{"id":"https://openalex.org/W3012693711","doi":"https://doi.org/10.21437/interspeech.2020-992","title":"Acoustic Scene Classification Using Audio Tagging","display_name":"Acoustic Scene Classification Using Audio Tagging","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3012693711","doi":"https://doi.org/10.21437/interspeech.2020-992","mag":"3012693711"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-992","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jee-weon Jung","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103211980","display_name":"Hye-jin Shim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hye-jin Shim","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101866564","display_name":"Ju-ho Kim","orcid":"https://orcid.org/0009-0001-4055-4564"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ju-ho Kim","raw_affiliation_strings":["NAVER CORPORATION"],"affiliations":[{"raw_affiliation_string":"NAVER CORPORATION","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028147662","display_name":"Seung-bin Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seung-bin Kim","raw_affiliation_strings":["NAVER CORPORATION"],"affiliations":[{"raw_affiliation_string":"NAVER CORPORATION","institution_ids":[]}]},{"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,"],"affiliations":[{"raw_affiliation_string":"University of Seoul,","institution_ids":["https://openalex.org/I124633538"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5091834525"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4546,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.59045425,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1176","last_page":"1180"},"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":0.9987999796867371,"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/T13996","display_name":"Diverse Musicological Studies","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8002784848213196},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7397952079772949},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6606770753860474},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5544680953025818},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.5276828408241272},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4885057210922241},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4792221188545227},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.45603856444358826},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4339510202407837},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.42476963996887207}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8002784848213196},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7397952079772949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6606770753860474},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5544680953025818},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.5276828408241272},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4885057210922241},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4792221188545227},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.45603856444358826},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4339510202407837},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.42476963996887207},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-992","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W2029960962","https://openalex.org/W2194775991","https://openalex.org/W2302255633","https://openalex.org/W2327501763","https://openalex.org/W2402040300","https://openalex.org/W2527564651","https://openalex.org/W2765407302","https://openalex.org/W2901459357","https://openalex.org/W2903099953","https://openalex.org/W2913795158","https://openalex.org/W2936774411","https://openalex.org/W2949117887","https://openalex.org/W2963403868","https://openalex.org/W2964052309","https://openalex.org/W2964308564","https://openalex.org/W2971670255","https://openalex.org/W2972369255","https://openalex.org/W2972581694","https://openalex.org/W2982343573","https://openalex.org/W2982461124","https://openalex.org/W2982683041","https://openalex.org/W2995348821","https://openalex.org/W3015700860"],"related_works":["https://openalex.org/W2373577936","https://openalex.org/W4387678054","https://openalex.org/W3095575180","https://openalex.org/W2389596151","https://openalex.org/W4221148444","https://openalex.org/W4226054107","https://openalex.org/W4306784355","https://openalex.org/W2510951244","https://openalex.org/W4246226292","https://openalex.org/W2150768546"],"abstract_inverted_index":{"Acoustic":[0],"scene":[1,24,89,105],"classification":[2,25,90,106,117,140],"systems":[3],"using":[4,63,76,108],"deep":[5],"neural":[6],"networks":[7],"classify":[8],"given":[9],"recordings":[10],"into":[11],"pre-defined":[12],"classes.":[13],"In":[14],"this":[15,61],"study,":[16],"we":[17,67],"propose":[18],"a":[19,139],"novel":[20],"scheme":[21],"for":[22],"acoustic":[23,42,88,104,119],"which":[26,53],"adopts":[27],"an":[28,41,77,82,87,103,166],"audio":[29,78],"tagging":[30,79],"system":[31,80,107,158],"inspired":[32],"by":[33],"the":[34,44,55,95,99,114,128,131,155,160],"human":[35],"perception":[36],"mechanism.":[37],"When":[38],"humans":[39],"identify":[40],"scene,":[43],"existence":[45],"of":[46,86,102,118,130,142,154,168],"different":[47],"sound":[48],"events":[49,122],"provides":[50],"discriminative":[51],"information":[52],"affects":[54],"judgement.":[56],"The":[57,157],"proposed":[58,132,161],"framework":[59],"mimics":[60],"mechanism":[62],"various":[64],"approaches.":[65],"Firstly,":[66],"employ":[68],"three":[69],"methods":[70],"to":[71,150],"concatenate":[72],"tag":[73,109],"vectors":[74],"extracted":[75],"with":[81,159],"intermediate":[83],"hidden":[84],"layer":[85],"system.":[91],"We":[92],"also":[93],"explore":[94],"multi-head":[96,136],"attention":[97,137],"on":[98,113],"feature":[100],"map":[101],"vectors.":[110],"Experiments":[111],"conducted":[112],"detection":[115],"and":[116,121,135,145],"scenes":[120],"2019":[123],"task":[124],"1-a":[125],"dataset":[126],"demonstrate":[127],"effectiveness":[129],"scheme.":[133],"Concatenation":[134],"show":[138],"accuracy":[141,153,167],"75.66":[143],"%":[144,152],"75.58":[146],"%,":[147],"respectively,":[148],"compared":[149],"73.63":[151],"baseline.":[156],"two":[162],"approaches":[163],"combined":[164],"demonstrates":[165],"76.75":[169],"%.":[170]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
