{"id":"https://openalex.org/W4400579233","doi":"https://doi.org/10.1109/taslp.2024.3426987","title":"Latent Space Interpolation of Synthesizer Parameters Using Timbre-Regularized Auto-Encoders","display_name":"Latent Space Interpolation of Synthesizer Parameters Using Timbre-Regularized Auto-Encoders","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4400579233","doi":"https://doi.org/10.1109/taslp.2024.3426987"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3426987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3426987","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://orbi.umons.ac.be/bitstream/20.500.12907/49507/1/taslp24_accepted.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056151896","display_name":"Gwendal Le Vaillant","orcid":"https://orcid.org/0000-0002-0299-9351"},"institutions":[{"id":"https://openalex.org/I130929987","display_name":"University of Mons","ror":"https://ror.org/02qnnz951","country_code":"BE","type":"education","lineage":["https://openalex.org/I130929987"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Gwendal Le Vaillant","raw_affiliation_strings":["Information, Signal and Artificial Intelligence Lab, University of Mons, Mons, Belgium"],"affiliations":[{"raw_affiliation_string":"Information, Signal and Artificial Intelligence Lab, University of Mons, Mons, Belgium","institution_ids":["https://openalex.org/I130929987"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088316535","display_name":"Thierry Dutoit","orcid":"https://orcid.org/0000-0001-9461-9215"},"institutions":[{"id":"https://openalex.org/I130929987","display_name":"University of Mons","ror":"https://ror.org/02qnnz951","country_code":"BE","type":"education","lineage":["https://openalex.org/I130929987"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Thierry Dutoit","raw_affiliation_strings":["Information, Signal and Artificial Intelligence Lab, University of Mons, Mons, Belgium"],"affiliations":[{"raw_affiliation_string":"Information, Signal and Artificial Intelligence Lab, University of Mons, Mons, Belgium","institution_ids":["https://openalex.org/I130929987"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5056151896"],"corresponding_institution_ids":["https://openalex.org/I130929987"],"apc_list":null,"apc_paid":null,"fwci":0.512,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.60556874,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"32","issue":null,"first_page":"3379","last_page":"3392"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9463000297546387,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9463000297546387,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T11034","display_name":"Digital Filter Design and Implementation","score":0.9132999777793884,"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/T10320","display_name":"Neural Networks and Applications","score":0.9115999937057495,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.669570803642273},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.6634109020233154},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5401962399482727},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5056443214416504},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48382845520973206},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.41189587116241455},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3235604166984558},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32168078422546387},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.05512791872024536}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.669570803642273},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.6634109020233154},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5401962399482727},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5056443214416504},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48382845520973206},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.41189587116241455},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3235604166984558},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32168078422546387},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.05512791872024536},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2024.3426987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3426987","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:orbi.umons.ac.be:20.500.12907/49507","is_oa":true,"landing_page_url":"https://orbi.umons.ac.be/handle/20.500.12907/49507","pdf_url":"https://orbi.umons.ac.be/bitstream/20.500.12907/49507/1/taslp24_accepted.pdf","source":{"id":"https://openalex.org/S7407055454","display_name":"ORBi UMONS","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech and Language Processing, 32, 3379 - 3392 (2024)","raw_type":"peer reviewed"}],"best_oa_location":{"id":"pmh:oai:orbi.umons.ac.be:20.500.12907/49507","is_oa":true,"landing_page_url":"https://orbi.umons.ac.be/handle/20.500.12907/49507","pdf_url":"https://orbi.umons.ac.be/bitstream/20.500.12907/49507/1/taslp24_accepted.pdf","source":{"id":"https://openalex.org/S7407055454","display_name":"ORBi UMONS","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech and Language Processing, 32, 3379 - 3392 (2024)","raw_type":"peer