{"id":"https://openalex.org/W7108629641","doi":"https://doi.org/10.5281/zenodo.17811447","title":"MIDI-VALLE: Improving Expressive Piano Performance Synthesis Through Neural Codec Language Modelling","display_name":"MIDI-VALLE: Improving Expressive Piano Performance Synthesis Through Neural Codec Language Modelling","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7108629641","doi":"https://doi.org/10.5281/zenodo.17811447"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.17811447","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811447","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.17811447","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jingjing Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jingjing Tang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xin Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhe Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhe Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Junichi Yamagish","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junichi Yamagish","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Geraint Wiggins","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Geraint Wiggins","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"George Fazekas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"George Fazekas","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"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":0.59753471,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.5709999799728394,"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":0.5709999799728394,"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":0.37040001153945923,"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":0.016200000420212746,"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":0.9776999950408936},{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.8614000082015991},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.616100013256073},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5432999730110168},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.4352000057697296},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3596000075340271}],"concepts":[{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.9776999950408936},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.8614000082015991},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7547000050544739},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.616100013256073},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.609000027179718},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5432999730110168},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.4352000057697296},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3596000075340271},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C196754913","wikidata":"https://www.wikidata.org/wiki/Q27333678","display_name":"Music technology","level":3,"score":0.2644999921321869},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26260000467300415},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2619999945163727}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.17811447","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811447","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":""}],"best_oa_location":{"id":"doi:10.5281/zenodo.17811447","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811447","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"sustainable_development_goals":[{"score":0.43537554144859314,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generating":[0],"expressive":[1,28],"audio":[2,96,117],"performances":[3],"from":[4,31,69],"music":[5,18],"scores":[6],"requires":[7],"models":[8],"to":[9,45,91,180],"capture":[10],"both":[11,114],"instrument":[12],"acoustics":[13],"and":[14,53,98,116,125,143,168,189],"human":[15],"interpretation.":[16],"Traditional":[17],"performance":[19,29,84,97,146,193],"synthesis":[20,187],"pipelines":[21],"follow":[22],"a":[23,32,63,94,122,155],"two-stage":[24],"approach,":[25],"first":[26],"generating":[27],"MIDI":[30,37,49,101,115,194],"score,":[33],"then":[34],"synthesising":[35],"the":[36,70,89,132,166,172,183],"into":[38],"audio.":[39],"However,":[40],"these":[41,58],"systems":[42,106],"often":[43],"struggle":[44],"generalise":[46],"across":[47,191],"diverse":[48,144,192],"sources,":[50],"musical":[51],"styles,":[52],"recording":[54],"environments.":[55],"To":[56],"address":[57],"challenges,":[59],"we":[60,87],"propose":[61],"MIDI-VALLE,":[62],"neural":[64],"codec":[65],"language":[66],"model":[67],"adapted":[68],"VALLE":[71],"framework,":[72],"which":[73],"was":[74],"originally":[75],"designed":[76],"for":[77,182],"zero-shot":[78],"personalised":[79],"text-to-speech":[80],"(TTS)":[81],"synthesis.":[82],"For":[83],"MIDI-to-audio":[85],"synthesis,":[86],"improve":[88],"architecture":[90],"condition":[92],"on":[93,109,140,165],"reference":[95],"its":[99],"corresponding":[100],"representation.":[102],"Unlike":[103],"previous":[104],"TTS-based":[105],"that":[107,151],"rely":[108],"piano":[110,129,145],"rolls,":[111],"MIDI-VALLE":[112,152,175],"encodes":[113],"as":[118],"discrete":[119],"tokens,":[120],"facilitating":[121],"more":[123],"consistent":[124],"robust":[126],"modelling":[127],"of":[128],"performances.":[130],"Furthermore,":[131],"model's":[133],"generalisation":[134,190],"ability":[135],"is":[136],"enhanced":[137],"by":[138],"training":[139],"an":[141],"extensive":[142],"dataset.":[147],"Evaluation":[148],"results":[149],"show":[150],"significantly":[153],"outperforms":[154],"state-of-the-art":[156],"baseline,":[157,184],"achieving":[158],"over":[159],"75%":[160],"lower":[161],"Fr\u00e9chet":[162],"Audio":[163],"Distance":[164],"ATEPP":[167],"Maestro":[169],"datasets.":[170],"In":[171],"listening":[173],"test,":[174],"received":[176],"202":[177],"votes":[178],"compared":[179],"58":[181],"demonstrating":[185],"improved":[186],"quality":[188],"inputs.":[195]},"counts_by_year":[],"updated_date":"2025-12-05T23:25:22.460635","created_date":"2025-12-05T00:00:00"}