{"id":"https://openalex.org/W3016228121","doi":"https://doi.org/10.1109/icassp40776.2020.9054444","title":"Learning With Out-of-Distribution Data for Audio Classification","display_name":"Learning With Out-of-Distribution Data for Audio Classification","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016228121","doi":"https://doi.org/10.1109/icassp40776.2020.9054444","mag":"3016228121"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5056441203","display_name":"Turab Iqbal","orcid":"https://orcid.org/0000-0003-3393-2544"},"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":"Turab Iqbal","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101590005","display_name":"Yin Cao","orcid":null},"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, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072482416","display_name":"Qiuqiang Kong","orcid":"https://orcid.org/0000-0003-2864-0475"},"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":"Qiuqiang Kong","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","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, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","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, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5056441203"],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":1.8184,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.85477288,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"636","last_page":"640"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9923999905586243,"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"}},{"id":"https://openalex.org/T13996","display_name":"Diverse Musicological Studies","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7095717191696167},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.4599446654319763},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41115936636924744},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33288198709487915},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1079455316066742}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7095717191696167},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.4599446654319763},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41115936636924744},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33288198709487915},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1079455316066742},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.49000000953674316}],"awards":[{"id":"https://openalex.org/G3034362336","display_name":null,"funder_award_id":"EP/P022529/1","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"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W1821462560","https://openalex.org/W1866072925","https://openalex.org/W2108598243","https://openalex.org/W2121056381","https://openalex.org/W2167460663","https://openalex.org/W2531327146","https://openalex.org/W2592335154","https://openalex.org/W2593116425","https://openalex.org/W2765407302","https://openalex.org/W2767414122","https://openalex.org/W2770119437","https://openalex.org/W2786712888","https://openalex.org/W2788907134","https://openalex.org/W2803187616","https://openalex.org/W2886811283","https://openalex.org/W2891021639","https://openalex.org/W2900801283","https://openalex.org/W2936774411","https://openalex.org/W2962762541","https://openalex.org/W2963215553","https://openalex.org/W2963399829","https://openalex.org/W2963446712","https://openalex.org/W2963693742","https://openalex.org/W2963759070","https://openalex.org/W2963859210","https://openalex.org/W2964121744","https://openalex.org/W2982305763","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6638523607","https://openalex.org/W6639331287","https://openalex.org/W6678280073","https://openalex.org/W6728622933","https://openalex.org/W6745136726","https://openalex.org/W6745891213","https://openalex.org/W6746278845","https://openalex.org/W6748163547","https://openalex.org/W6748865747","https://openalex.org/W6751420435","https://openalex.org/W6756539195"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0,16],"supervised":[1],"machine":[2],"learning,":[3],"the":[4,31,47,112,129],"assumption":[5],"that":[6,40,57,85],"training":[7],"data":[8,39,84,98],"is":[9,12,33,51,86,102,125],"labelled":[10,52],"correctly":[11],"not":[13,42],"always":[14],"satisfied.":[15],"this":[17,101],"paper,":[18],"we":[19],"investigate":[20],"an":[21,79],"instance":[22],"of":[23,46,97,131],"labelling":[24],"error":[25],"for":[26,91,100],"classification":[27],"tasks":[28],"in":[29],"which":[30],"dataset":[32],"corrupted":[34],"with":[35,140],"out-of-distribution":[36],"(OOD)":[37],"instances:":[38],"does":[41],"belong":[43],"to":[44,88,104,127],"any":[45],"target":[48],"classes,":[49],"but":[50],"as":[53],"such.":[54],"We":[55],"show":[56],"detecting":[58],"and":[59,93],"relabelling":[60],"certain":[61],"OOD":[62,117],"instances,":[63],"rather":[64],"than":[65],"discarding":[66],"them,":[67],"can":[68],"have":[69],"a":[70,136],"positive":[71],"effect":[72],"on":[73,83,111],"learning.":[74],"The":[75,95,122],"proposed":[76,123],"method":[77,124],"uses":[78],"auxiliary":[80],"classifier,":[81],"trained":[82],"known":[87],"be":[89,105],"in-distribution,":[90],"detection":[92],"relabelling.":[94],"amount":[96],"required":[99],"shown":[103,126],"small.":[106],"Experiments":[107],"are":[108,119,144],"carried":[109],"out":[110],"FSDnoisy18k":[113],"audio":[114],"dataset,":[115],"where":[116],"instances":[118],"very":[120],"prevalent.":[121],"improve":[128],"performance":[130],"convolutional":[132],"neural":[133],"networks":[134],"by":[135],"significant":[137],"margin.":[138],"Comparisons":[139],"other":[141],"noise-robust":[142],"techniques":[143],"similarly":[145],"encouraging.":[146]},"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":7},{"year":2021,"cited_by_count":2}],"updated_date":"2026-02-22T13:39:03.778224","created_date":"2025-10-10T00:00:00"}