{"id":"https://openalex.org/W2902444285","doi":"https://doi.org/10.23919/eusipco.2018.8553247","title":"Convolutional Recurrent Neural Networks for Urban Sound Classification Using Raw Waveforms","display_name":"Convolutional Recurrent Neural Networks for Urban Sound Classification Using Raw Waveforms","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2902444285","doi":"https://doi.org/10.23919/eusipco.2018.8553247","mag":"2902444285"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco.2018.8553247","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2018.8553247","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 26th European Signal Processing Conference (EUSIPCO)","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/A5016719660","display_name":"Jonghee Sang","orcid":null},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jonghee Sang","raw_affiliation_strings":["ETRI, Korea"],"affiliations":[{"raw_affiliation_string":"ETRI, Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087072036","display_name":"Soomyung Park","orcid":null},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soomyung Park","raw_affiliation_strings":["ETRI, Korea"],"affiliations":[{"raw_affiliation_string":"ETRI, Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101444556","display_name":"JunWoo Lee","orcid":"https://orcid.org/0000-0002-0141-4980"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Junwoo Lee","raw_affiliation_strings":["ETRI, Korea"],"affiliations":[{"raw_affiliation_string":"ETRI, Korea","institution_ids":["https://openalex.org/I142401562"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016719660"],"corresponding_institution_ids":["https://openalex.org/I142401562"],"apc_list":null,"apc_paid":null,"fwci":4.4908,"has_fulltext":false,"cited_by_count":83,"citation_normalized_percentile":{"value":0.95631795,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2444","last_page":"2448"},"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":0.9973999857902527,"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":0.9922999739646912,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.8067482709884644},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7842722535133362},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7184925079345703},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6384307742118835},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5829654932022095},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5318004488945007},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5135310292243958},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49961304664611816},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4737192988395691},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39570483565330505},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34631913900375366},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06963899731636047},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.05118018388748169}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.8067482709884644},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7842722535133362},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7184925079345703},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6384307742118835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5829654932022095},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5318004488945007},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5135310292243958},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49961304664611816},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4737192988395691},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39570483565330505},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34631913900375366},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06963899731636047},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.05118018388748169},{"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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco.2018.8553247","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2018.8553247","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 26th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.8399999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1496704041","https://openalex.org/W1511170870","https://openalex.org/W1522301498","https://openalex.org/W1533861849","https://openalex.org/W1836465849","https://openalex.org/W2038484192","https://openalex.org/W2059652044","https://openalex.org/W2089368853","https://openalex.org/W2095705004","https://openalex.org/W2119662931","https://openalex.org/W2130640900","https://openalex.org/W2135342008","https://openalex.org/W2140647972","https://openalex.org/W2147174722","https://openalex.org/W2154252319","https://openalex.org/W2191779130","https://openalex.org/W2196961052","https://openalex.org/W2211849486","https://openalex.org/W2232894815","https://openalex.org/W2250966211","https://openalex.org/W2292996718","https://openalex.org/W2398826216","https://openalex.org/W2401869809","https://openalex.org/W2403172465","https://openalex.org/W2403438050","https://openalex.org/W2408093180","https://openalex.org/W2529337537","https://openalex.org/W2593179621","https://openalex.org/W2593451766","https://openalex.org/W2621651613","https://openalex.org/W2622368070","https://openalex.org/W2745357708","https://openalex.org/W2766397045","https://openalex.org/W2949117887","https://openalex.org/W2963162200","https://openalex.org/W2964121744","https://openalex.org/W3028311979","https://openalex.org/W3105202226","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6674330103","https://openalex.org/W6713049558","https://openalex.org/W6734751391","https://openalex.org/W6738953990","https://openalex.org/W6742410318"],"related_works":["https://openalex.org/W1974895211","https://openalex.org/W2129841057","https://openalex.org/W3040712279","https://openalex.org/W2176409448","https://openalex.org/W4225394202","https://openalex.org/W4226493464","https://openalex.org/W3133861977","https://openalex.org/W2951211570","https://openalex.org/W3103566983","https://openalex.org/W3008584592"],"abstract_inverted_index":{"Recent":[0],"studies":[1],"have":[2,11],"demonstrated":[3],"deep":[4],"learning":[5],"approaches":[6],"directly":[7,45],"from":[8],"raw":[9,113],"data":[10],"been":[12,22],"successfully":[13],"used":[14],"in":[15,51,118],"image":[16],"and":[17,73,122],"text.":[18],"This":[19],"approach":[20],"has":[21],"applied":[23],"to":[24,130],"audio":[25],"signals":[26],"as":[27,49],"well":[28],"but":[29],"not":[30],"fully":[31],"explored":[32],"yet.":[33],"In":[34],"this":[35],"works,":[36],"we":[37],"propose":[38],"a":[39],"convolutional":[40,66,108],"recurrent":[41,59,74,109],"neural":[42,60,67,75,110],"network":[43,61,111],"that":[44],"uses":[46],"time-domain":[47],"waveforms":[48,114],"input":[50],"the":[52,81,89,92,116,131],"domain":[53],"of":[54,65,80,96,125,133],"urban":[55,97,119],"sound":[56,71,99,120],"classification.":[57],"Convolutional":[58],"is":[62],"combined":[63],"model":[64],"networks":[68,76],"for":[69,77,102],"extracting":[70],"features":[72],"temporal":[78],"aggregation":[79],"extracted":[82],"features.":[83],"The":[84,104],"method":[85],"was":[86],"evaluated":[87],"using":[88],"UrbanSound8k":[90],"dataset,":[91],"largest":[93],"public":[94],"dataset":[95],"environmental":[98],"sources":[100],"available":[101],"research.":[103],"results":[105],"show":[106],"how":[107],"with":[112,128],"improve":[115],"accuracy":[117],"classification":[121],"provide":[123],"effectiveness":[124],"its":[126],"structure":[127],"respect":[129],"number":[132],"parameters.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}