{"id":"https://openalex.org/W4416800026","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11248985","title":"Transformer-Based Unpaired Piano Accompaniment Style Transfer","display_name":"Transformer-Based Unpaired Piano Accompaniment Style Transfer","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416800026","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11248985"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11248985","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11248985","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/A5115901506","display_name":"Hsin Ai","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin Ai","raw_affiliation_strings":["National Taiwan University,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061291906","display_name":"Yi\u2010Hsuan Yang","orcid":"https://orcid.org/0000-0002-2724-6161"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Hsuan Yang","raw_affiliation_strings":["National Taiwan University,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32307162,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"240","last_page":"245"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.6722000241279602,"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"}},"topics":[{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.6722000241279602,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.250900000333786,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.025299999862909317,"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/piano","display_name":"Piano","score":0.8371000289916992},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.739799976348877},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6061000227928162},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5702999830245972},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.39480000734329224},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.38429999351501465}],"concepts":[{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.8371000289916992},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.739799976348877},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6061000227928162},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5702999830245972},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5346999764442444},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.39480000734329224},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.38429999351501465},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.37630000710487366},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35429999232292175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3531999886035919},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.3314000070095062},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.296999990940094},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.2955999970436096},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.26820001006126404},{"id":"https://openalex.org/C2993622096","wikidata":"https://www.wikidata.org/wiki/Q1344860","display_name":"Performance practice","level":3,"score":0.2549000084400177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11248985","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11248985","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":18,"referenced_works":["https://openalex.org/W2085778999","https://openalex.org/W2772474126","https://openalex.org/W2891757161","https://openalex.org/W2898827701","https://openalex.org/W2964706117","https://openalex.org/W3010903955","https://openalex.org/W3080857286","https://openalex.org/W3092879656","https://openalex.org/W3127854286","https://openalex.org/W4372260493","https://openalex.org/W4372266019","https://openalex.org/W4372348948","https://openalex.org/W4377719641","https://openalex.org/W4392271377","https://openalex.org/W4399418532","https://openalex.org/W4409346471","https://openalex.org/W4414359284","https://openalex.org/W4414359717"],"related_works":[],"abstract_inverted_index":{"Arranger-specific":[0],"style":[1,34,91],"transfer":[2],"for":[3,111,118],"pop":[4],"piano":[5],"covers":[6],"requires":[7],"effective":[8,110],"content-style":[9],"disentanglement.":[10],"To":[11],"address":[12],"this,":[13],"we":[14],"propose":[15],"a":[16,20,28,52,99,115],"framework":[17],"that":[18,73,98],"uses":[19],"lead":[21,106],"sheet":[22],"(namely,":[23],"melody":[24],"and":[25,84,90],"chords)":[26],"as":[27],"style-agnostic":[29],"content":[30,88,102],"anchor,":[31],"enabling":[32],"precise":[33],"manipulation":[35],"without":[36],"requiring":[37],"paired":[38],"data.":[39],"We":[40],"then":[41],"systematically":[42],"compare":[43],"several":[44],"Transformer-based":[45],"architectures":[46],"to":[47],"evaluate":[48],"the":[49,67,74,105],"efficacy":[50],"of":[51,87],"direct":[53],"token-based":[54,76],"conditioning":[55],"strategy":[56],"versus":[57],"more":[58],"complicated":[59],"embedding-based":[60],"methods.":[61],"While":[62],"all":[63],"approaches":[64],"effectively":[65],"capture":[66],"target":[68],"style,":[69],"our":[70],"evaluation":[71],"shows":[72],"simpler":[75],"model":[77],"achieves":[78],"superior":[79],"performance":[80],"in":[81],"both":[82],"objective":[83],"subjective":[85],"assessments":[86],"preservation":[89],"matching.":[92],"This":[93],"finding":[94],"provides":[95],"empirical":[96],"evidences":[97],"robust,":[100],"explicit":[101],"representation":[103],"(i.e.,":[104],"sheet)":[107],"is":[108],"highly":[109],"this":[112],"task,":[113],"offering":[114],"practical":[116],"benchmark":[117],"controllable":[119],"music":[120],"generation.":[121]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}