{"id":"https://openalex.org/W4372260290","doi":"https://doi.org/10.1109/icassp49357.2023.10096397","title":"Synthesizer Preset Interpolation Using Transformer Auto-Encoders","display_name":"Synthesizer Preset Interpolation Using Transformer Auto-Encoders","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260290","doi":"https://doi.org/10.1109/icassp49357.2023.10096397"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096397","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096397","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://orbi.umons.ac.be/bitstream/20.500.12907/46096/1/2023050993.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":["University of Mons,Information, Signal and Artificial Intelligence (ISIA),Belgium","HE2B-ISIB Research Institute, Brussels, Belgium","Information, Signal and Artificial Intelligence (ISIA), University of Mons, Belgium"],"affiliations":[{"raw_affiliation_string":"University of Mons,Information, Signal and Artificial Intelligence (ISIA),Belgium","institution_ids":["https://openalex.org/I130929987"]},{"raw_affiliation_string":"HE2B-ISIB Research Institute, Brussels, Belgium","institution_ids":[]},{"raw_affiliation_string":"Information, Signal and Artificial Intelligence (ISIA), University of Mons, Belgium","institution_ids":["https://openalex.org/I130929987"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042439255","display_name":"Thierry Dutoit","orcid":"https://orcid.org/0000-0001-7024-2150"},"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":["University of Mons,Information, Signal and Artificial Intelligence (ISIA),Belgium","Information, Signal and Artificial Intelligence (ISIA), University of Mons, Belgium"],"affiliations":[{"raw_affiliation_string":"University of Mons,Information, Signal and Artificial Intelligence (ISIA),Belgium","institution_ids":["https://openalex.org/I130929987"]},{"raw_affiliation_string":"Information, Signal and Artificial Intelligence (ISIA), University of 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":0.4048,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54199703,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"10","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9988999962806702,"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/computer-science","display_name":"Computer science","score":0.742370069026947},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.6458219289779663},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6206218004226685},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5854432582855225},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45106178522109985},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43556317687034607},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3131840229034424},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15439528226852417},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.10041797161102295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.742370069026947},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.6458219289779663},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6206218004226685},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5854432582855225},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45106178522109985},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43556317687034607},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3131840229034424},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15439528226852417},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.10041797161102295},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/icassp49357.2023.10096397","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096397","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:orbi.umons.ac.be:20.500.12907/46096","is_oa":true,"landing_page_url":"https://orbi.umons.ac.be/handle/20.500.12907/46096","pdf_url":"https://orbi.umons.ac.be/bitstream/20.500.12907/46096/1/2023050993.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":"ICASSP 2023 Proceedings (2023-06-04); ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes, Greece [GR], 4-10 June 2023","raw_type":"peer reviewed"}],"best_oa_location":{"id":"pmh:oai:orbi.umons.ac.be:20.500.12907/46096","is_oa":true,"landing_page_url":"https://orbi.umons.ac.be/handle/20.500.12907/46096","pdf_url":"https://orbi.umons.ac.be/bitstream/20.500.12907/46096/1/2023050993.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":"ICASSP 2023 Proceedings (2023-06-04); ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes, Greece [GR], 4-10 June 2023","raw_type":"peer reviewed"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4372260290.pdf","grobid_xml":"https://content.openalex.org/works/W4372260290.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2008066450","https://openalex.org/W2064675550","https://openalex.org/W2606176153","https://openalex.org/W2753738274","https://openalex.org/W2791716806","https://openalex.org/W2964122153","https://openalex.org/W2977735357","https://openalex.org/W2998588915","https://openalex.org/W3000389243","https://openalex.org/W3014271217","https://openalex.org/W3015625764","https://openalex.org/W3149069044","https://openalex.org/W3153832461","https://openalex.org/W3158390048","https://openalex.org/W4285367200","https://openalex.org/W4285606794","https://openalex.org/W4289751869","https://openalex.org/W4291960990","https://openalex.org/W4385245566","https://openalex.org/W6640963894","https://openalex.org/W6732492507","https://openalex.org/W6736723571","https://openalex.org/W6739901393","https://openalex.org/W6744627333","https://openalex.org/W6753934646","https://openalex.org/W6771763809","https://openalex.org/W6772588809","https://openalex.org/W6842676699"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W4205302943","https://openalex.org/W2561132942","https://openalex.org/W3155418658","https://openalex.org/W4243199227","https://openalex.org/W2379948177","https://openalex.org/W2119949815"],"abstract_inverted_index":{"Sound":[0],"synthesizers":[1,107],"are":[2],"widespread":[3],"in":[4],"modern":[5],"music":[6],"production":[7],"but":[8],"they":[9],"increasingly":[10],"require":[11],"expert":[12],"skills":[13],"to":[14,33,84],"be":[15,103],"mastered.":[16],"This":[17,62],"work":[18],"focuses":[19],"on":[20,67],"interpolation":[21,110],"between":[22],"presets,":[23],"i.e.,":[24],"sets":[25],"of":[26,28,38],"values":[27],"all":[29],"sound":[30,112],"synthesis":[31],"parameters,":[32],"enable":[34],"the":[35,82,99],"intuitive":[36],"creation":[37],"new":[39],"sounds":[40],"from":[41],"existing":[42],"ones.We":[43],"introduce":[44],"a":[45,68],"bimodal":[46],"auto-encoder":[47],"neural":[48],"network,":[49],"which":[50],"simultaneously":[51],"processes":[52],"presets":[53],"using":[54,60],"multi-head":[55],"attention":[56],"blocks,":[57],"and":[58,87,89],"audio":[59],"convolutions.":[61],"model":[63,83,101],"has":[64],"been":[65],"tested":[66],"popular":[69],"frequency":[70],"modulation":[71],"synthesizer":[72],"with":[73],"more":[74],"than":[75],"one":[76],"hundred":[77],"parameters.":[78],"Experiments":[79],"have":[80,90],"compared":[81],"related":[85],"architectures":[86],"methods,":[88],"demonstrated":[91],"that":[92],"it":[93],"performs":[94],"smoother":[95],"interpolations.":[96],"After":[97],"training,":[98],"proposed":[100],"can":[102],"integrated":[104],"into":[105],"commercial":[106],"for":[108],"live":[109],"or":[111],"design":[113],"tasks.":[114]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}
