{"id":"https://openalex.org/W3113043802","doi":"https://doi.org/10.1145/3441417.3441431","title":"CnnSound: Convolutional Neural Networks for the Classification of Environmental Sounds","display_name":"CnnSound: Convolutional Neural Networks for the Classification of Environmental Sounds","publication_year":2020,"publication_date":"2020-10-09","ids":{"openalex":"https://openalex.org/W3113043802","doi":"https://doi.org/10.1145/3441417.3441431","mag":"3113043802"},"language":"en","primary_location":{"id":"doi:10.1145/3441417.3441431","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3441417.3441431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 The 4th International Conference on Advances in Artificial Intelligence","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/A5057405456","display_name":"H\u00fcseyin \u015eeker","orcid":"https://orcid.org/0000-0002-1255-9552"},"institutions":[{"id":"https://openalex.org/I198012923","display_name":"University of Staffordshire","ror":"https://ror.org/00d6k8y35","country_code":"GB","type":"education","lineage":["https://openalex.org/I198012923"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Huseyin Seker","raw_affiliation_strings":["Staffordshire University, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Staffordshire University, UK","institution_ids":["https://openalex.org/I198012923"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026639416","display_name":"\u00d6zkan \u0130ni\u0307k","orcid":"https://orcid.org/0000-0003-4728-8438"},"institutions":[{"id":"https://openalex.org/I238144855","display_name":"Tokat Gaziosmanpa\u015fa \u00dcniversitesi","ror":"https://ror.org/01rpe9k96","country_code":"TR","type":"education","lineage":["https://openalex.org/I238144855"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Ozkan Inik","raw_affiliation_strings":["Tokat Gaziosmanpa\u00fea University, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokat Gaziosmanpa\u00fea University, Turkey","institution_ids":["https://openalex.org/I238144855"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7416,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.7150273,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"79","last_page":"84"},"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":0.9945999979972839,"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":0.9929999709129333,"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/computer-science","display_name":"Computer science","score":0.7857046723365784},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7855560779571533},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.661199688911438},{"id":"https://openalex.org/keywords/environmental-noise","display_name":"Environmental noise","score":0.6416403651237488},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5862246751785278},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5726957321166992},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4882824420928955},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.48311638832092285},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44382548332214355},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41651594638824463},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.3928833305835724},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3882068693637848},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3751872181892395},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2919098138809204},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08303654193878174},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07447952032089233}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7857046723365784},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7855560779571533},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.661199688911438},{"id":"https://openalex.org/C86781634","wikidata":"https://www.wikidata.org/wiki/Q2478325","display_name":"Environmental noise","level":3,"score":0.6416403651237488},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5862246751785278},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5726957321166992},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4882824420928955},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.48311638832092285},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44382548332214355},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41651594638824463},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.3928833305835724},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3882068693637848},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3751872181892395},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2919098138809204},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08303654193878174},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07447952032089233},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3441417.3441431","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3441417.3441431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 The 4th International Conference on Advances in Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.staffs.ac.uk:6640","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401113","display_name":"Staffordshire Online Repository (Staffordshire University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I198012923","host_organization_name":"University