{"id":"https://openalex.org/W4406860640","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849053","title":"Enhancing Acoustic Scene Classification with Layer-wise Fine-Tuning on the SSAST Model","display_name":"Enhancing Acoustic Scene Classification with Layer-wise Fine-Tuning on the SSAST Model","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406860640","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849053"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10849053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"conference-paper","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":null,"display_name":"Shuting Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shuting Hao","raw_affiliation_strings":["The University of Tokyo,Graduate School of Engineering,Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Graduate School of Engineering,Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066555365","display_name":"Daisuke Saito","orcid":"https://orcid.org/0000-0002-5999-2505"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daisuke Saito","raw_affiliation_strings":["The University of Tokyo,Graduate School of Engineering,Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Graduate School of Engineering,Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041213266","display_name":"Nobuaki Minematsu","orcid":"https://orcid.org/0000-0002-8778-9555"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobuaki Minematsu","raw_affiliation_strings":["The University of Tokyo,Graduate School of Engineering,Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Graduate School of Engineering,Tokyo","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9757000207901001,"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":0.9757000207901001,"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":0.9397000074386597,"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/T11698","display_name":"Underwater Acoustics Research","score":0.9376999735832214,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6870955228805542},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.6483417749404907},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.449897438287735},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4086463749408722},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35515284538269043},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3227607011795044},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.16304785013198853}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6870955228805542},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.6483417749404907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.449897438287735},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4086463749408722},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35515284538269043},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3227607011795044},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.16304785013198853},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10849053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4346272346","display_name":"Measurement of L2 pronunciation deviation and L2 listening disfluency and its application to prosody training for smooth international communication","funder_award_id":"23K17459","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8512205465","display_name":"Measurement and modeling of cognitive breakdown and their use to enhance cognitive robustness for international oral communication","funder_award_id":"22H00527","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2294370754","https://openalex.org/W2593116425","https://openalex.org/W2759976799","https://openalex.org/W2951942899","https://openalex.org/W3016227692","https://openalex.org/W3034368386","https://openalex.org/W3041618382","https://openalex.org/W3165945839","https://openalex.org/W3196974791","https://openalex.org/W3206996142","https://openalex.org/W4387244556","https://openalex.org/W6639703010","https://openalex.org/W6779341498","https://openalex.org/W6784333009","https://openalex.org/W6802510933"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"We":[0],"introduce":[1],"a":[2,19,48,103,143],"novel":[3,49],"approach":[4,105],"to":[5,97],"Acoustic":[6,35,71],"Scene":[7],"Classification":[8],"(ASC)":[9],"using":[10],"the":[11,25,32,68,89,112,117,121,147],"Self-Supervised":[12],"Audio":[13],"Spectrogram":[14],"Transformer":[15],"(SSAST)":[16],"sophisticated":[17],"with":[18,149],"focus":[20],"on":[21,88],"layerwise":[22],"fine-tuning.":[23,66],"Recognizing":[24],"challenge":[26],"in":[27,31,154,158],"distinguishing":[28],"similar":[29],"classes":[30],"TAU":[33,69],"Urban":[34,70],"Scenes":[36,72],"2022":[37,73],"dataset,":[38],"which":[39,84],"sometimes":[40],"exceeds":[41],"human":[42],"perceptual":[43],"capabilities,":[44],"this":[45],"study":[46],"introduces":[47],"architecture":[50],"that":[51],"categorizes":[52],"environmental":[53],"audio":[54],"streams":[55],"into":[56],"predefined":[57],"semantic":[58],"labels":[59],"through":[60],"integrating":[61],"multi-layer":[62],"classifiers":[63],"and":[64,79,91,108,137,156],"direct":[65],"Employing":[67],"Mobile":[74],"dataset":[75],"for":[76,119],"both":[77],"fine-tuning":[78,110],"validation,":[80],"our":[81,128],"SSAST":[82,130],"model,":[83],"was":[85,94,114],"initially":[86],"pre-trained":[87],"AudioSet":[90],"LibriSpeech":[92],"datasets,":[93],"uniquely":[95],"finetuned":[96],"enhance":[98],"ASC-specific":[99],"feature":[100],"learning.":[101],"Here,":[102],"combined":[104],"of":[106,111,135,140,152],"layer-wise":[107],"simultaneous":[109],"backbone":[113],"introduced,":[115],"eliminating":[116],"need":[118],"reassembling":[120],"dataset.":[122],"This":[123],"method":[124],"achieved":[125],"satisfactory":[126],"results,":[127],"layered":[129],"system":[131],"reached":[132],"an":[133,138],"accuracy":[134,155],"52.43%":[136],"AUC":[139],"88.51%,":[141],"marking":[142],"notable":[144],"improvement":[145],"over":[146],"baseline":[148],"absolute":[150],"increases":[151],"1.25%":[153],"0.70%":[157],"AUC.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}