{"id":"https://openalex.org/W6893264821","doi":"https://doi.org/10.5281/zenodo.14877495","title":"PerTok: Expressive Encoding and Modeling of Symbolic Musical Ideas and Variations","display_name":"PerTok: Expressive Encoding and Modeling of Symbolic Musical Ideas and Variations","publication_year":2024,"publication_date":"2024-11-10","ids":{"openalex":"https://openalex.org/W6893264821","doi":"https://doi.org/10.5281/zenodo.14877495"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14877495","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877495","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":"ConferencePaper"},"type":"conference-paper","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.14877495","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Julian Lenz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Julian Lenz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Anirudh Mani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anirudh Mani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.41013849,"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":true,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.6675999760627747,"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":0.6675999760627747,"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":0.10270000249147415,"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":0.08550000190734863,"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":0.736299991607666},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5138999819755554},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.5030999779701233},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.44609999656677246},{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.4327999949455261},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.42410001158714294},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.41040000319480896},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.3725999891757965}],"concepts":[{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.736299991607666},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6926000118255615},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5138999819755554},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5091999769210815},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.5030999779701233},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.44609999656677246},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.4327999949455261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4325000047683716},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.42410001158714294},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.41040000319480896},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3725999891757965},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.37059998512268066},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3571000099182129},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.3495999872684479},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3285999894142151},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3183000087738037},{"id":"https://openalex.org/C109568592","wikidata":"https://www.wikidata.org/wiki/Q207628","display_name":"Musical composition","level":3,"score":0.3066999912261963},{"id":"https://openalex.org/C88639978","wikidata":"https://www.wikidata.org/wiki/Q233861","display_name":"Musical notation","level":3,"score":0.3066999912261963},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.2540000081062317},{"id":"https://openalex.org/C4069607","wikidata":"https://www.wikidata.org/wiki/Q868732","display_name":"Aliasing","level":3,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14877495","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877495","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":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.5281/zenodo.14877495","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877495","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":"ConferencePaper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"introduce":[1],"Cadenza,":[2],"a":[3,26,75,107],"new":[4],"multi-stage":[5],"generative":[6],"framework":[7,60,168],"for":[8,52,181],"predicting":[9],"expressive":[10,37,150],"variations":[11],"of":[12,62,98,177],"symbolic":[13,137],"musical":[14,101,140],"ideas":[15,151,163],"as":[16,18],"well":[17],"unconditional":[19,135],"generations.":[20],"To":[21],"accomplish":[22],"this":[23],"we":[24],"propose":[25],"novel":[27,162],"MIDI":[28,121],"encoding":[29],"method,":[30],"PerTok":[31],"(Performance":[32],"Tokenizer)":[33],"that":[34,111,152],"captures":[35],"minute":[36],"details":[38],"whilst":[39,142,160],"reducing":[40],"sequence":[41],"length":[42],"up":[43,49],"to":[44,50,91,115,157,164],"59%":[45],"and":[46,55,68,86,118,124,146,172],"vocabulary":[47],"size":[48],"95%":[51],"polyphonic,":[53],"monophonic":[54],"rhythmic":[56],"tasks.":[57],"The":[58,71,103],"proposed":[59],"comprises":[61],"two":[63],"sequential":[64],"stages:":[65],"1)":[66,132],"Composer":[67,72],"2)":[69,147],"Performer.":[70],"model":[73,105],"is":[74,106,112,169],"transformer-based":[76],"Variational":[77],"Autoencoder":[78],"(VAE),":[79],"with":[80,174],"Rotary":[81],"Positional":[82],"Embeddings":[83],"(RoPE)":[84],"[1]":[85],"an":[87],"autoregressive":[88],"decoder":[89],"modified":[90],"more":[92,144],"effectively":[93],"integrate":[94],"the":[95,99,158,165,175],"latent":[96],"codes":[97],"input":[100,159],"idea.":[102],"Performer":[104],"bidirectional":[108],"transformer":[109],"encoder":[110],"separately":[113],"trained":[114],"predict":[116],"velocities":[117],"microtimings":[119],"on":[120],"sequences.":[122],"Objective":[123],"human":[125],"evaluations":[126],"demonstrate":[127],"Cadenza's":[128],"versatile":[129],"capability":[130],"in":[131,139],"matching":[133],"other":[134],"state-of-the-art":[136],"models":[138],"quality":[141],"sounding":[143],"expressive,":[145],"composing":[148],"new,":[149],"are":[153],"both":[154],"stylistically":[155],"related":[156],"providing":[161,179],"user.":[166],"Our":[167],"designed,":[170],"researched":[171],"implemented":[173],"objective":[176],"ethically":[178],"inspiration":[180],"musicians.":[182]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}