"classification,":[34],"audio":[35],"tagging,":[36],"sound":[38,67],"event":[39],"detection.":[40],"The":[41,51,78,113,135,190],"first":[42,52,95],"two":[43],"inspired":[46],"by":[47],"human":[48],"cognitive":[49],"processes.":[50],"architecture":[53,80,115],"resembles":[54,81],"the":[55,75,82,89,97,121,152,162,175,185],"short-term":[56],"perception":[57],"for":[58,172],"adults,":[62],"who":[63],"can":[64,144,167],"detect":[65],"various":[66],"then":[71,106],"used":[72,171],"identify":[74],"scene.":[77],"second":[79,122],"long-term":[83],"learning":[84],"babies,":[86],"being":[87],"also":[88],"concept":[90],"under-lying":[91],"self-supervised":[92],"learning.":[93],"Babies":[94],"observe":[96],"effects":[98],"abstract":[100],"notions":[101],"such":[102,111],"as":[103,146],"gravity":[104],"learn":[107],"specific":[108],"tasks":[109,176],"using":[110],"perceptions.":[112],"third":[114],"adds":[116],"a":[117,127,147],"few":[118],"layers":[119],"one":[123,188],"solely":[125],"single":[128],"task":[129],"before":[130],"its":[131],"corresponding":[132],"output":[133],"layer.":[134],"aim":[136],"is":[137],"build":[139],"an":[140],"system":[142],"serve":[145],"pretrained":[148,193],"model":[149],"abovementioned":[154],"tasks.":[155],"Experiments":[156],"on":[157],"datasets":[159],"demonstrate":[160],"proposed":[163],"architecture,":[164],"called":[165],"DcaseNet,":[166],"be":[168],"either":[169],"directly":[170],"any":[173],"while":[177],"providing":[178],"suitable":[179],"results":[180],"or":[181],"fine-tuned":[182],"improve":[184],"performance":[186],"task.":[189],"code":[191],"DcaseNet":[194],"weights":[195],"available":[197],"at":[198],"https://github.com/Jungjee/DcaseNet.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}