{"id":"https://openalex.org/W7125933431","doi":"https://doi.org/10.1109/smc58881.2025.11342755","title":"Exploring Classical Piano Performance Generation with Expressive Music Variational AutoEncoder","display_name":"Exploring Classical Piano Performance Generation with Expressive Music Variational AutoEncoder","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125933431","doi":"https://doi.org/10.1109/smc58881.2025.11342755"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11342755","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342755","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5042350489","display_name":"Jing Luo","orcid":"https://orcid.org/0000-0001-7138-3705"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jing Luo","raw_affiliation_strings":["Xi’an Jiaotong University,School of Computer Science and Technology,Xi’an,China,710049"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Computer Science and Technology,Xi’an,China,710049","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088751229","display_name":"Xia Yang","orcid":"https://orcid.org/0000-0002-3971-038X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Yang","raw_affiliation_strings":["Xi’an Jiaotong University,School of Computer Science and Technology,Xi’an,China,710049"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Computer Science and Technology,Xi’an,China,710049","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100440168","display_name":"Jie Wei","orcid":"https://orcid.org/0000-0002-1080-2774"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Wei","raw_affiliation_strings":["China Mobile Group Shaanxi Co., Ltd.,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"China Mobile Group Shaanxi Co., Ltd.,Xi’an,China","institution_ids":["https://openalex.org/I180662265"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5042350489"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.71567637,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1817","last_page":"1822"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.7286999821662903,"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":0.7286999821662903,"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":0.1995999962091446,"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":0.035100001841783524,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7544999718666077},{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.7038999795913696},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5475999712944031},{"id":"https://openalex.org/keywords/musical-notation","display_name":"Musical notation","score":0.5214999914169312},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.444599986076355},{"id":"https://openalex.org/keywords/creativity","display_name":"Creativity","score":0.39660000801086426},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.36500000953674316},{"id":"https://openalex.org/keywords/classical-music","display_name":"Classical music","score":0.35120001435279846}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7544999718666077},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.7038999795913696},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6503999829292297},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5475999712944031},{"id":"https://openalex.org/C88639978","wikidata":"https://www.wikidata.org/wiki/Q233861","display_name":"Musical notation","level":3,"score":0.5214999914169312},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49129998683929443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47369998693466187},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.444599986076355},{"id":"https://openalex.org/C11012388","wikidata":"https://www.wikidata.org/wiki/Q170658","display_name":"Creativity","level":2,"score":0.39660000801086426},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.36500000953674316},{"id":"https://openalex.org/C542929976","wikidata":"https://www.wikidata.org/wiki/Q9730","display_name":"Classical music","level":3,"score":0.35120001435279846},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3495999872684479},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C196017715","wikidata":"https://www.wikidata.org/wiki/Q862597","display_name":"Musical form","level":3,"score":0.31709998846054077},{"id":"https://openalex.org/C195818886","wikidata":"https://www.wikidata.org/wiki/Q5421724","display_name":"Expressive power","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.29739999771118164},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.289000004529953},{"id":"https://openalex.org/C47350684","wikidata":"https://www.wikidata.org/wiki/Q5157306","display_name":"Computational creativity","level":3,"score":0.28130000829696655},{"id":"https://openalex.org/C2983311337","wikidata":"https://www.wikidata.org/wiki/Q34379","display_name":"Musical instrument","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C2779732396","wikidata":"https://www.wikidata.org/wiki/Q2207288","display_name":"Craft","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.26820001006126404},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.2630000114440918},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2574000060558319},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C2780226923","wikidata":"https://www.wikidata.org/wiki/Q929848","display_name":"Movement (music)","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11342755","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342755","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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":9,"referenced_works":["https://openalex.org/W2899124505","https://openalex.org/W2963408210","https://openalex.org/W3092879656","https://openalex.org/W3108047681","https://openalex.org/W3175663427","https://openalex.org/W4372266019","https://openalex.org/W4377140494","https://openalex.org/W4385245566","https://openalex.org/W4401014602"],"related_works":[],"abstract_inverted_index":{"The":[0],"creativity":[1],"of":[2,32,45,71,116],"classical":[3,34,72,155],"music":[4],"arises":[5],"not":[6],"only":[7],"from":[8,17,37],"composers":[9],"who":[10,19],"craft":[11],"the":[12,21,30,42,50,55,65,79,102,114,167],"musical":[13,159,172],"sheets":[14],"but":[15],"also":[16],"performers":[18],"interpret":[20],"static":[22],"notations":[23],"with":[24,123,157],"expressive":[25,69,111],"nuances.":[26],"This":[27],"paper":[28],"addresses":[29],"challenge":[31],"generating":[33],"piano":[35],"performances":[36,156],"scratch,":[38],"aiming":[39],"to":[40,131,162,176],"emulate":[41],"dual":[43],"roles":[44],"composer":[46],"and":[47,68,104,136,148],"pianist":[48],"in":[49],"creative":[51],"process.":[52],"We":[53],"introduce":[54],"Expressive":[56,80],"Compound":[57],"Word":[58],"(ECP)":[59],"representation,":[60],"which":[61],"effectively":[62],"captures":[63],"both":[64],"metrical":[66],"structure":[67],"nuances":[70],"performances.":[73],"Building":[74],"on":[75,170],"this,":[76],"we":[77],"propose":[78],"Music":[81],"Variational":[82,93],"AutoEncoder":[83,94],"(XMVAE),":[84],"a":[85,90,105,128,177],"model":[86],"featuring":[87],"two":[88],"branches:":[89],"Vector":[91],"Quantized":[92],"(VQ-VAE)":[95],"branch":[96,108,169],"that":[97,109,152],"generates":[98,154],"score-related":[99],"content,":[100],"representing":[101],"Composer,":[103],"vanilla":[106],"VAE":[107],"produces":[110],"details,":[112],"fulfilling":[113],"role":[115],"Pianist.":[117],"These":[118],"branches":[119],"are":[120],"jointly":[121],"trained":[122],"similar":[124],"Seq2Seq":[125],"architectures,":[126],"leveraging":[127],"multiscale":[129],"encoder":[130],"capture":[132],"beat-level":[133],"contextual":[134],"information":[135],"an":[137],"orthogonal":[138],"Transformer":[139],"decoder":[140],"for":[141],"efficient":[142],"compound":[143],"tokens":[144],"decoding.":[145],"Both":[146],"objective":[147],"subjective":[149],"evaluations":[150],"demonstrate":[151],"XMVAE":[153],"superior":[158],"quality":[160],"compared":[161],"state-of-the-art":[163],"models.":[164],"Furthermore,":[165],"pre-training":[166],"Composer":[168],"extra":[171],"score":[173],"datasets":[174],"contribute":[175],"significant":[178],"performance":[179],"gain.":[180]},"counts_by_year":[],"updated_date":"2026-01-29T23:17:01.242718","created_date":"2026-01-29T00:00:00"}