{"id":"https://openalex.org/W3212416539","doi":"https://doi.org/10.1109/mlsp52302.2021.9596414","title":"Caesynth: Real-Time Timbre Interpolation and Pitch Control with Conditional Autoencoders","display_name":"Caesynth: Real-Time Timbre Interpolation and Pitch Control with Conditional Autoencoders","publication_year":2021,"publication_date":"2021-10-25","ids":{"openalex":"https://openalex.org/W3212416539","doi":"https://doi.org/10.1109/mlsp52302.2021.9596414","mag":"3212416539"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp52302.2021.9596414","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp52302.2021.9596414","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2111.05174","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064979071","display_name":"Aaron Valero Puche","orcid":"https://orcid.org/0009-0003-0777-9942"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Aaron Valero Puche","raw_affiliation_strings":["Artificial Intelligence School, Sungkyunkwan University, Suwon-si, Republic of Korea","Artificial Intelligence School, Sungkyunkwan University,Suwon-si,Republic of Korea,16419"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence School, Sungkyunkwan University, Suwon-si, Republic of Korea","institution_ids":["https://openalex.org/I848706"]},{"raw_affiliation_string":"Artificial Intelligence School, Sungkyunkwan University,Suwon-si,Republic of Korea,16419","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103020232","display_name":"Sukhan Lee","orcid":"https://orcid.org/0000-0002-1281-6889"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sukhan Lee","raw_affiliation_strings":["Artificial Intelligence School, Sungkyunkwan University, Suwon-si, Republic of Korea","Artificial Intelligence School, Sungkyunkwan University,Suwon-si,Republic of Korea,16419"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence School, Sungkyunkwan University, Suwon-si, Republic of Korea","institution_ids":["https://openalex.org/I848706"]},{"raw_affiliation_string":"Artificial Intelligence School, Sungkyunkwan University,Suwon-si,Republic of Korea,16419","institution_ids":["https://openalex.org/I848706"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5064979071"],"corresponding_institution_ids":["https://openalex.org/I848706"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14953521,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991999864578247,"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/T10860","display_name":"Speech and Audio Processing","score":0.998199999332428,"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/timbre","display_name":"Timbre","score":0.9357649683952332},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6998687386512756},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5749560594558716},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5401588082313538},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39208608865737915},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.18412140011787415},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.17885851860046387}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.9357649683952332},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6998687386512756},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5749560594558716},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5401588082313538},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39208608865737915},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.18412140011787415},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.17885851860046387},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/mlsp52302.2021.9596414","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp52302.2021.9596414","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2111.05174","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.05174","pdf_url":"https://arxiv.org/pdf/2111.05174","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3212416539","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2111.05174.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2111.05174","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2111.05174","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/njp7-s173","is_oa":true,"landing_page_url":"https://doi.org/10.17023/njp7-s173","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2111.05174","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.05174","pdf_url":"https://arxiv.org/pdf/2111.05174","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Life in Land","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/15"}],"awards":[{"id":"https://openalex.org/G2191473729","display_name":null,"funder_award_id":"2019-0-00421","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G4074280394","display_name":null,"funder_award_id":"IITP-2020-0-01821","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G5217505250","display_name":null,"funder_award_id":"2020-0-01821","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G5708442277","display_name":null,"funder_award_id":"IITP-2020-0-01821","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G6072120315","display_name":null,"funder_award_id":"funded","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G7685055460","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G8874964841","display_name":null,"funder_award_id":"2019-0-00421","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3212416539.pdf","grobid_xml":"https://content.openalex.org/works/W3212416539.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1710476689","https://openalex.org/W1922152898","https://openalex.org/W2187089797","https://openalex.org/W2191779130","https://openalex.org/W2475287302","https://openalex.org/W2584505851","https://openalex.org/W2766465839","https://openalex.org/W2898847420","https://openalex.org/W2910577860","https://openalex.org/W2915590429","https://openalex.org/W2938222313","https://openalex.org/W2949382160","https://openalex.org/W2951535099","https://openalex.org/W2962793481","https://openalex.org/W2963373786","https://openalex.org/W2963889406","https://openalex.org/W2989955315","https://openalex.org/W3003832272","https://openalex.org/W3090388844","https://openalex.org/W3094444047","https://openalex.org/W3095936335","https://openalex.org/W6718379498"],"related_works":["https://openalex.org/W2989955315","https://openalex.org/W3161927506","https://openalex.org/W2406877384","https://openalex.org/W2901739194","https://openalex.org/W3196700074","https://openalex.org/W2899775901","https://openalex.org/W3097059217","https://openalex.org/W2786220077","https://openalex.org/W1809214759","https://openalex.org/W3100781494","https://openalex.org/W3187921808","https://openalex.org/W49287718","https://openalex.org/W2030392454","https://openalex.org/W2962721334","https://openalex.org/W3160669408","https://openalex.org/W2100682932","https://openalex.org/W3186846710","https://openalex.org/W2778460379","https://openalex.org/W3111213250","https://openalex.org/W2051586096"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"a":[5,12,33,40],"novel":[6,98],"audio":[7,91,114,134],"synthesizer,":[8],"CAESynth,":[9],"based":[10,43,96],"on":[11,44,97],"conditional":[13,41],"autoencoder.":[14],"CAESynth":[15,109],"synthesizes":[16],"timbre":[17,47,57,69,99,119],"in":[18,25,46,59,93,116],"real-time":[19,117],"by":[20,106],"interpolating":[21],"the":[22],"reference":[23],"sounds":[24],"their":[26],"shared":[27,148],"latent":[28,60],"feature":[29],"space,":[30],"while":[31],"controlling":[32],"pitch":[34,54,72,125],"independently.":[35],"We":[36,104],"show":[37],"that":[38,108],"training":[39],"autoen-coder":[42],"accuracy":[45],"classification":[48],"together":[49],"with":[50,101,136,143],"adversarial":[51],"regularization":[52],"of":[53,83,90],"content":[55],"allows":[56],"distribution":[58],"space":[61],"to":[62,81,88],"be":[63],"more":[64],"effective":[65],"and":[66,71,112,121],"stable":[67],"for":[68,127,133],"interpolation":[70,120],"conditioning.":[73],"The":[74],"proposed":[75],"method":[76],"is":[77],"applicable":[78],"not":[79],"only":[80],"creation":[82],"musical":[84,128],"cues":[85,129],"but":[86],"also":[87],"exploration":[89],"affordance":[92,135],"mixed":[94],"reality":[95],"mixtures":[100],"environmental":[102,137],"sounds.":[103],"demonstrate":[105],"experiments":[107],"achieves":[110],"smooth":[111],"high-fidelity":[113],"synthesis":[115],"through":[118],"independent":[122],"yet":[123],"accurate":[124],"control":[126],"as":[130,132],"well":[131],"sound.":[138],"A":[139],"Python":[140],"implementation":[141],"along":[142],"some":[144],"generated":[145],"samples":[146],"are":[147],"online.":[149]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}