{"id":"https://openalex.org/W4415538808","doi":"https://doi.org/10.1145/3746027.3755871","title":"SyMuPe: Affective and Controllable Symbolic Music Performance","display_name":"SyMuPe: Affective and Controllable Symbolic Music Performance","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538808","doi":"https://doi.org/10.1145/3746027.3755871"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755871","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755871","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.03425","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092241618","display_name":"Ilya Borovik","orcid":"https://orcid.org/0009-0002-1186-2039"},"institutions":[{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Ilya Borovik","raw_affiliation_strings":["Skolkovo Institute of Science and Technology, Moscow, Russian Federation"],"affiliations":[{"raw_affiliation_string":"Skolkovo Institute of Science and Technology, Moscow, Russian Federation","institution_ids":["https://openalex.org/I125989756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002956551","display_name":"Dmitrii Gavrilev","orcid":"https://orcid.org/0009-0005-6904-2852"},"institutions":[{"id":"https://openalex.org/I125989756","display_name":"Skolkovo Institute of Science and Technology","ror":"https://ror.org/03f9nc143","country_code":"RU","type":"education","lineage":["https://openalex.org/I125989756"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Dmitrii Gavrilev","raw_affiliation_strings":["Skolkovo Institute of Science and Technology, Moscow, Russian Federation"],"affiliations":[{"raw_affiliation_string":"Skolkovo Institute of Science and Technology, Moscow, Russian Federation","institution_ids":["https://openalex.org/I125989756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015126177","display_name":"Vladimir Viro","orcid":"https://orcid.org/0000-0002-0473-0890"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vladimir Viro","raw_affiliation_strings":["Peachnote GmbH, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Peachnote GmbH, Munich, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5092241618"],"corresponding_institution_ids":["https://openalex.org/I125989756"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3159759,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10699","last_page":"10708"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10788","display_name":"Neuroscience and Music Perception","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10788","display_name":"Neuroscience and Music Perception","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.996999979019165,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9950000047683716,"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/midi","display_name":"MIDI","score":0.7978000044822693},{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.7211999893188477},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5063999891281128},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.4593999981880188},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.36959999799728394},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.34630000591278076},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.3325999975204468},{"id":"https://openalex.org/keywords/chord","display_name":"Chord (peer-to-peer)","score":0.32919999957084656},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.3228999972343445}],"concepts":[{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.7978000044822693},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.7211999893188477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6159999966621399},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5063999891281128},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46860000491142273},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.4593999981880188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42899999022483826},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.36959999799728394},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.34630000591278076},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.3325999975204468},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33160001039505005},{"id":"https://openalex.org/C194147245","wikidata":"https://www.wikidata.org/wiki/Q1076368","display_name":"Chord (peer-to-peer)","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C146902061","wikidata":"https://www.wikidata.org/wiki/Q476590","display_name":"Music psychology","level":3,"score":0.3125999867916107},{"id":"https://openalex.org/C2779812673","wikidata":"https://www.wikidata.org/wiki/Q169251","display_name":"Sadness","level":3,"score":0.2948000133037567},{"id":"https://openalex.org/C2988148770","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion detection","level":3,"score":0.2903999984264374},{"id":"https://openalex.org/C125468537","wikidata":"https://www.wikidata.org/wiki/Q214961","display_name":"Improvisation","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.27889999747276306},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.2759999930858612},{"id":"https://openalex.org/C2776141551","wikidata":"https://www.wikidata.org/wiki/Q16000087","display_name":"Emotion