{"id":"https://openalex.org/W4394564382","doi":"https://doi.org/10.1109/taslp.2024.3385287","title":"Few-Shot Class-Incremental Audio Classification With Adaptive Mitigation of Forgetting and Overfitting","display_name":"Few-Shot Class-Incremental Audio Classification With Adaptive Mitigation of Forgetting and Overfitting","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4394564382","doi":"https://doi.org/10.1109/taslp.2024.3385287"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3385287","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3385287","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":["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/A5070863631","display_name":"Yanxiong Li","orcid":"https://orcid.org/0000-0003-4362-1125"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yanxiong Li","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100708120","display_name":"Jialong Li","orcid":"https://orcid.org/0009-0002-9742-3044"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jialong Li","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082697451","display_name":"Yongjie Si","orcid":"https://orcid.org/0009-0006-0253-0891"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongjie Si","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083131190","display_name":"Jiaxin Tan","orcid":"https://orcid.org/0009-0002-6502-548X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxin Tan","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102706072","display_name":"Qianhua He","orcid":"https://orcid.org/0000-0002-9079-4566"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianhua He","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5070863631"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":3.0543,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.92058699,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"2297","last_page":"2311"},"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":0.9991000294685364,"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":0.9905999898910522,"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/overfitting","display_name":"Overfitting","score":0.932068943977356},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6738748550415039},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.6298828721046448},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5780381560325623},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5238054990768433},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4916570782661438},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3735160231590271},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37097325921058655},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34651970863342285},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.13602641224861145},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12861400842666626},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.06575602293014526}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.932068943977356},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6738748550415039},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.6298828721046448},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5780381560325623},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5238054990768433},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4916570782661438},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3735160231590271},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37097325921058655},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34651970863342285},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.13602641224861145},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12861400842666626},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.06575602293014526},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3385287","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3385287","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.5899999737739563}],"awards":[{"id":"https://openalex.org/G3080163795","display_name":null,"funder_award_id":"2022A1515011687","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G3994375257","display_name":null,"funder_award_id":"61771200","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6173053914","display_name":null,"funder_award_id":"62111530145","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6633902186","display_name":null,"funder_award_id":"62371195","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7284265120","display_name":null,"funder_award_id":"2021A1515011454","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2194775991","https://openalex.org/W2895776009","https://openalex.org/W2964189064","https://openalex.org/W2968134922","https://openalex.org/W2972313371","https://openalex.org/W2980689481","https://openalex.org/W2986739609","https://openalex.org/W2997546679","https://openalex.org/W3015594652","https://openalex.org/W3021946687","https://openalex.org/W3035342403","https://openalex.org/W3088889289","https://openalex.org/W3096805028","https://openalex.org/W3150815752","https://openalex.org/W3160045550","https://openalex.org/W3160061063","https://openalex.org/W3160262112","https://openalex.org/W3162549784","https://openalex.org/W3166898278","https://openalex.org/W3175270254","https://openalex.org/W3177494822","https://openalex.org/W4205236539","https://openalex.org/W4206364333","https://openalex.org/W4210634873","https://openalex.org/W4226134030","https://openalex.org/W4226442948","https://openalex.org/W4226512326","https://openalex.org/W4281261996","https://openalex.org/W4285005022","https://openalex.org/W4285206108","https://openalex.org/W4294690835","https://openalex.org/W4310609408","https://openalex.org/W4312411897","https://openalex.org/W4312923322","https://openalex.org/W4322707137","https://openalex.org/W4362638963","https://openalex.org/W4372260443","https://openalex.org/W4372330959","https://openalex.org/W4372340915","https://openalex.org/W4378194825","https://openalex.org/W4385822464","https://openalex.org/W4385823439","https://openalex.org/W4386057810","https://openalex.org/W6682132143","https://openalex.org/W6736723571","https://openalex.org/W6845412689"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W4378510483","https://openalex.org/W4221142204"],"abstract_inverted_index":{"Few-shot":[0],"Class-incremental":[1],"Audio":[2],"Classification":[3],"(FCAC)":[4],"is":[5,35,64,93,101,119,165,240],"a":[6,60,97],"task":[7],"to":[8,30,36,66,148,167],"continuously":[9],"identify":[10],"incremental":[11,53,78,126,130,159,190],"classes":[12,24,74,127,155],"with":[13,25],"only":[14],"few":[15,122],"training":[16,19,123,185],"samples":[17,108,124,205],"after":[18,103],"the":[20,32,39,69,94,113,150,173,187],"model":[21,40,81,184],"on":[22],"base":[23,46,73,110,154,188],"abundant":[26],"samples.":[27],"The":[28,91,132,143,162,238],"key":[29],"solving":[31],"FCAC":[33,61],"problem":[34],"ensure":[37],"that":[38,218],"has":[41,229],"good":[42],"stability":[43],"(without":[44,51],"forgetting":[45,71,152],"classes)":[47],"and":[48,75,87,100,118,139,156,189,198,212,228],"strong":[49],"plasticity":[50],"overfitting":[52,76,157],"classes).":[54],"In":[55,177],"this":[56],"paper,":[57],"we":[58,179],"propose":[59],"method":[62,221],"which":[63],"able":[65],"adaptively":[67,168],"mitigate":[68,149],"model's":[70,151],"of":[72,77,83,96,109,125,136,153,158,209],"classes.":[79],"Our":[80],"consists":[82,135],"an":[84,88],"embedding":[85],"extractor":[86],"expandable":[89,117,133],"classifier.":[90],"former":[92],"backbone":[95],"residual":[98],"network":[99],"frozen":[102],"being":[104],"trained":[105],"using":[106,121],"sufficient":[107],"classes,":[111,160],"whereas":[112],"latter":[114],"can":[115],"be":[116],"updated":[120],"in":[128,186,226,235],"each":[129],"session.":[131],"classifier":[134],"two":[137,144,175,181],"branches":[138,145],"one":[140],"fusion":[141,163],"module.":[142],"are":[146,200],"designed":[147,166],"respectively.":[161,192,214],"module":[164],"fuse":[169],"predictions":[170],"output":[171],"by":[172,202],"above":[174],"branches.":[176],"addition,":[178],"define":[180],"losses":[182],"for":[183],"sessions,":[191],"Three":[193],"experimental":[194],"datasets":[195],"(NSynth-100,":[196],"FSC-89":[197],"LS-100)":[199],"created":[201],"randomly":[203],"choosing":[204],"from":[206],"audio":[207],"corpora":[208],"NSynth,":[210],"FSD-MIX-CLIP":[211],"LibriSpeech,":[213],"Experimental":[215],"results":[216],"demonstrate":[217],"our":[219],"proposed":[220],"outperforms":[222],"all":[223],"previous":[224,233],"methods":[225,234],"accuracy":[227],"advantage":[230],"over":[231],"most":[232],"computational":[236],"load.":[237],"code":[239],"available":[241],"at":[242],"<uri":[243],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[244],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/Jialongdustin/AMFO</uri>":[245],".":[246]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}