reviewed"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400579233.pdf","grobid_xml":"https://content.openalex.org/works/W4400579233.grobid-xml"},"referenced_works_count":80,"referenced_works":["https://openalex.org/W171274525","https://openalex.org/W234667439","https://openalex.org/W1566660863","https://openalex.org/W1583791393","https://openalex.org/W1966135023","https://openalex.org/W1966365432","https://openalex.org/W1986595194","https://openalex.org/W1990611383","https://openalex.org/W1999188026","https://openalex.org/W2002318609","https://openalex.org/W2007752977","https://openalex.org/W2008066450","https://openalex.org/W2020883660","https://openalex.org/W2064675550","https://openalex.org/W2076608692","https://openalex.org/W2108469791","https://openalex.org/W2108708552","https://openalex.org/W2120847449","https://openalex.org/W2133239587","https://openalex.org/W2140356304","https://openalex.org/W2146007250","https://openalex.org/W2150307531","https://openalex.org/W2193399897","https://openalex.org/W2255834243","https://openalex.org/W2328848613","https://openalex.org/W2515020857","https://openalex.org/W2791716806","https://openalex.org/W2944683144","https://openalex.org/W2962721334","https://openalex.org/W2977735357","https://openalex.org/W2998588915","https://openalex.org/W3014271217","https://openalex.org/W3015625764","https://openalex.org/W3048062783","https://openalex.org/W3122300013","https://openalex.org/W3135377667","https://openalex.org/W3149069044","https://openalex.org/W3153832461","https://openalex.org/W3158390048","https://openalex.org/W3160669408","https://openalex.org/W3162289111","https://openalex.org/W3163547199","https://openalex.org/W4200561583","https://openalex.org/W4285367200","https://openalex.org/W4285606794","https://openalex.org/W4307977691","https://openalex.org/W4309117899","https://openalex.org/W4316660651","https://openalex.org/W4372260290","https://openalex.org/W4372266552","https://openalex.org/W4375869093","https://openalex.org/W6631848007","https://openalex.org/W6633727632","https://openalex.org/W6633849734","https://openalex.org/W6635136107","https://openalex.org/W6640963894","https://openalex.org/W6687738023","https://openalex.org/W6690496053","https://openalex.org/W6711609916","https://openalex.org/W6712929052","https://openalex.org/W6714644935","https://openalex.org/W6732492507","https://openalex.org/W6733471323","https://openalex.org/W6736723571","https://openalex.org/W6739901393","https://openalex.org/W6744627333","https://openalex.org/W6752996073","https://openalex.org/W6753934646","https://openalex.org/W6771689491","https://openalex.org/W6771719626","https://openalex.org/W6771763809","https://openalex.org/W6779490555","https://openalex.org/W6779837268","https://openalex.org/W6791353385","https://openalex.org/W6793276785","https://openalex.org/W6799235175","https://openalex.org/W6803922201","https://openalex.org/W6842676699","https://openalex.org/W6842893850","https://openalex.org/W6931359900"],"related_works":["https://openalex.org/W2406877384","https://openalex.org/W2595839522","https://openalex.org/W3109975354","https://openalex.org/W2124576126","https://openalex.org/W2138455584","https://openalex.org/W1984264321","https://openalex.org/W2357614930","https://openalex.org/W2008642382","https://openalex.org/W1541822869","https://openalex.org/W2037604299"],"abstract_inverted_index":{"Sound":[0],"synthesizers":[1],"are":[2],"ubiquitous":[3],"in":[4],"modern":[5],"music":[6],"production":[7],"but":[8],"manipulating":[9],"their":[10],"presets,":[11,76],"i.e.":[12],"the":[13,37,50,121],"sets":[14],"of":[15,40,56,103,139],"synthesis":[16,57],"parameters,":[17,58],"demands":[18],"expert":[19],"skills.":[20],"This":[21],"study":[22],"presents":[23],"a":[24,100,130,136],"novel":[25],"variational":[26],"auto-encoder":[27],"model":[28,51,126],"tailored":[29],"for":[30],"black-box":[31],"synthesizer":[32,134],"preset":[33],"interpolation,":[34],"which":[35],"enables":[36],"intuitive":[38],"generation":[39],"new":[41],"presets":[42],"from":[43],"pre-existing":[44],"ones.":[45],"Leveraging":[46],"multi-head":[47],"self-attention":[48],"networks,":[49],"efficiently":[52],"learns":[53],"latent":[54],"representations":[55],"aligning":[59],"these":[60],"with":[61,120,135],"perceived":[62],"timbre":[63],"dimensions":[64],"through":[65,111],"attribute-based":[66],"regularization.":[67],"It":[68,142],"is":[69,109,127],"able":[70],"to":[71,146],"gradually":[72],"transition":[73],"between":[74],"diverse":[75],"surpassing":[77],"traditional":[78],"linear":[79],"parametric":[80],"interpolation":[81],"methods.":[82],"Furthermore,":[83],"we":[84],"introduce":[85],"an":[86],"objective":[87,123],"and":[88,95,150,158],"reproducible":[89],"evaluation":[90],"method,":[91],"based":[92],"on":[93,99],"linearity":[94],"smoothness":[96],"metrics":[97],"computed":[98],"broad":[101],"set":[102,138],"audio":[104],"features.":[105],"The":[106,125],"model's":[107],"efficacy":[108],"demonstrated":[110],"subjective":[112],"experiments,":[113],"whose":[114],"results":[115],"also":[116],"highlight":[117],"significant":[118],"correlations":[119],"proposed":[122],"metrics.":[124],"validated":[128],"using":[129],"widespread":[131],"frequency":[132],"modulation":[133],"large":[137],"interdependent":[140],"parameters.":[141],"can":[143,151],"be":[144],"adapted":[145],"various":[147],"commercial":[148],"synthesizers,":[149],"perform":[152],"other":[153],"tasks":[154],"such":[155],"as":[156],"modulations":[157],"extrapolations.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}