{"id":"https://openalex.org/W4213366994","doi":"https://doi.org/10.1109/lsp.2022.3150258","title":"CNN-RNN and Data Augmentation Using Deep Convolutional Generative Adversarial Network for Environmental Sound Classification","display_name":"CNN-RNN and Data Augmentation Using Deep Convolutional Generative Adversarial Network for Environmental Sound Classification","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4213366994","doi":"https://doi.org/10.1109/lsp.2022.3150258"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2022.3150258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2022.3150258","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5084090230","display_name":"Behnaz Bahmei","orcid":"https://orcid.org/0000-0002-9036-3352"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Behnaz Bahmei","raw_affiliation_strings":["School of Mechatronics System Engineering, Simon Fraser University, Surrey, BC, Canada"],"raw_orcid":"https://orcid.org/0000-0002-9036-3352","affiliations":[{"raw_affiliation_string":"School of Mechatronics System Engineering, Simon Fraser University, Surrey, BC, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053018438","display_name":"Elina Birmingham","orcid":"https://orcid.org/0000-0001-7172-8582"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Elina Birmingham","raw_affiliation_strings":["Faculty of Education, Simon Fraser University, Burnaby, BC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Education, Simon Fraser University, Burnaby, BC, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001883401","display_name":"Siamak Arzanpour","orcid":"https://orcid.org/0000-0001-7734-9372"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Siamak Arzanpour","raw_affiliation_strings":["School of Mechatronics System Engineering, Simon Fraser University, Surrey, BC, Canada"],"raw_orcid":"https://orcid.org/0000-0001-7734-9372","affiliations":[{"raw_affiliation_string":"School of Mechatronics System Engineering, Simon Fraser University, Surrey, BC, Canada","institution_ids":["https://openalex.org/I18014758"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":16.2028,"has_fulltext":false,"cited_by_count":117,"citation_normalized_percentile":{"value":0.99716549,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"29","issue":null,"first_page":"682","last_page":"686"},"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":0.9955000281333923,"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":0.9725000262260437,"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":0.8123813271522522},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7739031314849854},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.747822642326355},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7298392057418823},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6492174863815308},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.647529661655426},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6052265763282776},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5737938284873962},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5620818734169006},{"id":"https://openalex.org/keywords/generative-adversarial-network","display_name":"Generative adversarial network","score":0.5143402814865112},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4891124367713928},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.46030452847480774},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4518257975578308},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.44329914450645447},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.41320404410362244},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3282555937767029}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8123813271522522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7739031314849854},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.747822642326355},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7298392057418823},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6492174863815308},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.647529661655426},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6052265763282776},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5737938284873962},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5620818734169006},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.5143402814865112},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4891124367713928},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.46030452847480774},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4518257975578308},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.44329914450645447},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.41320404410362244},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3282555937767029},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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:10.1109/lsp.2022.3150258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2022.3150258","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.6800000071525574,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320329131","display_name":"Kids Brain Health Network","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W47831154","https://openalex.org/W1518188273","https://openalex.org/W1800356822","https://openalex.org/W1922658220","https://openalex.org/W1972227112","https://openalex.org/W1972567154","https://openalex.org/W1983963761","https://openalex.org/W2038484192","https://openalex.org/W2064675550","https://openalex.org/W2103235956","https://openalex.org/W2113278353","https://openalex.org/W2120599713","https://openalex.org/W2154252319","https://openalex.org/W2155776568","https://openalex.org/W2157331557","https://openalex.org/W2160860215","https://openalex.org/W2198584637","https://openalex.org/W2250966211","https://openalex.org/W2509065397","https://openalex.org/W2538385631","https://openalex.org/W2563536398","https://openalex.org/W2591013610","https://openalex.org/W2751841560","https://openalex.org/W2807869636","https://openalex.org/W2883588054","https://openalex.org/W2937047963","https://openalex.org/W2963745697","https://openalex.org/W2982325051","https://openalex.org/W2983148138","https://openalex.org/W3096831136","https://openalex.org/W3098357269","https://openalex.org/W3131523676","https://openalex.org/W6628877408","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6638114406","https://openalex.org/W6685352114","https://openalex.org/W6729831399"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2440023763","https://openalex.org/W2962474440"],"abstract_inverted_index":{"Deep":[0,95],"neural":[1,28,81],"networks":[2,29],"in":[3,22,35],"deep":[4,59],"learning":[5,20,60],"have":[6,11,31,148],"been":[7],"widely":[8],"demonstrated":[9],"to":[10,44,71,89,113,117,134,151,160],"higher":[12],"accuracy":[13],"and":[14,38,127,156,163],"distinct":[15],"advantages":[16],"over":[17],"traditional":[18],"machine":[19],"methods":[21],"extracting":[23],"data":[24,105,108],"features.":[25],"While":[26],"convolutional":[27],"(CNNs)":[30],"shown":[32],"great":[33],"success":[34],"feature":[36,129],"extraction":[37],"audio":[39],"classification,":[40],"it":[41],"is":[42,62,87,101,111],"important":[43],"note":[45],"that":[46,63,142,174],"real-time":[47],"audios":[48],"are":[49,132],"dependent":[50],"on":[51,170],"previous":[52],"scenes.":[53],"Also,":[54],"the":[55,114,119,136,143,152,158,165,175,183],"main":[56],"drawback":[57],"of":[58,69],"algorithms":[61],"they":[64],"need":[65],"a":[66,79,94],"huge":[67],"number":[68],"datasets":[70,172],"indicate":[72],"their":[73],"efficient":[74],"performance.":[75],"In":[76],"this":[77,91],"paper,":[78],"recurrent":[80],"network":[82],"(RNN)":[83],"combined":[84],"with":[85],"CNN":[86],"proposed":[88,176],"address":[90],"problem.":[92],"Moreover,":[93],"Convolutional":[96],"Generative":[97],"Adversarial":[98],"Network":[99],"(DCGAN)":[100],"used":[102,133],"for":[103],"high-quality":[104],"augmentation.":[106],"This":[107],"augmentation":[109],"technique":[110],"applied":[112],"UrbanSound8K":[115,171],"dataset":[116],"improve":[118,135,164],"environmental":[120],"sound":[121],"classification.":[122],"Batch":[123],"normalization,":[124],"transfer":[125],"learning,":[126],"three":[128],"representations":[130],"map":[131],"model":[137],"accuracy.":[138,167],"The":[139],"results":[140,169],"show":[141],"generated":[144],"images":[145,155],"by":[146],"DCGAN":[147],"similar":[149],"features":[150],"original":[153],"training":[154],"has":[157],"capability":[159],"generate":[161],"spectrograms":[162],"classification":[166,185],"Experimental":[168],"demonstrate":[173],"CNN-RNN":[177],"architecture":[178],"achieves":[179],"better":[180],"performance":[181],"than":[182],"state-of-the-art":[184],"models.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":30},{"year":2024,"cited_by_count":38},{"year":2023,"cited_by_count":31},{"year":2022,"cited_by_count":10}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}