{"id":"https://openalex.org/W2768083292","doi":"https://doi.org/10.1109/icdsp.2017.8096153","title":"Dilated convolution neural network with LeakyReLU for environmental sound classification","display_name":"Dilated convolution neural network with LeakyReLU for environmental sound classification","publication_year":2017,"publication_date":"2017-08-01","ids":{"openalex":"https://openalex.org/W2768083292","doi":"https://doi.org/10.1109/icdsp.2017.8096153","mag":"2768083292"},"language":"en","primary_location":{"id":"doi:10.1109/icdsp.2017.8096153","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdsp.2017.8096153","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 22nd International Conference on Digital Signal Processing (DSP)","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/A5100635891","display_name":"Xiaohu Zhang","orcid":"https://orcid.org/0000-0001-5654-1445"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaohu Zhang","raw_affiliation_strings":["ADSPLab/ELIP/Shenzhen Key Laboratory for IMVR, Peking University Shenzhen Graduate School, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"ADSPLab/ELIP/Shenzhen Key Laboratory for IMVR, Peking University Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002795838","display_name":"Yuexian Zou","orcid":"https://orcid.org/0000-0001-9999-6140"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuexian Zou","raw_affiliation_strings":["ADSPLab/ELIP/Shenzhen Key Laboratory for IMVR, Peking University Shenzhen Graduate School, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"ADSPLab/ELIP/Shenzhen Key Laboratory for IMVR, Peking University Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032675026","display_name":"Wei Shi","orcid":"https://orcid.org/0000-0002-3129-0296"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Shi","raw_affiliation_strings":["Hian Speech Science & Technology Co., Ltd., Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Hian Speech Science & Technology Co., Ltd., Shenzhen, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100635891"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":14.371,"has_fulltext":false,"cited_by_count":284,"citation_normalized_percentile":{"value":0.99362883,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.996399998664856,"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/computer-science","display_name":"Computer science","score":0.7685815691947937},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7523605823516846},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6927313208580017},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5823560357093811},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.541904628276825},{"id":"https://openalex.org/keywords/activation-function","display_name":"Activation function","score":0.5227839350700378},{"id":"https://openalex.org/keywords/transformative-learning","display_name":"Transformative learning","score":0.49410727620124817},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4839227795600891},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4495184123516083},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.42615950107574463},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4099244475364685},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3657769560813904}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7685815691947937},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7523605823516846},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6927313208580017},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5823560357093811},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.541904628276825},{"id":"https://openalex.org/C38365724","wikidata":"https://www.wikidata.org/wiki/Q4677469","display_name":"Activation function","level":3,"score":0.5227839350700378},{"id":"https://openalex.org/C70587473","wikidata":"https://www.wikidata.org/wiki/Q7834111","display_name":"Transformative learning","level":2,"score":0.49410727620124817},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4839227795600891},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4495184123516083},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.42615950107574463},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4099244475364685},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3657769560813904},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","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},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdsp.2017.8096153","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdsp.2017.8096153","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 