{"id":"https://openalex.org/W3016659311","doi":"https://doi.org/10.1109/icpr48806.2021.9413035","title":"ESResNet: Environmental Sound Classification Based on Visual Domain Models","display_name":"ESResNet: Environmental Sound Classification Based on Visual Domain Models","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3016659311","doi":"https://doi.org/10.1109/icpr48806.2021.9413035","mag":"3016659311"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9413035","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9413035","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.07301","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051399221","display_name":"Andrey Guzhov","orcid":null},"institutions":[{"id":"https://openalex.org/I153267046","display_name":"University of Kaiserslautern","ror":"https://ror.org/04zrf7b53","country_code":"DE","type":"education","lineage":["https://openalex.org/I153267046"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Andrey Guzhov","raw_affiliation_strings":["TU Kaiserslautern, Kaiserslautern, Germany","TU Kaiserslautern, Kaiserslautern Germany"],"affiliations":[{"raw_affiliation_string":"TU Kaiserslautern, Kaiserslautern, Germany","institution_ids":["https://openalex.org/I153267046"]},{"raw_affiliation_string":"TU Kaiserslautern, Kaiserslautern Germany","institution_ids":["https://openalex.org/I153267046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029509133","display_name":"Federico Raue","orcid":"https://orcid.org/0000-0002-8604-6207"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Federico Raue","raw_affiliation_strings":["DFKI GmbH, Kaiserslautern, Germany","German Research Centre for Artificial Intelligence"],"affiliations":[{"raw_affiliation_string":"DFKI GmbH, Kaiserslautern, Germany","institution_ids":["https://openalex.org/I33256026"]},{"raw_affiliation_string":"German Research Centre for Artificial Intelligence","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019899855","display_name":"J.J. van Hees","orcid":"https://orcid.org/0000-0002-0084-8998"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jorn Hees","raw_affiliation_strings":["DFKI GmbH, Kaiserslautern, Germany","DFKI GmbH,Kaiserslautern,Germany"],"affiliations":[{"raw_affiliation_string":"DFKI GmbH, Kaiserslautern, Germany","institution_ids":["https://openalex.org/I33256026"]},{"raw_affiliation_string":"DFKI GmbH,Kaiserslautern,Germany","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101904182","display_name":"Andreas Dengel","orcid":"https://orcid.org/0000-0002-6100-8255"},"institutions":[{"id":"https://openalex.org/I153267046","display_name":"University of Kaiserslautern","ror":"https://ror.org/04zrf7b53","country_code":"DE","type":"education","lineage":["https://openalex.org/I153267046"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Dengel","raw_affiliation_strings":["TU Kaiserslautern, Kaiserslautern, Germany","TU Kaiserslautern, Kaiserslautern Germany"],"affiliations":[{"raw_affiliation_string":"TU Kaiserslautern, Kaiserslautern, Germany","institution_ids":["https://openalex.org/I153267046"]},{"raw_affiliation_string":"TU Kaiserslautern, Kaiserslautern Germany","institution_ids":["https://openalex.org/I153267046"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5051399221"],"corresponding_institution_ids":["https://openalex.org/I153267046"],"apc_list":null,"apc_paid":null,"fwci":3.0779,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.91973693,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4933","last_page":"4940"},"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":0.9961000084877014,"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":0.9815000295639038,"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":0.7582122683525085},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6999797224998474},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6421548128128052},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5819874405860901},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5559294819831848},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5028840899467468},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.45708703994750977},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4263789653778076},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3611152172088623},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.348796546459198},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3229312002658844},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08855867385864258},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.07188597321510315}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7582122683525085},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6999797224998474},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6421548128128052},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5819874405860901},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5559294819831848},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5028840899467468},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.45708703994750977},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4263789653778076},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3611152172088623},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.348796546459198},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3229312002658844},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08855867385864258},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.07188597321510315},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icpr48806.2021.9413035","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9413035","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2004.07301","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.07301","pdf_url":"https://arxiv.org/pdf/2004.07301","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"},{"id":"mag:3016659311","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2004.07301","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2004.07301","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2004.07301","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.07301","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.07301","pdf_url":"https://arxiv.org/pdf/2004.07301","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":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3016659311.pdf","grobid_xml":"https://content.openalex.org/works/W3016659311.