{"id":"https://openalex.org/W2934177128","doi":"https://doi.org/10.1109/icassp.2019.8683292","title":"Generalisation in Environmental Sound Classification: The \u2018Making Sense of Sounds\u2019 Data Set and Challenge","display_name":"Generalisation in Environmental Sound Classification: The \u2018Making Sense of Sounds\u2019 Data Set and Challenge","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2934177128","doi":"https://doi.org/10.1109/icassp.2019.8683292","mag":"2934177128"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683292","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683292","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://e-space.mmu.ac.uk/622909/1/08683292.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089482942","display_name":"Christian Kroos","orcid":"https://orcid.org/0000-0002-6984-9139"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Christian Kroos","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014159968","display_name":"Oliver Bones","orcid":"https://orcid.org/0000-0002-1608-3459"},"institutions":[{"id":"https://openalex.org/I54459138","display_name":"University of Salford","ror":"https://ror.org/01tmqtf75","country_code":"GB","type":"education","lineage":["https://openalex.org/I54459138"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Oliver Bones","raw_affiliation_strings":["Acoustics Research Centre, University of Salford, Manchester, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Acoustics Research Centre, University of Salford, Manchester, UK","institution_ids":["https://openalex.org/I54459138"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101590005","display_name":"Yin Cao","orcid":"https://orcid.org/0000-0001-9086-7027"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yin Cao","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061137378","display_name":"Lara Harris","orcid":"https://orcid.org/0000-0001-9939-0392"},"institutions":[{"id":"https://openalex.org/I54459138","display_name":"University of Salford","ror":"https://ror.org/01tmqtf75","country_code":"GB","type":"education","lineage":["https://openalex.org/I54459138"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lara Harris","raw_affiliation_strings":["Acoustics Research Centre, University of Salford, Manchester, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Acoustics Research Centre, University of Salford, Manchester, UK","institution_ids":["https://openalex.org/I54459138"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022165330","display_name":"Philip J. B. Jackson","orcid":"https://orcid.org/0000-0001-7933-5935"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philip J. B. Jackson","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082258889","display_name":"William J. Davies","orcid":"https://orcid.org/0000-0002-5835-7489"},"institutions":[{"id":"https://openalex.org/I54459138","display_name":"University of Salford","ror":"https://ror.org/01tmqtf75","country_code":"GB","type":"education","lineage":["https://openalex.org/I54459138"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"William J. Davies","raw_affiliation_strings":["Acoustics Research Centre, University of Salford, Manchester, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Acoustics Research Centre, University of Salford, Manchester, UK","institution_ids":["https://openalex.org/I54459138"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024074402","display_name":"Trevor J. Cox","orcid":"https://orcid.org/0000-0002-4075-7564"},"institutions":[{"id":"https://openalex.org/I54459138","display_name":"University of Salford","ror":"https://ror.org/01tmqtf75","country_code":"GB","type":"education","lineage":["https://openalex.org/I54459138"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Trevor J. Cox","raw_affiliation_strings":["Acoustics Research Centre, University of Salford, Manchester, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Acoustics Research Centre, University of Salford, Manchester, UK","institution_ids":["https://openalex.org/I54459138"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066967599","display_name":"Mark D. Plumbley","orcid":"https://orcid.org/0000-0002-9708-1075"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark D. Plumbley","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Guildford, Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5089482942"],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":0.8351,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.71953225,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8082","last_page":"8086"},"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":0.9944000244140625,"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":0.9850999712944031,"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":0.6653410792350769},{"id":"https://openalex.org/keywords/soundscape","display_name":"Soundscape","score":0.6215077042579651},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6213546991348267},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6005960702896118},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.49480265378952026},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4063095152378082},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37023720145225525},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35136061906814575},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1214745044708252}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6653410792350769},{"id":"https://openalex.org/C142795923","wikidata":"https://www.wikidata.org/wiki/Q1358257","display_name":"Soundscape","level":3,"score":0.6215077042579651},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6213546991348267},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6005960702896118},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.49480265378952026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4063095152378082},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37023720145225525},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35136061906814575},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1214745044708252},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp.2019.8683292","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683292","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:e-space.mmu.ac.uk:622909","is_oa":true,"landing_page_url":"https://e-space.mmu.ac.uk/view/authors/e1eb89ad0687743f43dca65b3e5c044b.html>","pdf_url":"https://e-space.mmu.ac.uk/622909/1/08683292.pdf","source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:usir.salford.ac.uk:51499","is_oa":true,"landing_page_url":null,"pdf_url":"http://usir.salford.ac.uk/id/eprint/51499/1/Generalisation%20in%20environmental%20sound%20classification.pdf","source":{"id":"https://openalex.org/S4306401501","display_name":"University of Salford Institutional Repository (University of Salford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I54459138","host_organization_name":"University of Salford","host_organization_lineage":["https://openalex.org/I54459138"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},{"id":"pmh:oai:epubs.surrey.ac.uk:850658","is_oa":false,"landing_page_url":"http://epubs.surrey.ac.uk/850658/1/Generalisation%20in%20environmental%20sound%20classification.