{"id":"https://openalex.org/W7108732427","doi":"https://doi.org/10.5281/zenodo.17811548","title":"Conditional Diffusion as Latent Constraints for Controllable Symbolic Music Generation","display_name":"Conditional Diffusion as Latent Constraints for Controllable Symbolic Music Generation","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7108732427","doi":"https://doi.org/10.5281/zenodo.17811548"},"language":"en","primary_location":{"id":"pmh:oai:re.public.polimi.it:11311/1311936","is_oa":true,"landing_page_url":"https://zenodo.org/records/17811548","pdf_url":"https://zenodo.org/records/17811548/files/000006.pdf","source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"type":"conference-paper","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/records/17811548/files/000006.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Matteo Petten\u00f2","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matteo Petten\u00f2","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Alessandro Mezza","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alessandro Mezza","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Alberto Bernardini","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alberto Bernardini","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":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.52216852,"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":0.621399998664856,"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":0.621399998664856,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.1429000049829483,"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":0.06880000233650208,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5529000163078308},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5436999797821045},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4677000045776367},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.41909998655319214},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.38350000977516174},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.350600004196167},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.3483000099658966},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.3037000000476837}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6686000227928162},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5529000163078308},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5436999797821045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5005999803543091},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4677000045776367},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.41909998655319214},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4025000035762787},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.38350000977516174},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.350600004196167},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.3483000099658966},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.28870001435279846},{"id":"https://openalex.org/C101721835","wikidata":"https://www.wikidata.org/wiki/Q813908","display_name":"Conditional entropy","level":3,"score":0.288100004196167},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:re.public.polimi.it:11311/1311936","is_oa":true,"landing_page_url":"https://zenodo.org/records/17811548","pdf_url":"https://zenodo.org/records/17811548/files/000006.pdf","source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.5281/zenodo.17811548","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811548","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":"pmh:oai:re.public.polimi.it:11311/1311936","is_oa":true,"landing_page_url":"https://zenodo.org/records/17811548","pdf_url":"https://zenodo.org/records/17811548/files/000006.pdf","source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7108732427.pdf","grobid_xml":"https://content.openalex.org/works/W7108732427.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"explore":[1],"the":[2,53,59,100,118,124,128],"application":[3],"of":[4,56,74,89,102,120,130,138],"denoising":[5],"diffusion":[6,22,92],"processes":[7],"as":[8,52,95,142],"plug-and-play":[9],"latent":[10,21,163],"constraints":[11,156,164],"for":[12,67],"unconditional":[13,105],"symbolic":[14],"music":[15],"generation":[16],"models.":[17],"Recent":[18],"advances":[19],"in":[20,28],"models":[23,93],"have":[24,110],"demonstrated":[25],"state-of-the-art":[26],"performance":[27],"high-dimensional":[29],"time-series":[30],"data":[31],"synthesis":[32],"while":[33,175],"providing":[34],"flexible":[35],"control":[36],"through":[37],"conditioning":[38],"and":[39,148,161,172,180],"guidance.":[40],"However,":[41],"existing":[42],"methodologies":[43],"primarily":[44],"rely":[45],"on":[46,83,99],"musical":[47,76,139],"context":[48],"or":[49],"natural":[50],"language":[51],"main":[54],"modality":[55],"interacting":[57],"with":[58],"generative":[60],"process,":[61],"which":[62],"may":[63],"not":[64],"be":[65],"ideal":[66],"expert":[68],"users":[69],"seeking":[70],"precise":[71],"fader-like":[72],"manipulation":[73],"specific":[75],"attributes.":[77],"In":[78],"this":[79,115],"work,":[80,116],"we":[81],"focus":[82],"a":[84,87,103,135],"framework":[85],"leveraging":[86],"library":[88],"small":[90],"conditional":[91],"operating":[94],"implicit":[96],"probabilistic":[97],"priors":[98],"latents":[101],"frozen":[104],"backbone.":[106],"While":[107],"previous":[108],"studies":[109],"explored":[111],"domain-specific":[112],"use":[113],"cases,":[114],"to":[117,126],"best":[119],"our":[121],"knowledge,":[122],"is":[123],"first":[125],"demonstrate":[127],"versatility":[129],"such":[131,141],"an":[132],"approach":[133],"across":[134],"diverse":[136],"array":[137],"attributes,":[140],"note":[143],"density,":[144],"pitch":[145],"range,":[146],"contour,":[147],"rhythm":[149],"complexity.":[150],"Our":[151],"experiments":[152],"show":[153],"that":[154],"diffusion-driven":[155],"outperform":[157],"traditional":[158],"attribute":[159],"regularization":[160],"other":[162],"architectures,":[165],"achieving":[166],"significantly":[167],"stronger":[168],"correlations":[169],"between":[170],"target":[171],"generated":[173],"attributes":[174],"maintaining":[176],"high":[177],"perceptual":[178],"quality":[179],"diversity.":[181]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-12-05T00:00:00"}