{"id":"https://openalex.org/W3165587897","doi":"https://doi.org/10.1109/taslp.2021.3082307","title":"Receptive Field Regularization Techniques for Audio Classification and Tagging With Deep Convolutional Neural Networks","display_name":"Receptive Field Regularization Techniques for Audio Classification and Tagging With Deep Convolutional Neural Networks","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3165587897","doi":"https://doi.org/10.1109/taslp.2021.3082307","mag":"3165587897"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3082307","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3082307","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2105.12395","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026220503","display_name":"Khaled Koutini","orcid":"https://orcid.org/0000-0002-9193-732X"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Khaled Koutini","raw_affiliation_strings":["Institute of Computational Perception (CP-JKU), Johannes Kepler University Linz, Austria"],"affiliations":[{"raw_affiliation_string":"Institute of Computational Perception (CP-JKU), Johannes Kepler University Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032086214","display_name":"Hamid Eghbal-zadeh","orcid":"https://orcid.org/0000-0003-0773-5651"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Hamid Eghbal-zadeh","raw_affiliation_strings":["LIT Artificial Intelligence Lab, Johannes Kepler University Linz, Austria"],"affiliations":[{"raw_affiliation_string":"LIT Artificial Intelligence Lab, Johannes Kepler University Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003768123","display_name":"Gerhard Widmer","orcid":"https://orcid.org/0000-0003-3531-1282"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Gerhard Widmer","raw_affiliation_strings":["LIT Artificial Intelligence Lab, Johannes Kepler University Linz, Austria"],"affiliations":[{"raw_affiliation_string":"LIT Artificial Intelligence Lab, Johannes Kepler University Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5026220503"],"corresponding_institution_ids":["https://openalex.org/I121883995"],"apc_list":null,"apc_paid":null,"fwci":5.386,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.96631099,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"29","issue":null,"first_page":"1987","last_page":"2000"},"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":0.9995999932289124,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.8048937320709229},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7916914820671082},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5593532919883728},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5470408797264099},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5433070063591003},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5167202353477478},{"id":"https://openalex.org/keywords/receptive-field","display_name":"Receptive field","score":0.49237191677093506},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45891818404197693},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4116498827934265},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3594513237476349}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.8048937320709229},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7916914820671082},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5593532919883728},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5470408797264099},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5433070063591003},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5167202353477478},{"id":"https://openalex.org/C19071747","wikidata":"https://www.wikidata.org/wiki/Q1755207","display_name":"Receptive field","level":2,"score":0.49237191677093506},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45891818404197693},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4116498827934265},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3594513237476349},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2021.3082307","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3082307","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2105.12395","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.12395","pdf_url":"https://arxiv.org/pdf/2105.12395","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2105.12395","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.12395","pdf_url":"https://arxiv.org/pdf/2105.12395","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":93,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1616026663","https://openalex.org/W1686810756","https://openalex.org/W1832693441","https://openalex.org/W1836465849","https://openalex.org/W2001571181","https://openalex.org/W2054297915","https://openalex.org/W2064675550","https://openalex.org/W2088722255","https://openalex.org/W2108598243","https://openalex.org/W2117130368","https://openalex.org/W2130325614","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2186845332","https://openalex.org/W2188365844","https://openalex.org/W2194775991","https://openalex.org/W2302255633","https://openalex.org/W2342562905","https://openalex.org/W2437181147","https