of Staffordshire","host_organization_lineage":["https://openalex.org/I198012923"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.7900000214576721,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W1496704041","https://openalex.org/W1844944916","https://openalex.org/W1875800788","https://openalex.org/W1972043280","https://openalex.org/W1972567154","https://openalex.org/W2031339194","https://openalex.org/W2038484192","https://openalex.org/W2046972719","https://openalex.org/W2061686014","https://openalex.org/W2064311306","https://openalex.org/W2086384421","https://openalex.org/W2089368853","https://openalex.org/W2103235956","https://openalex.org/W2104680684","https://openalex.org/W2114777924","https://openalex.org/W2121272582","https://openalex.org/W2130640900","https://openalex.org/W2135342008","https://openalex.org/W2137343183","https://openalex.org/W2137561966","https://openalex.org/W2161755617","https://openalex.org/W2163605009","https://openalex.org/W2211849486","https://openalex.org/W2343999517","https://openalex.org/W2403518287","https://openalex.org/W2422999386","https://openalex.org/W2481544852","https://openalex.org/W2493586332","https://openalex.org/W2509065397","https://openalex.org/W2529337537","https://openalex.org/W2544224704","https://openalex.org/W2552850818","https://openalex.org/W2619623002","https://openalex.org/W2751841560","https://openalex.org/W2768083292","https://openalex.org/W2768188490","https://openalex.org/W2791611639","https://openalex.org/W2799016299","https://openalex.org/W2811482466","https://openalex.org/W2866575265","https://openalex.org/W2883588054","https://openalex.org/W2890026644","https://openalex.org/W2899318643","https://openalex.org/W2902422112","https://openalex.org/W2905547304","https://openalex.org/W2912899030","https://openalex.org/W2920665996","https://openalex.org/W2937047963","https://openalex.org/W2961301969","https://openalex.org/W2963543871","https://openalex.org/W2963838685","https://openalex.org/W2974308198","https://openalex.org/W2982052411","https://openalex.org/W2993777217","https://openalex.org/W2999819273","https://openalex.org/W3022215617","https://openalex.org/W3043920615","https://openalex.org/W3082878506","https://openalex.org/W3098357269","https://openalex.org/W3103385400","https://openalex.org/W4398958419","https://openalex.org/W6675827131"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W2909726438","https://openalex.org/W2067046791","https://openalex.org/W2909888262","https://openalex.org/W2056769785","https://openalex.org/W4313906399","https://openalex.org/W4321487865","https://openalex.org/W3020957235","https://openalex.org/W2964954556","https://openalex.org/W3019910406"],"abstract_inverted_index":{"The":[0,13,63,95,153,168,220],"classification":[1],"of":[2,22,98,125,129,143,166,176,231],"environmental":[3,18,55,148],"sounds":[4,19,71,154],"(ESC)":[5],"has":[6,172,197],"been":[7,198],"increasingly":[8],"studied":[9],"in":[10,35,38,45,82,134,155,239],"recent":[11],"years.":[12],"main":[14,96],"reason":[15],"is":[16,36,43,65,101],"that":[17,32,78,191],"are":[20,74,218],"part":[21],"our":[23,30],"daily":[24],"life,":[25],"and":[26,93,127,203,215,236],"associating":[27],"them":[28],"with":[29],"environment":[31,61],"we":[33],"live":[34],"important":[37],"several":[39],"aspects":[40],"as":[41,48,177,179],"ESC":[42,64],"used":[44,133],"areas":[46],"such":[47],"managing":[49],"smart":[50],"cities,":[51],"determining":[52],"location":[53],"from":[54],"sounds,":[56],"surveillance":[57],"systems,":[58],"machine":[59],"hearing,":[60],"monitoring.":[62],"however":[66],"more":[67,89,105],"difficult":[68,90],"than":[69,183],"other":[70,207],"because":[72],"there":[73,188],"too":[75],"many":[76],"parameters":[77,132],"generate":[79],"background":[80],"noise":[81],"the":[83,87,123,135,141,144,146,194,210,232],"ESC,":[84],"which":[85],"makes":[86],"sound":[88,149],"to":[91,103,139,200,206,228],"model":[92,171],"classify.":[94],"aim":[97],"this":[99,113,156],"study":[100],"therefore":[102],"develop":[104],"robust":[106],"convolution":[107],"neural":[108],"networks":[109],"architecture":[110,235],"(CNN).":[111],"For":[112],"purpose,":[114],"150":[115],"different":[116],"CNN-based":[117],"models":[118],"were":[119,159],"designed":[120],"by":[121],"changing":[122],"number":[124],"layers":[126],"values":[128],"their":[130],"tuning":[131],"layers.":[136],"In":[137],"order":[138],"test":[140],"accuracy":[142,175,196,214],"models,":[145],"Urbansound8k":[147,211],"database":[150],"was":[151,189],"used.":[152],"data":[157],"set":[158],"first":[160],"converted":[161],"into":[162],"an":[163,174],"image":[164],"format":[165],"32x32x3.":[167],"proposed":[169,233],"CNN":[170,234],"yielded":[173],"much":[178,192],"82.5%":[180],"being":[181],"higher":[182],"its":[184,237],"classical":[185],"counterpart.":[186],"As":[187],"not":[190],"fine-tuning,":[193],"obtained":[195],"found":[199],"be":[201],"better":[202],"satisfactory":[204],"compared":[205],"studies":[208],"on":[209],"when":[212],"both":[213],"computational":[216],"complexity":[217,230],"considered.":[219],"results":[221],"also":[222],"suggest":[223],"further":[224],"improvement":[225],"possible":[226],"due":[227],"low":[229],"applicability":[238],"real-world":[240],"settings.":[241]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}