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400680","display_name":"Surrey Research Insight Open Access (The University of Surrey)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28290843","host_organization_name":"University of Surrey","host_organization_lineage":["https://openalex.org/I28290843"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},{"id":"pmh:oai:pure.atira.dk:publications/bb2d0619-9309-486b-80cc-d26f1bca1884","is_oa":false,"landing_page_url":"https://pureportal.coventry.ac.uk/en/publications/bb2d0619-9309-486b-80cc-d26f1bca1884","pdf_url":null,"source":{"id":"https://openalex.org/S4306402411","display_name":"Pure (Coventry University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I73417466","host_organization_name":"Coventry University","host_organization_lineage":["https://openalex.org/I73417466"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Kroos, C, Bones, O, Cao, Y, Harris, L, Jackson, P J B, Davies, W J, Wang, W, Cox, T J & Plumbley, M D 2019, Generalisation in Environmental Sound Classification : The \u2018Making Sense of Sounds\u2019 Data Set and Challenge. in ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp. 8082-8086, 44th International Conference on Acoustics, Speech, and Signal Processing, Brighton, United Kingdom, 12/05/19. https://doi.org/10.1109/icassp.2019.8683292","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:e-space.mmu.ac.uk:622909","is_oa":true,"landing_page_url":"https://e-space.mmu.ac.uk/view/authors/e1eb89ad0687743f43dca65b3e5c044b.html>","pdf_url":"https://e-space.mmu.ac.uk/622909/1/08683292.pdf","source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.8199999928474426,"display_name":"Sustainable cities and communities"}],"awards":[{"id":"https://openalex.org/G3009645685","display_name":null,"funder_award_id":"688382","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G4937468798","display_name":null,"funder_award_id":"H2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5045220161","display_name":null,"funder_award_id":"H2020","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5939146501","display_name":"Making Sense of Sounds","funder_award_id":"EP/N014111/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8995825145","display_name":null,"funder_award_id":"EP/N014111/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G972256834","display_name":null,"funder_award_id":"688382","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2934177128.pdf","grobid_xml":"https://content.openalex.org/works/W2934177128.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1552898570","https://openalex.org/W1581788322","https://openalex.org/W1836465849","https://openalex.org/W1967348532","https://openalex.org/W2008415856","https://openalex.org/W2028335839","https://openalex.org/W2032337854","https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2052696562","https://openalex.org/W2081580037","https://openalex.org/W2093716889","https://openalex.org/W2114082868","https://openalex.org/W2153947402","https://openalex.org/W2319576313","https://openalex.org/W2518102674","https://openalex.org/W2522224406","https://openalex.org/W2551033818","https://openalex.org/W2566935005","https://openalex.org/W2593116425","https://openalex.org/W2775505379","https://openalex.org/W2805311821","https://openalex.org/W2886066471","https://openalex.org/W2903099953","https://openalex.org/W2995348821","https://openalex.org/W6633152265","https://openalex.org/W6634732120","https://openalex.org/W6638667902","https://openalex.org/W6673976075","https://openalex.org/W6747331233"],"related_works":["https://openalex.org/W2896201871","https://openalex.org/W2282503792","https://openalex.org/W2365709658","https://openalex.org/W1562588264","https://openalex.org/W1593731728","https://openalex.org/W2970126706","https://openalex.org/W2770198033","https://openalex.org/W4386864222","https://openalex.org/W2747085439","https://openalex.org/W2535705314"],"abstract_inverted_index":{"Humans":[0],"are":[1,25,80],"able":[2],"to":[3,15,33,56,82],"identify":[4],"a":[5,49,60,87,91,130],"large":[6],"number":[7],"of":[8,28,48,59,69,107,116,136],"environmental":[9],"sounds":[10,21,35],"and":[11,66],"categorise":[12],"them":[13],"according":[14,55],"high-level":[16,138],"semantic":[17],"categories,":[18],"e.g.":[19],"urban":[20],"or":[22,129],"music.":[23],"They":[24],"also":[26],"capable":[27],"generalising":[29],"from":[30,63],"past":[31],"experience":[32],"new":[34],"when":[36],"applying":[37],"these":[38],"categories.":[39,139],"In":[40],"this":[41],"paper":[42],"we":[43],"report":[44],"on":[45,103],"the":[46,57,67,104,114,126,137],"creation":[47],"data":[50,106],"set":[51],"that":[52],"is":[53,111],"structured":[54],"top-level":[58],"taxonomy":[61],"derived":[62],"human":[64],"judgements":[65],"design":[68],"an":[70,100],"associated":[71],"machine":[72],"learning":[73],"challenge,":[74],"in":[75,113,125],"which":[76,95],"strong":[77,97],"generalisation":[78],"abilities":[79],"required":[81],"be":[83],"successful.":[84],"We":[85],"introduce":[86],"baseline":[88],"classification":[89],"system,":[90],"deep":[92],"convolutional":[93],"network,":[94],"showed":[96],"performance":[98],"with":[99],"average":[101],"accuracy":[102],"evaluation":[105],"80.8%.":[108],"The":[109],"result":[110],"discussed":[112],"light":[115],"two":[117],"alternative":[118],"explanations:":[119],"An":[120],"unlikely":[121],"accidental":[122],"category":[123],"bias":[124],"sound":[127],"recordings":[128],"more":[131],"plausible":[132],"true":[133],"acoustic":[134],"grounding":[135]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-06-05T09:01:59.212387","created_date":"2025-10-10T00:00:00"}