{"id":"https://openalex.org/W6968019254","doi":"https://doi.org/10.5281/zenodo.14877437","title":"Combining Audio Control and Style Transfer Using Latent Diffusion","display_name":"Combining Audio Control and Style Transfer Using Latent Diffusion","publication_year":2024,"publication_date":"2024-11-10","ids":{"openalex":"https://openalex.org/W6968019254","doi":"https://doi.org/10.5281/zenodo.14877437"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14877437","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877437","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.14877437","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Nils Demerl\u00e9","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nils Demerl\u00e9","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Philippe Esling","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Philippe Esling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Guillaume Doras","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guillaume Doras","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"David Genova","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Genova","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":0.44316091,"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/T11309","display_name":"Music and Audio Processing","score":0.3779999911785126,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.3779999911785126,"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":0.2603999972343445,"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":0.20440000295639038,"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/timbre","display_name":"Timbre","score":0.8364999890327454},{"id":"https://openalex.org/keywords/melody","display_name":"Melody","score":0.650600016117096},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5546000003814697},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5134999752044678},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4909000098705292},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4708000123500824},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.4140999913215637},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.39430001378059387},{"id":"https://openalex.org/keywords/sound-recording-and-reproduction","display_name":"Sound recording and reproduction","score":0.3727000057697296}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.8364999890327454},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7504000067710876},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.650600016117096},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6241000294685364},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5546000003814697},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5134999752044678},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4909000098705292},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4708000123500824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4480000138282776},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.4140999913215637},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.39430001378059387},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.3727000057697296},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3677999973297119},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.3668999969959259},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3619999885559082},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.3334999978542328},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.33309999108314514},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28040000796318054},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C194147245","wikidata":"https://www.wikidata.org/wiki/Q1076368","display_name":"Chord (peer-to-peer)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.27000001072883606},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.26030001044273376},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14877437","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877437","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.14877437","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877437","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":[{"display_name":"Reduced inequalities","score":0.4145399034023285,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deep":[0],"generative":[1],"models":[2],"are":[3,41],"now":[4],"able":[5],"to":[6,21,45,58,75,92,98,189],"synthesize":[7],"high-quality":[8],"audio":[9,19,123,138,164,195],"signals,":[10],"shifting":[11],"the":[12,32,47,87,190],"critical":[13],"aspect":[14],"in":[15,96,161,196],"their":[16],"development":[17],"from":[18],"quality":[20,165],"control":[22,36,61],"capabilities.":[23],"Although":[24],"text-to-music":[25],"generation":[26],"is":[27],"getting":[28],"largely":[29],"adopted":[30],"by":[31,69,183],"general":[33],"public,":[34],"explicit":[35,60,133],"and":[37,51,62,72,79,113,148,154,166,186],"example-based":[38],"style":[39,63,191],"transfer":[40,64,147],"more":[42],"adequate":[43],"modalities":[44],"capture":[46,76],"intents":[48],"of":[49,89,163,179,192],"artists":[50],"musicians.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56,85,157,170],"aim":[57],"unify":[59],"within":[65],"a":[66,114,125,193,197],"single":[67],"model":[68,120,143],"separating":[70],"local":[71],"global":[73],"information":[74],"musical":[77,181],"structure":[78,130],"timbre":[80,126,146],"respectively.":[81],"To":[82],"do":[83],"so,":[84],"leverage":[86],"capabilities":[88],"diffusion":[90],"autoencoders":[91],"extract":[93],"semantic":[94],"features,":[95],"order":[97],"build":[99],"two":[100],"representation":[101],"spaces.":[102],"We":[103,140],"enforce":[104],"disentanglement":[105],"between":[106],"those":[107],"spaces":[108],"using":[109],"an":[110],"adversarial":[111],"criterion":[112],"two-stage":[115],"training":[116],"strategy.":[117],"Our":[118],"resulting":[119],"can":[121,175],"generate":[122,176],"matching":[124],"target,":[127],"while":[128],"specifying":[129],"either":[131],"with":[132],"controls":[134],"or":[135],"through":[136],"another":[137],"example.":[139],"evaluate":[141],"our":[142,173],"on":[144,151],"one-shot":[145],"MIDI-to-audio":[149],"tasks":[150],"instrumental":[152],"recordings":[153],"show":[155,171],"that":[156,172],"outperform":[158],"existing":[159],"baselines":[160],"terms":[162],"target":[167,194],"fidelity.":[168],"Furthermore,":[169],"method":[174],"cover":[177],"versions":[178],"complete":[180],"pieces":[182],"transferring":[184],"rhythmic":[185],"melodic":[187],"content":[188],"different":[198],"genre.":[199]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}