{"id":"https://openalex.org/W4385822464","doi":"https://doi.org/10.21437/interspeech.2023-1380","title":"Few-shot Class-incremental Audio Classification Using Adaptively-refined Prototypes","display_name":"Few-shot Class-incremental Audio Classification Using Adaptively-refined Prototypes","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822464","doi":"https://doi.org/10.21437/interspeech.2023-1380"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-1380","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5100617962","display_name":"Wei Xie","orcid":"https://orcid.org/0000-0001-7163-2521"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wei Xie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070863631","display_name":"Yanxiong Li","orcid":"https://orcid.org/0000-0003-4362-1125"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanxiong Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102706072","display_name":"Qianhua He","orcid":"https://orcid.org/0000-0002-9079-4566"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qianhua He","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055239917","display_name":"Wenchang Cao","orcid":"https://orcid.org/0009-0008-2790-2983"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenchang Cao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5049691461","display_name":"Tuomas Virtanen","orcid":"https://orcid.org/0000-0002-4604-9729"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tuomas Virtanen","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100617962"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5674,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84067021,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"301","last_page":"305"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.998199999332428,"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":0.998199999332428,"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":0.9926000237464905,"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":0.9409999847412109,"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/shot","display_name":"Shot (pellet)","score":0.7822076082229614},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7365009188652039},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.7067105770111084},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5269069075584412},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.4406638741493225},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3524324893951416},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3515051603317261},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08745023608207703}],"concepts":[{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.7822076082229614},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7365009188652039},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.7067105770111084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5269069075584412},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.4406638741493225},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3524324893951416},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3515051603317261},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08745023608207703},{"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},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2023-1380","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:trepo.tuni.fi:10024/207274","is_oa":false,"landing_page_url":"https://trepo.tuni.fi/handle/10024/207274","pdf_url":null,"source":{"id":"https://openalex.org/S7407055260","display_name":"Trepo - Institutional Repository of Tampere University","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1891287906","https://openalex.org/W2036807459","https://openalex.org/W2775347418","https://openalex.org/W1969923398","https://openalex.org/W2772917594","https://openalex.org/W2166024367","https://openalex.org/W2755342338","https://openalex.org/W4306975314","https://openalex.org/W2981091784","https://openalex.org/W4381730653"],"abstract_inverted_index":{"New":[0],"classes":[1,46,56],"of":[2,30,47,54,84,130],"sounds":[3,48,83],"constantly":[4],"emerge":[5],"with":[6,49,94],"a":[7,40,50,67,95],"few":[8,51],"samples,":[9],"making":[10],"it":[11],"challenging":[12],"for":[13,81],"models":[14],"to":[15,17,25,38,42,69,76,106,118],"adapt":[16],"dynamic":[18,111],"acoustic":[19],"environments.":[20],"This":[21,35],"challenge":[22],"motivates":[23],"us":[24],"address":[26],"the":[27,59,78,108,116,128,136],"new":[28,45,55,85],"problem":[29],"few-shot":[31],"class-incremental":[32],"audio":[33],"classification.":[34],"study":[36],"aims":[37],"enable":[39],"model":[41,90],"continuously":[43],"recognize":[44],"training":[52,98],"samples":[53],"while":[57],"remembering":[58],"learned":[60,87],"ones.":[61],"To":[62],"this":[63],"end,":[64],"we":[65],"propose":[66],"method":[68,138],"generate":[70,107],"discriminative":[71],"prototypes":[72,117],"and":[73,86,100,132,146],"use":[74],"them":[75],"expand":[77],"model's":[79],"classifier":[80],"recognizing":[82],"classes.":[88],"The":[89],"is":[91,104],"first":[92],"trained":[93],"random":[96],"episodic":[97],"strategy,":[99],"then":[101],"its":[102],"backbone":[103],"used":[105],"prototypes.":[109],"A":[110],"relation":[112],"projection":[113],"module":[114],"refines":[115],"enhance":[119],"their":[120],"discriminability.":[121],"Results":[122],"on":[123],"two":[124],"datasets":[125],"(derived":[126],"from":[127],"corpora":[129],"Nsynth":[131],"FSD-MIX-CLIPS)":[133],"show":[134],"that":[135],"proposed":[137],"exceeds":[139],"three":[140],"state-of-the-art":[141],"methods":[142],"in":[143],"average":[144],"accuracy":[145],"performance":[147],"dropping":[148],"rate.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-12T07:58:50.170612","created_date":"2025-10-10T00:00:00"}