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W15066456","https://openalex.org/W396690109","https://openalex.org/W1522301498","https://openalex.org/W1558247033","https://openalex.org/W1972567154","https://openalex.org/W1975929202","https://openalex.org/W2020997493","https://openalex.org/W2033875152","https://openalex.org/W2038484192","https://openalex.org/W2040488623","https://openalex.org/W2052666245","https://openalex.org/W2059020775","https://openalex.org/W2061171222","https://openalex.org/W2101234009","https://openalex.org/W2103869314","https://openalex.org/W2108598243","https://openalex.org/W2111460811","https://openalex.org/W2123133018","https://openalex.org/W2125324924","https://openalex.org/W2131030868","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2411037331","https://openalex.org/W2509065397","https://openalex.org/W2531409750","https://openalex.org/W2593451766","https://openalex.org/W2622263826","https://openalex.org/W2745357708","https://openalex.org/W2751841560","https://openalex.org/W2766087987","https://openalex.org/W2766397045","https://openalex.org/W2888469011","https://openalex.org/W2914312680","https://openalex.org/W2937047963","https://openalex.org/W2962785008","https://openalex.org/W2963403868","https://openalex.org/W2963838685","https://openalex.org/W2964328535","https://openalex.org/W2972247414","https://openalex.org/W2996339284","https://openalex.org/W3091905774","https://openalex.org/W3098357269","https://openalex.org/W3209073848","https://openalex.org/W4232336823","https://openalex.org/W6600593648","https://openalex.org/W6613520308","https://openalex.org/W6631190155","https://openalex.org/W6675354045","https://openalex.org/W6678788828","https://openalex.org/W6684191040","https://openalex.org/W6739622702","https://openalex.org/W6739901393","https://openalex.org/W6772396411","https://openalex.org/W6783596713"],"related_works":["https://openalex.org/W2052666245","https://openalex.org/W2038484192","https://openalex.org/W3098357269","https://openalex.org/W3045062880","https://openalex.org/W2964328535","https://openalex.org/W2194775991","https://openalex.org/W1972567154","https://openalex.org/W2593116425","https://openalex.org/W3135791241","https://openalex.org/W3176445421","https://openalex.org/W3080144805","https://openalex.org/W3193738580","https://openalex.org/W3207460686","https://openalex.org/W3162348871","https://openalex.org/W3196355955","https://openalex.org/W3095391551","https://openalex.org/W2954384604","https://openalex.org/W2889435835","https://openalex.org/W3118952246","https://openalex.org/W2915357883"],"abstract_inverted_index":{"Environmental":[0],"Sound":[1],"Classification":[2],"(ESC)":[3],"is":[4,92,100,111,225],"an":[5],"active":[6],"research":[7],"area":[8],"in":[9,20,47,164],"the":[10,21,27,51,57,76,81,85,129,140,195,199,208],"audio":[11],"domain":[12,131],"and":[13,38,105,121,136,147,178],"has":[14],"seen":[15],"a":[16,64,97,165,191],"lot":[17],"of":[18,26,56,66,75,84,89,142,171,194,198],"progress":[19],"past":[22,58],"years.":[23],"However,":[24],"many":[25],"existing":[28],"approaches":[29,127,163],"achieve":[30],"high":[31],"accuracy":[32],"by":[33,168,201],"relying":[34],"on":[35,72,113,151,207],"domain-specific":[36],"features":[37],"architectures,":[39],"making":[40],"it":[41],"harder":[42],"to":[43,63],"benefit":[44],"from":[45,128],"advances":[46],"other":[48],"fields":[49],"(e.g.,":[50],"image":[52,130],"domain).":[53],"Additionally,":[54],"some":[55],"successes":[59],"have":[60],"been":[61],"attributed":[62],"discrepancy":[65],"how":[67],"results":[68,206],"are":[69],"evaluated":[70],"(i.e.,":[71,132],"unofficial":[73,214],"splits":[74],"UrbanSound8K":[77],"(US8K)":[78],"dataset),":[79],"distorting":[80],"overall":[82],"progression":[83],"field.":[86],"The":[87],"contribution":[88],"this":[90],"paper":[91],"twofold.":[93],"First,":[94],"we":[95,189],"present":[96],"model":[98,110,150,158],"that":[99,156],"inherently":[101],"compatible":[102],"with":[103,124],"mono":[104,185],"stereo":[106],"sound":[107],"inputs.":[108],"Our":[109],"based":[112],"simple":[114],"log-power":[115],"Short-Time":[116],"Fourier":[117],"Transform":[118],"(STFT)":[119],"spectrograms":[120],"combines":[122],"them":[123],"several":[125,203],"well-known":[126],"ResNet,":[133],"Siamese-like":[134],"networks":[135],"attention).":[137],"We":[138,154],"investigate":[139],"influence":[141],"cross-domain":[143],"pre-training,":[144],"architectural":[145],"changes,":[146],"evaluate":[148],"our":[149,157,219],"standard":[152],"datasets.":[153],"find":[155],"out-performs":[159],"all":[160],"previously":[161,204],"known":[162],"fair":[166],"comparison":[167],"achieving":[169],"accuracies":[170],"97.0":[172],"%":[173,176,180,183],"(ESC-10),":[174],"91.5":[175],"(ESC-50)":[177],"84.2":[179],"/":[181,186],"85.4":[182],"(US8K":[184],"stereo).":[187],"Second,":[188],"provide":[190],"comprehensive":[192],"overview":[193],"actual":[196],"state":[197],"field,":[200],"differentiating":[202],"reported":[205],"US8K":[209],"dataset":[210],"between":[211],"official":[212],"or":[213],"splits.":[215],"For":[216],"better":[217],"reproducibility,":[218],"code":[220],"(including":[221],"any":[222],"re-":[223],"implementations)":[224],"made":[226],"available.":[227]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":5}],"updated_date":"2026-03-21T08:13:44.787528","created_date":"2022-07-26T00:00:00"}