{"id":"https://openalex.org/W4410771569","doi":"https://doi.org/10.1109/icasspw65056.2025.11011278","title":"Class-Incremental Learning for Sound Event Localization and Detection","display_name":"Class-Incremental Learning for Sound Event Localization and Detection","publication_year":2025,"publication_date":"2025-04-06","ids":{"openalex":"https://openalex.org/W4410771569","doi":"https://doi.org/10.1109/icasspw65056.2025.11011278"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw65056.2025.11011278","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw65056.2025.11011278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5086898291","display_name":"Ruchi Pandey","orcid":null},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Ruchi Pandey","raw_affiliation_strings":["Tampere University,Signal Processing Research Centre,Finland"],"affiliations":[{"raw_affiliation_string":"Tampere University,Signal Processing Research Centre,Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053990884","display_name":"Manjunath Mulimani","orcid":"https://orcid.org/0000-0001-9927-1123"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Manjunath Mulimani","raw_affiliation_strings":["Tampere University,Signal Processing Research Centre,Finland"],"affiliations":[{"raw_affiliation_string":"Tampere University,Signal Processing Research Centre,Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010846139","display_name":"Archontis Politis","orcid":"https://orcid.org/0000-0002-0595-2356"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Archontis Politis","raw_affiliation_strings":["Tampere University,Signal Processing Research Centre,Finland"],"affiliations":[{"raw_affiliation_string":"Tampere University,Signal Processing Research Centre,Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079981416","display_name":"Annamaria Mesaros","orcid":"https://orcid.org/0000-0002-6640-9752"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Annamaria Mesaros","raw_affiliation_strings":["Tampere University,Signal Processing Research Centre,Finland"],"affiliations":[{"raw_affiliation_string":"Tampere University,Signal Processing Research Centre,Finland","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5086898291"],"corresponding_institution_ids":["https://openalex.org/I166825849"],"apc_list":null,"apc_paid":null,"fwci":3.8348,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93069206,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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":0.9994000196456909,"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":0.987500011920929,"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":0.9452000260353088,"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/computer-science","display_name":"Computer science","score":0.6726658344268799},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5696534514427185},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5358836054801941},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4828927516937256},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4529813230037689},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3478715121746063},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.14768275618553162},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06256592273712158}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6726658344268799},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5696534514427185},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5358836054801941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4828927516937256},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4529813230037689},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3478715121746063},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.14768275618553162},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06256592273712158},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw65056.2025.11011278","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw65056.2025.11011278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2088720693","https://openalex.org/W2397865640","https://openalex.org/W2473930607","https://openalex.org/W2788388592","https://openalex.org/W2810934215","https://openalex.org/W2936093102","https://openalex.org/W2939137134","https://openalex.org/W2948734064","https://openalex.org/W2964189064","https://openalex.org/W2964342924","https://openalex.org/W2998139081","https://openalex.org/W3083274258","https://openalex.org/W3163193264","https://openalex.org/W3163881933","https://openalex.org/W3197097128","https://openalex.org/W3208750293","https://openalex.org/W4221159370","https://openalex.org/W4372260505","https://openalex.org/W4392909553","https://openalex.org/W4401610131","https://openalex.org/W6796679619","https://openalex.org/W6838853441","https://openalex.org/W6849910596","https://openalex.org/W6850731298","https://openalex.org/W6869752739","https://openalex.org/W6870663847"],"related_works":["https://openalex.org/W2909726438","https://openalex.org/W2067046791","https://openalex.org/W2909888262","https://openalex.org/W2025747832","https://openalex.org/W3020957235","https://openalex.org/W2056769785","https://openalex.org/W611303608","https://openalex.org/W4313595395","https://openalex.org/W2312783472","https://openalex.org/W2909748163"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,60,75,88,96,99,104],"feasibility":[4],"of":[5,33,77,107],"class-incremental":[6],"learning":[7,38,83],"(CIL)":[8],"for":[9,113],"Sound":[10,63],"Event":[11],"Localization":[12],"and":[13,73,86],"Detection":[14],"(SELD)":[15],"tasks.":[16],"The":[17,36,55],"method":[18,119],"features":[19],"an":[20],"incremental":[21,97],"learner":[22],"that":[23],"can":[24],"learn":[25],"new":[26,90],"sound":[27,71],"classes":[28,72,85,91],"independently":[29],"while":[30],"preserving":[31],"knowledge":[32],"old":[34],"classes.":[35,109],"continual":[37],"is":[39,101],"achieved":[40],"through":[41],"a":[42],"mean":[43],"square":[44],"error-based":[45],"distillation":[46],"loss":[47],"to":[48],"minimize":[49],"output":[50],"discrepancies":[51],"between":[52],"subsequent":[53],"learners.":[54],"experiments":[56],"are":[57],"conducted":[58],"on":[59,103],"TAU-NIGENS":[61],"Spatial":[62],"Events":[64],"2021":[65],"dataset,":[66,116],"which":[67],"includes":[68],"12":[69],"different":[70],"demonstrate":[74],"efficacy":[76],"proposed":[78,118],"method.":[79],"We":[80],"begin":[81],"by":[82],"8":[84],"introduce":[87],"4":[89],"at":[92],"next":[93],"stage.":[94],"After":[95],"phase,":[98],"system":[100],"evaluated":[102],"full":[105],"set":[106],"learned":[108],"Results":[110],"show":[111],"that,":[112],"this":[114],"realistic":[115],"our":[117],"successfully":[120],"maintains":[121],"baseline":[122],"performance":[123],"across":[124],"all":[125],"metrics.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}