perception","level":3,"score":0.27300000190734863},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C10864753","wikidata":"https://www.wikidata.org/wiki/Q4353948","display_name":"Music and emotion","level":4,"score":0.26570001244544983},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.25589999556541443},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2542000114917755}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3755871","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755871","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.03425","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.03425","pdf_url":"https://arxiv.org/pdf/2511.03425","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2511.03425","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.03425","pdf_url":"https://arxiv.org/pdf/2511.03425","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415538808.pdf","grobid_xml":"https://content.openalex.org/works/W4415538808.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1555851617","https://openalex.org/W2072206615","https://openalex.org/W2129285401","https://openalex.org/W2149628368","https://openalex.org/W2166345358","https://openalex.org/W2773935811","https://openalex.org/W2899124505","https://openalex.org/W2981644170","https://openalex.org/W2990617740","https://openalex.org/W2990692574","https://openalex.org/W3092879656","https://openalex.org/W3111868559","https://openalex.org/W3173187964","https://openalex.org/W3175663427","https://openalex.org/W4226103472","https://openalex.org/W4256689234","https://openalex.org/W4288028629","https://openalex.org/W4301581299","https://openalex.org/W4304139990","https://openalex.org/W4309501364","https://openalex.org/W4309501419","https://openalex.org/W4381733190","https://openalex.org/W4382021246","https://openalex.org/W4382239517","https://openalex.org/W4387140657","https://openalex.org/W4387195417","https://openalex.org/W4388979610","https://openalex.org/W4392904491","https://openalex.org/W4392931276","https://openalex.org/W4399399630","https://openalex.org/W4399743538","https://openalex.org/W4401014602","https://openalex.org/W4402953786","https://openalex.org/W4403345555","https://openalex.org/W4405917844","https://openalex.org/W4406457807","https://openalex.org/W4407425831","https://openalex.org/W4408353409","https://openalex.org/W4408354053","https://openalex.org/W4414682104","https://openalex.org/W6893317412","https://openalex.org/W6911082919","https://openalex.org/W6930721015","https://openalex.org/W6948692994","https://openalex.org/W6949433589","https://openalex.org/W6963154644","https://openalex.org/W6967349063"],"related_works":[],"abstract_inverted_index":{"Emotions":[0],"are":[1],"fundamental":[2],"to":[3,57,145,177],"the":[4,112,178],"creation":[5,179],"and":[6,15,39,42,71,92,98,108,122,128,149,158,183],"perception":[7],"of":[8,73,85,88,147,180],"music":[9,74,185],"performances.":[10,95],"However,":[11],"achieving":[12],"human-like":[13],"expression":[14],"emotion":[16,99,106,154],"through":[17],"machine":[18],"learning":[19],"models":[20,130],"for":[21,37],"performance":[22,46,61,75,105,142,186],"rendering":[23],"remains":[24],"a":[25,34,81,103],"challenging":[26],"task.":[27],"In":[28],"this":[29],"work,":[30],"we":[31,79,101,156],"present":[32,157],"SyMuPe,":[33],"novel":[35],"framework":[36],"developing":[38],"training":[40],"affective":[41],"controllable":[43],"symbolic":[44],"piano":[45,104],"models.":[47],"Our":[48],"flagship":[49],"model,":[50],"PianoFlow,":[51],"uses":[52],"conditional":[53,119],"flow":[54],"matching":[55],"trained":[56],"solve":[58],"diverse":[59],"multi-mask":[60],"inpainting":[62],"tasks.":[63],"By":[64],"design,":[65],"it":[66],"supports":[67],"both":[68],"unconditional":[69],"generation":[70],"infilling":[72],"features.":[76],"For":[77,96,153],"training,":[78],"use":[80],"curated,":[82],"cleaned":[83],"dataset":[84],"2,968":[86],"hours":[87],"aligned":[89],"musical":[90],"scores":[91],"expressive":[93],"MIDI":[94,151],"text":[97,115,164],"control,":[100,155],"integrate":[102],"classifier":[107],"tune":[109],"PianoFlow":[110,133],"with":[111],"emotion-weighted":[113],"Flan-T5":[114],"embeddings":[116],"provided":[117],"as":[118],"inputs.":[120],"Objective":[121],"subjective":[123],"evaluations":[124],"against":[125],"transformer-based":[126],"baselines":[127],"existing":[129],"show":[131],"that":[132,146],"not":[134],"only":[135],"outperforms":[136],"other":[137],"approaches,":[138],"but":[139],"also":[140],"achieves":[141],"quality":[143],"comparable":[144],"human-recorded":[148],"transcribed":[150],"samples.":[152],"analyze":[159],"samples":[160],"generated":[161],"under":[162],"different":[163],"conditioning":[165],"scenarios.":[166],"The":[167],"developed":[168],"model":[169],"can":[170],"be":[171],"integrated":[172],"into":[173],"interactive":[174],"applications,":[175],"contributing":[176],"more":[181],"accessible":[182],"engaging":[184],"systems.":[187]},"counts_by_year":[],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-25T00:00:00"}
