{"id":"https://openalex.org/W4416756142","doi":"https://doi.org/10.1109/lsp.2025.3633579","title":"Velocity2DMs: A Contextual Modeling Approach to Dynamics Marking Prediction in Piano Performance","display_name":"Velocity2DMs: A Contextual Modeling Approach to Dynamics Marking Prediction in Piano Performance","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416756142","doi":"https://doi.org/10.1109/lsp.2025.3633579"},"language":null,"primary_location":{"id":"doi:10.1109/lsp.2025.3633579","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3633579","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/lsp.2025.3633579","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091266621","display_name":"Hyon Kim","orcid":"https://orcid.org/0000-0002-8202-9768"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Pompeu Fabra University","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Hyon Kim","raw_affiliation_strings":["Music Technology Group, Department of Information and Communication Technologies, Universitat Pompeu Fabra, Barcelona, Spain","Music Technology Group, Department of Information and Communication Technologies, Universit Pompeu Fabra, Spain"],"affiliations":[{"raw_affiliation_string":"Music Technology Group, Department of Information and Communication Technologies, Universitat Pompeu Fabra, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"Music Technology Group, Department of Information and Communication Technologies, Universit Pompeu Fabra, Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Emmanouil Benetos","orcid":"https://orcid.org/0000-0002-6820-6764"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emmanouil Benetos","raw_affiliation_strings":["Centre for Digital Music, School of Electronic Engineering and Computer Science, Queen Mary University of London, London, U.K","Centre for Digital Music, School of Electronic Engineering and Computer Science, Queen Mary University of London, U.K"],"affiliations":[{"raw_affiliation_string":"Centre for Digital Music, School of Electronic Engineering and Computer Science, Queen Mary University of London, London, U.K","institution_ids":[]},{"raw_affiliation_string":"Centre for Digital Music, School of Electronic Engineering and Computer Science, Queen Mary University of London, U.K","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006479715","display_name":"Xavier Serra","orcid":"https://orcid.org/0000-0003-1395-2345"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Pompeu Fabra University","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Xavier Serra","raw_affiliation_strings":["Music Technology Group, Department of Information and Communication Technologies, Universitat Pompeu Fabra, Barcelona, Spain","Music Technology Group, Department of Information and Communication Technologies, Universit Pompeu Fabra, Spain"],"affiliations":[{"raw_affiliation_string":"Music Technology Group, Department of Information and Communication Technologies, Universitat Pompeu Fabra, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"Music Technology Group, Department of Information and Communication Technologies, Universit Pompeu Fabra, Spain","institution_ids":["https://openalex.org/I170486558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5091266621"],"corresponding_institution_ids":["https://openalex.org/I170486558"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40386068,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"4459","last_page":"4463"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.5759999752044678,"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":0.5759999752044678,"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":0.16609999537467957,"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":0.15360000729560852,"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/midi","display_name":"MIDI","score":0.9365000128746033},{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.8306999802589417},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.6261000037193298},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.6212999820709229},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5407000184059143},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.43799999356269836},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41510000824928284}],"concepts":[{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.9365000128746033},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.8306999802589417},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7979999780654907},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.6261000037193298},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.6212999820709229},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5407000184059143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4867999851703644},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44769999384880066},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.43799999356269836},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41510000824928284},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.39410001039505005},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37560001015663147},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3188999891281128},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C71611378","wikidata":"https://www.wikidata.org/wiki/Q5165191","display_name":"Contextual design","level":3,"score":0.26969999074935913},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.2694999873638153},{"id":"https://openalex.org/C16101541","wikidata":"https://www.wikidata.org/wiki/Q1350838","display_name":"Symbolic dynamics","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2025.3633579","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3633579","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/lsp.2025.3633579","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3633579","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1993800166","https://openalex.org/W2042283011","https://openalex.org/W2592549691","https://openalex.org/W2810454758","https://openalex.org/W2995428882","https://openalex.org/W3092879656","https://openalex.org/W3123742938","https://openalex.org/W3162764010","https://openalex.org/W3173187964","https://openalex.org/W3175663427","https://openalex.org/W4293192967","https://openalex.org/W4382021246","https://openalex.org/W4392271377","https://openalex.org/W4393102125","https://openalex.org/W4415000648"],"related_works":[],"abstract_inverted_index":{"Expressive":[0],"dynamics":[1,117,139],"in":[2,31,140],"music":[3,155,161],"performance":[4,33,40,109,157],"are":[5,75],"subjective":[6,69],"and":[7,48,64,77,95,123,137,159],"context-dependent,":[8],"yet":[9],"most":[10],"symbolic":[11],"models":[12],"treat":[13],"Dynamics":[14],"Markings":[15],"(DMs)":[16],"as":[17],"static":[18],"with":[19,39],"fixed":[20],"MIDI":[21,41,62],"velocities.":[22],"This":[23,128],"paper":[24],"proposes":[25],"a":[26,44,80,141],"method":[27],"for":[28,68,153],"predicting":[29],"DMs":[30,97],"piano":[32],"by":[34],"combining":[35],"MusicXML":[36],"score":[37],"information":[38],"data":[42],"through":[43],"novel":[45],"tokenization":[46],"scheme":[47],"an":[49],"adapted":[50],"RoBERTa-based":[51],"Masked":[52],"Language":[53],"Model":[54],"(MLM).":[55],"Our":[56],"approach":[57],"focuses":[58],"on":[59],"contextual":[60,120,145],"aggregated":[61],"velocities":[63],"corresponding":[65],"DMs,":[66],"accounting":[67],"interpretations":[70],"of":[71,82],"pianists.":[72],"Note-level":[73],"features":[74],"serialized":[76],"translated":[78],"into":[79],"sequence":[81,146],"tokens":[83],"to":[84,133],"predict":[85],"both":[86,135],"constant":[87,126,136],"(e.g.,":[88,98],"<italic":[89,92,99,102],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[90,93,100,103],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">mp</i>,":[91],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">ff</i>)":[94],"non-constant":[96,138],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">crescendo</i>,":[101],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">fp</i>).":[104],"Evaluation":[105],"across":[106],"three":[107],"expert":[108],"datasets":[110],"shows":[111],"that":[112],"the":[113,130],"model":[114,134],"effectively":[115],"learns":[116],"transitions":[118],"from":[119],"note":[121],"blocks":[122],"generalizes":[124],"beyond":[125],"markings.":[127],"is":[129],"first":[131],"study":[132],"unified":[142],"framework":[143],"using":[144],"learning.":[147],"The":[148],"results":[149],"suggest":[150],"promising":[151],"applications":[152],"expressive":[154],"analysis,":[156],"modeling,":[158],"computer-assisted":[160],"education.":[162]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-17T00:00:00"}