{"id":"https://openalex.org/W4416798936","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249342","title":"TAPA-ICL: Taxonomy-Aware Prompt Augmentation for in-Context Learning in Music Understanding","display_name":"TAPA-ICL: Taxonomy-Aware Prompt Augmentation for in-Context Learning in Music Understanding","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798936","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249342"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249342","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249342","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/A5075027462","display_name":"Jiahao Zhao","orcid":"https://orcid.org/0000-0002-6003-8516"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jiahao Zhao","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University,Kyoto,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University,Kyoto,Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072369703","display_name":"Yunjia Li","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunjia Li","raw_affiliation_strings":["School of Computer Science and Technology, Fudan University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Fudan University,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067956319","display_name":"Kazuyoshi Yoshii","orcid":"https://orcid.org/0000-0001-8387-8609"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuyoshi Yoshii","raw_affiliation_strings":["Graduate School of Engineering, Kyoto University,Kyoto,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Kyoto University,Kyoto,Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39362401,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"264","last_page":"269"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9437000155448914,"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":0.9437000155448914,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.011500000022351742,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.010300000198185444,"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/task","display_name":"Task (project management)","score":0.6887000203132629},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6309000253677368},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5782999992370605},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5382000207901001},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.49810001254081726},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4652000069618225}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6887000203132629},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6560999751091003},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6309000253677368},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5782999992370605},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5382000207901001},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5134000182151794},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.49810001254081726},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4652000069618225},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4359999895095825},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.38600000739097595},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.37869998812675476},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.3736000061035156},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2913999855518341},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2833000123500824},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.2831999957561493},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2784000039100647},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2612000107765198}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249342","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249342","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1983507146","https://openalex.org/W2149628368","https://openalex.org/W2963408210","https://openalex.org/W3092879656","https://openalex.org/W3094138986","https://openalex.org/W3205091761","https://openalex.org/W4377140494","https://openalex.org/W4382239690","https://openalex.org/W4385392784","https://openalex.org/W4388821551","https://openalex.org/W4402670276","https://openalex.org/W4410089085"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"TAPA-ICL,":[3],"a":[4],"novel":[5],"in-context":[6],"learning":[7],"(ICL)":[8],"framework":[9],"for":[10],"few/zero-shot":[11,129],"symbolic":[12,50],"music":[13],"understanding":[14,49],"task":[15,167],"that":[16,86,143],"generates":[17],"human-readable":[18],"analysis.":[19],"Conventional":[20],"ICL":[21,151],"approaches":[22],"mainly":[23],"rely":[24],"on":[25,69,156,164],"the":[26,70,121],"ability":[27],"of":[28,48,78,100,160],"large":[29],"language":[30],"models":[31],"(LLMs)":[32],"to":[33,53,173],"infer":[34],"patterns":[35],"and":[36,97,114,120,136,158,168],"tasks":[37],"from":[38],"contextual":[39],"examples.":[40],"However,":[41],"while":[42],"LLMs":[43],"have":[44],"shown":[45],"basic":[46],"capability":[47,56],"music,":[51],"how":[52],"enhance":[54],"such":[55],"via":[57,104],"additional":[58],"context":[59,91],"still":[60],"remains":[61],"unexplored.":[62],"To":[63],"tackle":[64],"this":[65],"issue,":[66],"we":[67],"focus":[68],"two":[71],"major":[72],"challenges":[73],"as":[74],"follows:":[75],"(1)":[76],"Sparsity":[77],"Score":[79],"Input":[80],"through":[81],"taxonomy-aware":[82],"prompt":[83],"augmentation":[84],"(TAPA)":[85],"distills":[87],"label-to-feature":[88],"profiles,":[89],"reducing":[90],"length":[92],"by":[93],"over":[94],"10":[95],"times;":[96],"(2)":[98],"Complexity":[99],"Musical":[101],"Semantics":[102],"Reasoning":[103],"structured":[105],"chain-of-thought":[106],"(CoT)":[107],"prompts":[108],"enforcing":[109],"feature":[110],"extraction,":[111],"context-aware":[112],"analysis,":[113],"decisionmaking.":[115],"By":[116],"combining":[117],"TAPA":[118],"strategy":[119],"CoT":[122],"reasoning":[123],"prompts,":[124],"our":[125,144],"method":[126,146],"enables":[127],"effective":[128],"adaptation":[130],"across":[131],"emotion":[132],"recognition,":[133],"composer":[134],"identification,":[135],"genre":[137],"classification":[138],"tasks.":[139],"Experimental":[140],"results":[141],"show":[142],"TAPAICL":[145],"significantly":[147],"outperforms":[148],"conventional":[149],"few-shot":[150],"baselines":[152],"(including":[153],"those":[154],"based":[155],"ultra-large":[157],"mixture":[159],"experts":[161],"(MoE)":[162],"models)":[163],"each":[165],"downstream":[166],"achieves":[169],"slightly":[170],"weaker":[171],"performance":[172],"existing":[174],"many-shot":[175],"approaches.":[176]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}