{"id":"https://openalex.org/W4405271548","doi":"https://doi.org/10.1109/cvmi61877.2024.10781826","title":"Elevating Environmental Sound Classification with Stacked Convolutional Neural Networks","display_name":"Elevating Environmental Sound Classification with Stacked Convolutional Neural Networks","publication_year":2024,"publication_date":"2024-10-19","ids":{"openalex":"https://openalex.org/W4405271548","doi":"https://doi.org/10.1109/cvmi61877.2024.10781826"},"language":"en","primary_location":{"id":"doi:10.1109/cvmi61877.2024.10781826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvmi61877.2024.10781826","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Computer Vision and Machine Intelligence (CVMI)","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":null,"display_name":"Shreyan Mittal","orcid":null},"institutions":[{"id":"https://openalex.org/I33459947","display_name":"Charotar University of Science and Technology","ror":"https://ror.org/0442pkv24","country_code":"IN","type":"education","lineage":["https://openalex.org/I33459947"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Shreyan Mittal","raw_affiliation_strings":["CSPIT, CHARUSAT,Department of Computer Science and Engineering,Anand,India"],"affiliations":[{"raw_affiliation_string":"CSPIT, CHARUSAT,Department of Computer Science and Engineering,Anand,India","institution_ids":["https://openalex.org/I33459947"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004124938","display_name":"Drashti Patel","orcid":null},"institutions":[{"id":"https://openalex.org/I33459947","display_name":"Charotar University of Science and Technology","ror":"https://ror.org/0442pkv24","country_code":"IN","type":"education","lineage":["https://openalex.org/I33459947"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Drashti Patel","raw_affiliation_strings":["CSPIT, CHARUSAT,Department of Computer Science and Engineering,Anand,India"],"affiliations":[{"raw_affiliation_string":"CSPIT, CHARUSAT,Department of Computer Science and Engineering,Anand,India","institution_ids":["https://openalex.org/I33459947"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003117267","display_name":"Mrugendrasinh Rahevar","orcid":"https://orcid.org/0000-0002-0551-9229"},"institutions":[{"id":"https://openalex.org/I33459947","display_name":"Charotar University of Science and Technology","ror":"https://ror.org/0442pkv24","country_code":"IN","type":"education","lineage":["https://openalex.org/I33459947"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mrugendrasinh Rahevar","raw_affiliation_strings":["CSPIT, CHARUSAT,U & P U. Patel Department of Computer Engineering,Anand,India"],"affiliations":[{"raw_affiliation_string":"CSPIT, CHARUSAT,U & P U. Patel Department of Computer Engineering,Anand,India","institution_ids":["https://openalex.org/I33459947"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I33459947"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24503311,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9965999722480774,"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":0.9965999722480774,"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":0.9419999718666077,"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":0.9283000230789185,"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/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7480261921882629},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7034133672714233},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.48898231983184814},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47862640023231506},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3724258542060852},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3446590304374695},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.19341787695884705},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.058014094829559326}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7480261921882629},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7034133672714233},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.48898231983184814},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47862640023231506},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3724258542060852},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3446590304374695},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.19341787695884705},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.058014094829559326}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvmi61877.2024.10781826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvmi61877.2024.10781826","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Computer Vision and Machine Intelligence (CVMI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","score":0.7599999904632568,"display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W648910355","https://openalex.org/W1501987291","https://openalex.org/W1972567154","https://openalex.org/W2020290924","https://openalex.org/W2037533030","https://openalex.org/W2040064214","https://openalex.org/W2103235956","https://openalex.org/W2509065397","https://openalex.org/W2751841560","https://openalex.org/W2801920224","https://openalex.org/W2902444285","https://openalex.org/W2907020666","https://openalex.org/W2909327627","https://openalex.org/W2973284423","https://openalex.org/W3014593905","https://openalex.org/W3083566224","https://openalex.org/W3092956051","https://openalex.org/W3133941734","https://openalex.org/W4200337780","https://openalex.org/W4311765953","https://openalex.org/W4318831574","https://openalex.org/W6712469065","https://openalex.org/W6781150751"],"related_works":["https://openalex.org/W2909726438","https://openalex.org/W2067046791","https://openalex.org/W4391621807","https://openalex.org/W2909888262","https://openalex.org/W4321487865","https://openalex.org/W2025747832","https://openalex.org/W4313906399","https://openalex.org/W3020957235","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Environmental":[0],"sound":[1,33],"classification":[2],"(ESC)":[3],"stands":[4],"as":[5],"a":[6,84,94],"cornerstone":[7],"in":[8,31,108],"audio":[9,15,39,120],"recognition,":[10],"with":[11,115],"far-reaching":[12],"applications":[13],"encompassing":[14],"surveillance":[16],"and":[17,72],"forensic":[18],"investigations.":[19],"Yet,":[20],"ESC":[21,45,52,78,113],"presents":[22],"formidable":[23],"hurdles":[24],"owing":[25],"to":[26,50,75],"the":[27,47,64,103,110],"nuanced":[28],"complexities":[29],"inherent":[30],"environmental":[32],"data,":[34],"diverging":[35],"significantly":[36],"from":[37],"conventional":[38],"sources.":[40],"Our":[41],"study":[42],"delves":[43],"into":[44],"utilizing":[46],"UrbanSound8k":[48],"dataset":[49],"investigate":[51],"using":[53],"Stacked":[54],"Convolutional":[55],"Neural":[56],"Networks":[57],"(CNNs).":[58],"Through":[59],"meticulous":[60],"experimentation,":[61],"we":[62],"probe":[63],"intricate":[65],"interplay":[66],"of":[67,87,105,112],"hyperparameters,":[68],"including":[69],"layer":[70],"count":[71],"filter":[73],"configurations,":[74],"finely":[76],"tune":[77],"accuracy.":[79],"Notably,":[80],"our":[81,106],"method":[82],"yields":[83],"peak":[85],"accuracy":[86],"${9":[88],"3.":[89],"8":[90],"2":[91],"\\%}$,":[92],"showcasing":[93],"significant":[95],"improvement":[96],"over":[97],"existing":[98],"benchmarks.":[99],"This":[100],"achievement":[101],"underscores":[102],"efficacy":[104],"approach":[107],"pushing":[109],"boundaries":[111],"research,":[114],"implications":[116],"for":[117],"advancing":[118],"state-of-the-art":[119],"recognition":[121],"technologies.":[122]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}