{"id":"https://openalex.org/W4297841677","doi":"https://doi.org/10.21437/interspeech.2022-515","title":"AudioTagging Done Right: 2nd comparison of deep learning methods for environmental sound classification","display_name":"AudioTagging Done Right: 2nd comparison of deep learning methods for environmental sound classification","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841677","doi":"https://doi.org/10.21437/interspeech.2022-515"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-515","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-515","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100648014","display_name":"Juncheng Li","orcid":"https://orcid.org/0000-0001-7314-6754"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juncheng Li","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112694715","display_name":"Shuhui Qu","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuhui Qu","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063149046","display_name":"Po-Yao Huang","orcid":"https://orcid.org/0000-0002-3319-5145"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Po-Yao Huang","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Florian Metze","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.9228,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.75037821,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1521","last_page":"1525"},"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":0.991599977016449,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9830999970436096,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.6974886059761047},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5789350271224976},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5056850910186768},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4366823434829712},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41553959250450134},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32664912939071655},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1876039206981659}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6974886059761047},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5789350271224976},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5056850910186768},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4366823434829712},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41553959250450134},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32664912939071655},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1876039206981659},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-515","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-515","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2676925568","https://openalex.org/W2766164908","https://openalex.org/W2908510526","https://openalex.org/W2936774411","https://openalex.org/W2963173418","https://openalex.org/W2963587345","https://openalex.org/W2963610932","https://openalex.org/W2973109987","https://openalex.org/W2991391304","https://openalex.org/W3094502228","https://openalex.org/W3094550259","https://openalex.org/W3162819547","https://openalex.org/W3162999565","https://openalex.org/W3170874841","https://openalex.org/W3196974791","https://openalex.org/W3205475937","https://openalex.org/W3205550549","https://openalex.org/W3205743929","https://openalex.org/W4286582832","https://openalex.org/W4286914341","https://openalex.org/W4287126759","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W2961085424","https://openalex.org/W3215138031","https://openalex.org/W4306674287","https://openalex.org/W3009238340","https://openalex.org/W4321369474","https://openalex.org/W4360585206","https://openalex.org/W4285208911","https://openalex.org/W3046775127","https://openalex.org/W3082895349"],"abstract_inverted_index":{"After":[0],"its":[1],"sweeping":[2],"success":[3],"in":[4,47,80],"vision":[5],"and":[6,75,125,136,140,151,177],"language":[7],"tasks,":[8],"pure":[9],"attention-based":[10,152],"neural":[11,31,147],"architectures":[12],"(e.g.DeiT)":[13],"[1]":[14],"are":[15,78],"emerging":[16],"to":[17,73,166],"the":[18,109,122,133,138],"top":[19],"of":[20,53,142,146],"audio":[21],"tagging":[22],"(AT)":[23],"leaderboards":[24],"[2],":[25,64],"which":[26,107],"seemingly":[27,81],"obsoletes":[28],"traditional":[29],"convolutional":[30],"networks":[32,35],"(CNNs),":[33],"feed-forward":[34],"or":[36],"recurrent":[37],"networks.However,":[38],"taking":[39],"a":[40,68,87,128],"closer":[41],"look,":[42],"there":[43],"is":[44,95,108],"great":[45],"variability":[46],"published":[48],"research,":[49],"for":[50,67,86,174],"instance,":[51],"performances":[52],"models":[54],"initialized":[55],"with":[56],"pretrained":[57],"weights":[58],"differ":[59],"drastically":[60],"from":[61,71],"without":[62],"pretraining":[63],"training":[65],"time":[66],"model":[69],"varies":[70],"hours":[72],"weeks,":[74],"often,":[76],"essences":[77],"hidden":[79],"trivial":[82],"details.This":[83],"urgently":[84],"calls":[85],"comprehensive":[88],"study":[89,137],"since":[90],"our":[91],"1st":[92],"comparison":[93],"[3]":[94],"half-decade":[96],"old.In":[97],"this":[98],"work,":[99],"we":[100,116],"perform":[101],"extensive":[102],"experiments":[103],"on":[104,121,132],"AudioSet":[105],"[4]":[106],"largest":[110],"weakly-labeled":[111],"sound":[112],"event":[113],"dataset":[114],"available,":[115],"also":[117,154],"did":[118],"analysis":[119],"based":[120],"data":[123],"quality":[124],"efficiency.We":[126],"compare":[127],"few":[129],"state-of-the-art":[130],"baselines":[131],"AT":[134],"task,":[135],"performance":[139],"efficiency":[141],"2":[143,179],"major":[144],"categories":[145],"architectures:":[148],"CNN":[149],"variants":[150],"variants.We":[153],"closely":[155],"examine":[156],"their":[157],"optimization":[158,172],"procedures.Our":[159],"opensourced":[160],"experimental":[161],"results":[162],"1":[163],"provide":[164],"insights":[165],"trade":[167],"off":[168],"between":[169],"performance,":[170],"efficiency,":[171],"process,":[173],"both":[175],"practitioners":[176],"researchers.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}