{"id":"https://openalex.org/W4416250146","doi":"https://doi.org/10.1109/waspaa66052.2025.11230989","title":"Online incremental learning for audio classification using a pretrained audio model","display_name":"Online incremental learning for audio classification using a pretrained audio model","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416250146","doi":"https://doi.org/10.1109/waspaa66052.2025.11230989"},"language":null,"primary_location":{"id":"doi:10.1109/waspaa66052.2025.11230989","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230989","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/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":true,"raw_author_name":"Manjunath Mulimani","raw_affiliation_strings":["Tampere University,Signal Processing Research Centre,Tampere,Finland"],"affiliations":[{"raw_affiliation_string":"Tampere University,Signal Processing Research Centre,Tampere,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,Tampere,Finland"],"affiliations":[{"raw_affiliation_string":"Tampere University,Signal Processing Research Centre,Tampere,Finland","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5053990884"],"corresponding_institution_ids":["https://openalex.org/I166825849"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.45179237,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":0.6302000284194946,"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":0.6302000284194946,"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":0.16920000314712524,"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":0.06340000033378601,"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/incremental-learning","display_name":"Incremental learning","score":0.8057000041007996},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.7653999924659729},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.48500001430511475},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4528999924659729},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4293000102043152},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.3955000042915344},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.37470000982284546},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.328900009393692}],"concepts":[{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.8057000041007996},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.7653999924659729},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7648000121116638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5648000240325928},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48809999227523804},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.48500001430511475},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4528999924659729},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4293000102043152},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3955000042915344},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39320001006126404},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.37470000982284546},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3116999864578247},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.26409998536109924},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11230989","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230989","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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":22,"referenced_works":["https://openalex.org/W1972567154","https://openalex.org/W2052666245","https://openalex.org/W2788388592","https://openalex.org/W2997208223","https://openalex.org/W3094550259","https://openalex.org/W3160262112","https://openalex.org/W3196974791","https://openalex.org/W3205475937","https://openalex.org/W3206996142","https://openalex.org/W4211058963","https://openalex.org/W4312923322","https://openalex.org/W4313125978","https://openalex.org/W4378194825","https://openalex.org/W4385823383","https://openalex.org/W4392904001","https://openalex.org/W4392904244","https://openalex.org/W4392909553","https://openalex.org/W4394564382","https://openalex.org/W4404609334","https://openalex.org/W4406860640","https://openalex.org/W4408092460","https://openalex.org/W4408345623"],"related_works":[],"abstract_inverted_index":{"Incremental":[0],"learning":[1,19,171,175,181],"aims":[2],"to":[3,40,52,54,62,86],"learn":[4,41],"new":[5,56],"tasks":[6,97],"sequentially":[7],"without":[8],"forgetting":[9,65,156],"the":[10,16,26,31,35,64,111,117,122,125,130,139,148,162,165,186,196],"previously":[11],"learned":[12],"ones.":[13],"Most":[14],"of":[15,66,124,133,151,157,164,182],"existing":[17],"incremental":[18,43,90,170],"methods":[20],"for":[21,49,76,193],"audio":[22,79,95,114],"focus":[23],"on":[24,30],"training":[25,149],"model":[27,37,46,85,140],"from":[28,185],"scratch":[29],"initial":[32],"task,":[33,57,153],"and":[34,116,127,178],"same":[36],"is":[38,47],"used":[39],"upcoming":[42],"tasks.":[44,68,159],"The":[45],"trained":[48],"several":[50],"iterations":[51],"adapt":[53],"each":[55],"using":[58,77,176],"some":[59],"specific":[60],"approaches":[61],"reduce":[63],"old":[67,158],"In":[69],"this":[70,119],"work,":[71],"we":[72,101],"propose":[73],"a":[74,83,103,106,142],"method":[75,137,167],"generalizable":[78],"embeddings":[80,115,126],"produced":[81],"by":[82],"pre-trained":[84,112],"develop":[87],"an":[88],"online":[89],"learner":[91],"that":[92],"solves":[93],"sequential":[94],"classification":[96],"over":[98],"time.":[99],"Specifically,":[100],"inject":[102],"layer":[104,120],"with":[105,154],"nonlinear":[107],"activation":[108],"function":[109],"between":[110],"model\u2019s":[113],"classifier;":[118],"expands":[121],"dimensionality":[123],"effectively":[128],"captures":[129],"distinct":[131],"characteristics":[132],"sound":[134],"classes.":[135],"Our":[136],"adapts":[138],"in":[141,168],"single":[143],"forward":[144],"pass":[145],"(online)":[146],"through":[147],"samples":[150],"any":[152],"minimal":[155],"We":[160],"demonstrate":[161],"performance":[163],"proposed":[166,197],"two":[169],"setups:":[172],"one":[173,179],"class-incremental":[174],"ESC-50":[177],"domain-incremental":[180],"different":[183],"cities":[184],"TAU":[187],"Urban":[188],"Acoustic":[189],"Scenes":[190],"2019":[191],"dataset;":[192],"both":[194],"cases,":[195],"approach":[198],"outperforms":[199],"other":[200],"methods.":[201]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}