{"id":"https://openalex.org/W4406858748","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848699","title":"Wavetable Synthesis Using CVAE for Timbre Control Based on Semantic Label","display_name":"Wavetable Synthesis Using CVAE for Timbre Control Based on Semantic Label","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406858748","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848699"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10848699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114618248","display_name":"Tsugumasa Yutani","orcid":null},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Tsugumasa Yutani","raw_affiliation_strings":["University of Tsukuba,Tsukuba,Japan"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba,Tsukuba,Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101025232","display_name":"Yuya Yamamoto","orcid":null},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuya Yamamoto","raw_affiliation_strings":["University of Tsukuba,Tsukuba,Japan"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba,Tsukuba,Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040556492","display_name":"Shuyo Nakatani","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087174","display_name":"CYBO (Japan)","ror":"https://ror.org/003md6g43","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210087174"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shuyo Nakatani","raw_affiliation_strings":["Cybozu Labs,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Cybozu Labs,Tokyo,Japan","institution_ids":["https://openalex.org/I4210087174"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008403512","display_name":"Hiroko Terasawa","orcid":null},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroko Terasawa","raw_affiliation_strings":["University of Tsukuba,Tsukuba,Japan"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba,Tsukuba,Japan","institution_ids":["https://openalex.org/I146399215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5114618248"],"corresponding_institution_ids":["https://openalex.org/I146399215"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27331158,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9297999739646912,"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":0.9297999739646912,"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":0.7307723760604858},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.5518671274185181},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.43002861738204956},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42847511172294617},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4175992012023926},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3925560414791107}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7307723760604858},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.5518671274185181},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.43002861738204956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42847511172294617},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4175992012023926},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3925560414791107},{"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/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10848699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1995268113","https://openalex.org/W1998446618","https://openalex.org/W2018472963","https://openalex.org/W2073959870","https://openalex.org/W2079080230","https://openalex.org/W2100495367","https://openalex.org/W2122538988","https://openalex.org/W2162531249","https://openalex.org/W2194775991","https://openalex.org/W2404664354","https://openalex.org/W2471230781","https://openalex.org/W2924334974","https://openalex.org/W2998588915","https://openalex.org/W3160669408","https://openalex.org/W3207866885","https://openalex.org/W4281287975","https://openalex.org/W4324290832","https://openalex.org/W4381516725","https://openalex.org/W6602049110","https://openalex.org/W6610798393","https://openalex.org/W6631190155","https://openalex.org/W6633700168","https://openalex.org/W6640963894","https://openalex.org/W6734126215","https://openalex.org/W6736723571","https://openalex.org/W6739139180","https://openalex.org/W6744627333","https://openalex.org/W6758675244","https://openalex.org/W6803922201","https://openalex.org/W6811204662","https://openalex.org/W6931359900","https://openalex.org/W7062442193"],"related_works":["https://openalex.org/W2406877384","https://openalex.org/W2595839522","https://openalex.org/W2124576126","https://openalex.org/W2138455584","https://openalex.org/W1984264321","https://openalex.org/W3109975354","https://openalex.org/W2357614930","https://openalex.org/W2008642382","https://openalex.org/W1541822869","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Synthesizers":[0],"are":[1,117],"essential":[2],"in":[3,27,82],"modern":[4],"music":[5],"production.":[6],"However,":[7],"their":[8,80],"complex":[9],"timbre":[10,25,53,98,109],"parameters,":[11],"often":[12],"filled":[13],"with":[14,54],"technical":[15],"terms,":[16],"require":[17],"expertise.":[18],"This":[19],"research":[20],"introduces":[21],"a":[22,40,48],"method":[23],"of":[24,96,99],"control":[26,95,110],"wavetable":[28,49,73,101],"synthesis":[29],"that":[30,88],"is":[31],"intuitive":[32,108],"and":[33,35,50,60,67,105],"sensible":[34],"utilizes":[36],"semantic":[37,103,113],"labels.":[38],"Using":[39],"conditional":[41],"variational":[42],"autoencoder":[43],"(CVAE),":[44],"users":[45],"can":[46],"select":[47],"define":[51],"the":[52,72,83,97,100,120],"labels":[55],"such":[56],"as":[57],"bright,":[58],"warm,":[59],"rich.":[61],"The":[62],"CVAE":[63],"model,":[64],"featuring":[65],"convolutional":[66],"upsampling":[68],"layers,":[69],"effectively":[70],"captures":[71],"nuances,":[74],"ensuring":[75],"real-time":[76],"performance":[77],"owing":[78],"to":[79],"processing":[81],"time":[84],"domain.":[85],"Experiments":[86],"demonstrate":[87],"this":[89],"approach":[90],"allows":[91],"for":[92,107],"real-time,":[93],"effective":[94],"using":[102],"inputs":[104],"aims":[106],"through":[111],"data-based":[112],"control.":[114],"Audio":[115],"examples":[116],"available":[118],"on":[119],"online":[121],"demo":[122],"page<sup":[123],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[124],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[125]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}