22nd International Conference on Digital Signal Processing (DSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.6800000071525574}],"awards":[],"funders":[{"id":"https://openalex.org/F4320329791","display_name":"Shenzhen Fundamental Research Program","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1257806174","https://openalex.org/W1502364872","https://openalex.org/W1517367463","https://openalex.org/W1533861849","https://openalex.org/W1921523184","https://openalex.org/W1972567154","https://openalex.org/W2009618608","https://openalex.org/W2037533030","https://openalex.org/W2095705004","https://openalex.org/W2112739286","https://openalex.org/W2140745013","https://openalex.org/W2156387975","https://openalex.org/W2286929393","https://openalex.org/W2359377300","https://openalex.org/W2398456099","https://openalex.org/W2400604769","https://openalex.org/W2400753342","https://openalex.org/W2493586332","https://openalex.org/W2509065397","https://openalex.org/W2519091744","https://openalex.org/W2529337537","https://openalex.org/W2963840672","https://openalex.org/W3098357269","https://openalex.org/W4300499061"],"related_works":["https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3193565141","https://openalex.org/W3133861977","https://openalex.org/W3167935049","https://openalex.org/W2964954556","https://openalex.org/W3029198973","https://openalex.org/W2806426850","https://openalex.org/W4297795098","https://openalex.org/W3019910406"],"abstract_inverted_index":{"Environmental":[0],"sound":[1,105,214],"classification":[2],"task":[3],"(ESC)":[4],"is":[5,74,112,130,218,247],"still":[6],"open":[7],"and":[8,68,156,196],"challenging.":[9],"In":[10,45],"contrast":[11],"to":[12,47,65,108,180,220],"speech,":[13],"sounds":[14],"of":[15,27,35,104,115,119,125,177,203,244,253],"a":[16,24,147],"specific":[17],"acoustic":[18,36],"event":[19,215],"may":[20],"be":[21],"produced":[22],"by":[23,139,233],"wide":[25],"variety":[26],"sources.":[28],"Thus":[29],"for":[30,99,134],"one":[31],"class,":[32],"feature":[33,51,56],"spectrums":[34],"events":[37],"are":[38,160,168],"much":[39],"more":[40,182],"transformative":[41,55],"than":[42,251],"human":[43],"speech.":[44],"order":[46],"learn":[48],"better":[49],"high-level":[50],"representations":[52],"from":[53],"these":[54,140],"spectrums,":[57],"convolution":[58,84,178],"neural":[59],"network":[60,194],"(CNN)":[61],"has":[62],"been":[63],"applied":[64],"ESC":[66,79,127,150,230],"tasks":[67],"achieved":[69],"state-of-the-art":[70,229],"results.":[71],"However,":[72],"it":[73],"noted":[75],"that":[76,169,222,252],"existing":[77],"CNN-based":[78,126,149],"systems":[80],"only":[81],"use":[82],"small":[83],"filters":[85,155,172],"(typically":[86],"2\u00d72":[87],"or":[88],"3\u00d73)":[89],"in":[90,95,142],"CNN":[91,97],"model":[92,98],"which":[93,129],"results":[94,231],"deep":[96,235],"learning":[100],"long":[101],"contextual":[102,183],"information":[103],"events.":[106],"Besides,":[107],"our":[109,166,204,223,245],"knowledge,":[110],"there":[111],"no":[113],"work":[114],"evaluating":[116],"the":[117,123,136,170,186,190,193,197,201,228,241],"effect":[118],"activation":[120,158],"functions":[121],"on":[122,212,238],"performance":[124],"systems,":[128],"actually":[131],"very":[132,234],"critical":[133],"improving":[135],"performance.":[137,198],"Motivated":[138],"findings,":[141],"this":[143],"study,":[144],"we":[145,208],"propose":[146],"dilated":[148,154,171],"(D-CNN-ESC)":[151],"system":[152,226,237],"where":[153],"LeakyReLU":[157,187],"function":[159,188],"adopted.":[161],"The":[162],"main":[163],"ideas":[164],"behind":[165],"research":[167],"will":[173],"increase":[174],"receptive":[175],"field":[176],"layers":[179],"incorporate":[181],"information.":[184],"Moreover,":[185],"brings":[189],"tradeoff":[191],"between":[192],"sparsity":[195],"To":[199],"evaluate":[200],"effectiveness":[202],"proposed":[205,224],"D-CNN-ESC":[206,225],"system,":[207],"conduct":[209],"several":[210],"experiments":[211],"three":[213],"datasets.":[216],"It":[217],"encouraged":[219],"see":[221],"outperforms":[227],"obtained":[232],"CNN-ESC":[236],"UrbanSound8K":[239],"dataset,":[240],"absolute":[242],"error":[243],"method":[246],"about":[248],"10%":[249],"less":[250],"compared":[254],"method.":[255]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":45},{"year":2022,"cited_by_count":54},{"year":2021,"cited_by_count":61},{"year":2020,"cited_by_count":42},{"year":2019,"cited_by_count":27},{"year":2018,"cited_by_count":8}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}