://openalex.org/W2526050071","https://openalex.org/W2548275288","https://openalex.org/W2549139847","https://openalex.org/W2556967412","https://openalex.org/W2565516711","https://openalex.org/W2580221632","https://openalex.org/W2593116425","https://openalex.org/W2618530766","https://openalex.org/W2765407302","https://openalex.org/W2775505379","https://openalex.org/W2883935097","https://openalex.org/W2888806961","https://openalex.org/W2902029681","https://openalex.org/W2903137797","https://openalex.org/W2903539539","https://openalex.org/W2949427019","https://openalex.org/W2949545402","https://openalex.org/W2949846184","https://openalex.org/W2950060770","https://openalex.org/W2950776302","https://openalex.org/W2955425717","https://openalex.org/W2957789971","https://openalex.org/W2962835968","https://openalex.org/W2963163009","https://openalex.org/W2963358591","https://openalex.org/W2963399829","https://openalex.org/W2963403868","https://openalex.org/W2963446712","https://openalex.org/W2963840672","https://openalex.org/W2964121744","https://openalex.org/W2982343573","https://openalex.org/W2982346427","https://openalex.org/W2982415754","https://openalex.org/W2982469053","https://openalex.org/W2982862350","https://openalex.org/W2986661129","https://openalex.org/W2986663693","https://openalex.org/W2987999870","https://openalex.org/W2991611669","https://openalex.org/W2996603747","https://openalex.org/W3000940430","https://openalex.org/W3003269897","https://openalex.org/W3011335337","https://openalex.org/W3015321085","https://openalex.org/W3090085715","https://openalex.org/W3091687589","https://openalex.org/W3206370014","https://openalex.org/W4206410067","https://openalex.org/W4288284459","https://openalex.org/W4295723153","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6638667902","https://openalex.org/W6687045409","https://openalex.org/W6696085341","https://openalex.org/W6729482032","https://openalex.org/W6729983426","https://openalex.org/W6732646663","https://openalex.org/W6739901393","https://openalex.org/W6747331233","https://openalex.org/W6752516136","https://openalex.org/W6756597712","https://openalex.org/W6756690837","https://openalex.org/W6756873980","https://openalex.org/W6763945542","https://openalex.org/W6765212446","https://openalex.org/W6765921464","https://openalex.org/W6769198072","https://openalex.org/W6770069182","https://openalex.org/W6771252938","https://openalex.org/W6775218080","https://openalex.org/W6802972430"],"related_works":["https://openalex.org/W2089544495","https://openalex.org/W2079003682","https://openalex.org/W1555021777","https://openalex.org/W2913266608","https://openalex.org/W2799648451","https://openalex.org/W1964918325","https://openalex.org/W2189496153","https://openalex.org/W2186491718","https://openalex.org/W2034008118","https://openalex.org/W2055164815"],"abstract_inverted_index":{"In":[0,47],"this":[1],"paper,":[2],"we":[3],"study":[4,108],"the":[5,24,39,44,57,128,135,152,163],"performance":[6,99],"of":[7,9,28,86,88,130,154,165],"variants":[8],"well-known":[10,109],"Convolutional":[11],"Neural":[12],"Network":[13],"(CNN)":[14],"architectures":[15,71,111,137,169],"on":[16,138,173],"different":[17,139],"audio":[18,102,140],"tasks.":[19,106],"We":[20,107,121],"show":[21,149],"that":[22,150],"tuning":[23],"Receptive":[25],"Field":[26],"(RF)":[27],"CNNs":[29,49,131,155,178],"is":[30],"crucial":[31],"to":[32,42,55,62,64,81,126,189,196],"their":[33,90,114,118],"generalization.":[34],"An":[35],"insufficient":[36],"RF":[37,53,91,129,153],"limits":[38],"CNN's":[40],"ability":[41],"fit":[43],"training":[45,58],"data.":[46,67],"contrast,":[48],"with":[50],"an":[51],"excessive":[52],"tend":[54,80],"over-fit":[56],"data":[59],"and":[60,76,94,104,112,132,142,145,170,191],"fail":[61],"generalize":[63],"unseen":[65],"testing":[66],"As":[68],"state-of-the-art":[69,180],"CNN":[70,110],"-":[72,79],"in":[73,84,98,100,182,194,204],"computer":[74],"vision":[75],"other":[77],"domains":[78],"go":[82],"deeper":[83],"terms":[85],"number":[87],"layers,":[89],"size":[92],"increases":[93],"therefore":[95],"they":[96],"degrade":[97],"several":[101,123,205],"classification":[103,141,188],"tagging":[105,143],"how":[113],"building":[115],"blocks":[116],"affect":[117],"receptive":[119],"field.":[120],"propose":[122],"systematic":[124],"approaches":[125,159],"control":[127],"systematically":[133],"test":[134],"resulting":[136],"tasks":[144],"datasets.":[146,175],"The":[147,176],"experiments":[148],"regularizing":[151],"using":[156],"our":[157],"proposed":[158,177],"can":[160],"drastically":[161],"improve":[162],"generalization":[164],"models,":[166],"out-performing":[167],"complex":[168],"pre-trained":[171],"models":[172],"larger":[174],"achieve":[179],"results":[181],"multiple":[183],"tasks,":[184],"from":[185],"acoustic":[186],"scene":[187],"emotion":[190],"theme":[192],"detection":[193],"music":[195],"instrument":[197],"recognition,":[198],"as":[199],"demonstrated":[200],"by":[201],"top":[202],"ranks":[203],"pertinent":[206],"challenges":[207],"(DCASE,":[208],"MediaEval).":[209]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2021-06-07T00:00:00"}