{"id":"https://openalex.org/W4416798949","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249250","title":"Attention-Based Adaptive Structured Patchout Spectrogram Transformer for Music Classification","display_name":"Attention-Based Adaptive Structured Patchout Spectrogram Transformer for Music Classification","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798949","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249250"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249250","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5069339294","display_name":"Yuan Liu","orcid":"https://orcid.org/0000-0002-2578-0707"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuan Liu","raw_affiliation_strings":["Waseda University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069351161","display_name":"Lingqing Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Lingqing Liu","raw_affiliation_strings":["Waseda University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015202222","display_name":"Yichen Yang","orcid":"https://orcid.org/0000-0002-3365-7178"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yichen Yang","raw_affiliation_strings":["Waseda University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075702573","display_name":"Shoji Makino","orcid":"https://orcid.org/0000-0003-1934-640X"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoji Makino","raw_affiliation_strings":["Waseda University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38579935,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"282","last_page":"287"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9846000075340271,"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":0.9846000075340271,"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":0.001500000013038516,"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/T10057","display_name":"Face and Expression Recognition","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/spectrogram","display_name":"Spectrogram","score":0.8873999714851379},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6316999793052673},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.46630001068115234},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.41600000858306885},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.41510000824928284},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4041000008583069},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3910999894142151}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8873999714851379},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6593000292778015},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6316999793052673},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6097999811172485},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.46630001068115234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.460099995136261},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.41600000858306885},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.41510000824928284},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4041000008583069},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3910999894142151},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C159693508","wikidata":"https://www.wikidata.org/wiki/Q3301075","display_name":"Phonocardiogram","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26489999890327454},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2646999955177307},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.2563999891281128},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.25429999828338623},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249250","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2123843894","https://openalex.org/W2127615536","https://openalex.org/W2131981197","https://openalex.org/W2133824856","https://openalex.org/W2178339699","https://openalex.org/W3196974791","https://openalex.org/W3205475937","https://openalex.org/W3206996142","https://openalex.org/W4213019189","https://openalex.org/W4226442948","https://openalex.org/W4387244556","https://openalex.org/W4390190626","https://openalex.org/W4399256826","https://openalex.org/W4402111678","https://openalex.org/W4415428168"],"related_works":[],"abstract_inverted_index":{"Music":[0],"classification":[1],"is":[2,23,34],"a":[3,36,80],"subfield":[4],"of":[5,16,63],"audio":[6,29],"classification,":[7],"which":[8],"aims":[9],"to":[10,60],"understand":[11],"and":[12,43,128],"differentiate":[13],"various":[14],"types":[15],"music.":[17,76],"Patchout":[18,39,85,144],"faSt":[19],"Spectrogram":[20],"Transformer":[21],"(PaSST)":[22],"an":[24],"efficient":[25],"transformer":[26],"model":[27,45],"for":[28,73,118],"classification.":[30,131],"Its":[31],"core":[32],"innovation":[33],"Patchout,":[35],"token-dropping":[37],"mechanism.":[38,114],"reduces":[40],"computational":[41],"demands":[42],"improves":[44],"generalization":[46],"by":[47,94],"shortening":[48],"the":[49,61,90,96,110,141],"input":[50],"sequence.":[51],"However,":[52],"its":[53],"random":[54,143],"patch":[55],"selection":[56],"strategy":[57],"may":[58],"lead":[59],"loss":[62,67],"crucial":[64],"information.":[65],"This":[66],"hinders":[68],"full":[69],"feature":[70],"learning,":[71],"especially":[72],"structurally":[74],"rich":[75],"Therefore,":[77],"we":[78],"proposed":[79,138],"novel":[81],"Attention-based":[82],"Adaptive":[83],"Structured":[84],"(AASPatchout).":[86],"It":[87],"deterministically":[88],"preserves":[89],"most":[91],"informative":[92],"patches":[93],"using":[95],"transformer's":[97],"internal":[98],"attention":[99,113],"scores.":[100],"Our":[101],"AASPatchout":[102,117],"requires":[103],"no":[104],"additional":[105],"modules,":[106],"instead":[107],"directly":[108],"utilizing":[109],"model's":[111],"existing":[112],"We":[115],"evaluated":[116],"two":[119],"downstream":[120],"tasks":[121],"in":[122],"music":[123,129],"classification:":[124],"polyphonic":[125],"instrument":[126],"recognition":[127],"genre":[130],"The":[132],"experimental":[133],"results":[134],"demonstrated":[135],"that":[136],"our":[137],"method":[139],"outperformed":[140],"conventional":[142],"baseline.":[145]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}