{"id":"https://openalex.org/W4408352693","doi":"https://doi.org/10.1109/icassp49660.2025.10888403","title":"TokenSynth: A Token-based Neural Synthesizer for Instrument Cloning and Text-to-Instrument","display_name":"TokenSynth: A Token-based Neural Synthesizer for Instrument Cloning and Text-to-Instrument","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352693","doi":"https://doi.org/10.1109/icassp49660.2025.10888403"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888403","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888403","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5000349069","display_name":"Kyungsu Kim","orcid":"https://orcid.org/0000-0001-6622-6545"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Kyungsu Kim","raw_affiliation_strings":["Seoul National University,Music and Audio Research Group (MARG),Department of Intelligence and Information"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Music and Audio Research Group (MARG),Department of Intelligence and Information","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116269906","display_name":"Junghyun Koo","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Junghyun Koo","raw_affiliation_strings":["Seoul National University,Music and Audio Research Group (MARG),Department of Intelligence and Information"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Music and Audio Research Group (MARG),Department of Intelligence and Information","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100402788","display_name":"Sung\u2010Ho Lee","orcid":"https://orcid.org/0000-0002-7957-3228"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungho Lee","raw_affiliation_strings":["Seoul National University,Music and Audio Research Group (MARG),Department of Intelligence and Information"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Music and Audio Research Group (MARG),Department of Intelligence and Information","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116269907","display_name":"Haesun Joung","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Haesun Joung","raw_affiliation_strings":["Seoul National University,Music and Audio Research Group (MARG),Department of Intelligence and Information"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Music and Audio Research Group (MARG),Department of Intelligence and Information","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088852010","display_name":"Kyogu Lee","orcid":"https://orcid.org/0000-0002-4210-0312"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyogu Lee","raw_affiliation_strings":["Seoul National University,Music and Audio Research Group (MARG),Department of Intelligence and Information"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Music and Audio Research Group (MARG),Department of Intelligence and Information","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5000349069"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04138426,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9980000257492065,"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":0.9980000257492065,"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/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9819999933242798,"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/security-token","display_name":"Security token","score":0.7125885486602783},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.618180513381958},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15490621328353882}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7125885486602783},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.618180513381958},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15490621328353882}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888403","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888403","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320321292","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1970491336","https://openalex.org/W2264578237","https://openalex.org/W2752796333","https://openalex.org/W2890043615","https://openalex.org/W2962721334","https://openalex.org/W3215457199","https://openalex.org/W3215615641","https://openalex.org/W4293363567","https://openalex.org/W4307323391","https://openalex.org/W4312974539","https://openalex.org/W4372260310","https://openalex.org/W4372263680","https://openalex.org/W4372341951","https://openalex.org/W4375868847","https://openalex.org/W4385245566","https://openalex.org/W4387195417","https://openalex.org/W4390745914","https://openalex.org/W4398226295","https://openalex.org/W4406888640","https://openalex.org/W6714030504","https://openalex.org/W6736723571","https://openalex.org/W6745245109","https://openalex.org/W6758675244","https://openalex.org/W6771763809","https://openalex.org/W6783182287","https://openalex.org/W6791353385","https://openalex.org/W6798451072","https://openalex.org/W6803088475","https://openalex.org/W6810452849","https://openalex.org/W6840815571","https://openalex.org/W6842676699","https://openalex.org/W6845479124","https://openalex.org/W6848735303","https://openalex.org/W6849105126","https://openalex.org/W6849109464","https://openalex.org/W6853096648","https://openalex.org/W6853515095","https://openalex.org/W6857924758","https://openalex.org/W6872454346","https://openalex.org/W7058503882"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,14],"neural":[3,34,122,132],"audio":[4,12,16,44,123,140],"codecs":[5,124],"have":[6],"enabled":[7],"the":[8,88,91,94,110,117],"use":[9],"of":[10,63,90,119],"tokenized":[11],"representations":[13],"various":[15],"generation":[17],"tasks,":[18],"such":[19],"as":[20],"text-to-speech,":[21],"text-to-audio,":[22],"and":[23,49,69,82,99,102,125,130,139],"text-to-music":[24],"generation.":[25],"Leveraging":[26],"this":[27],"approach,":[28],"we":[29],"propose":[30],"TokenSynth,":[31],"a":[32,38],"novel":[33],"synthesizer":[35],"that":[36],"utilizes":[37],"decoder-only":[39],"transformer":[40],"to":[41,127],"generate":[42],"desired":[43],"tokens":[45,48],"from":[46],"MIDI":[47],"CLAP":[50],"(Contrastive":[51],"Language-Audio":[52],"Pretraining)":[53],"embedding,":[54],"which":[55],"has":[56],"timbre-related":[57],"information.":[58],"Our":[59],"model":[60,137],"is":[61],"capable":[62],"performing":[64],"instrument":[65],"cloning,":[66],"text-to-instrument":[67],"synthesis,":[68],"text-guided":[70],"timbre":[71,84],"manipulation":[72],"without":[73],"any":[74],"fine-tuning.":[75],"This":[76],"flexibility":[77],"enables":[78],"diverse":[79],"sound":[80],"design":[81],"intuitive":[83],"control.":[85],"We":[86],"evaluated":[87],"quality":[89],"synthesized":[92,98],"audio,":[93],"timbral":[95],"similarity":[96],"between":[97],"target":[100],"audio/text,":[101],"synthesis":[103],"accuracy":[104],"(i.e.,":[105],"how":[106],"accurately":[107],"it":[108],"follows":[109],"input":[111],"MIDI)":[112],"using":[113],"objective":[114],"measures.TokenSynth":[115],"demonstrates":[116],"potential":[118],"leveraging":[120],"advanced":[121],"transformers":[126],"create":[128],"powerful":[129],"versatile":[131],"synthesizers.":[133],"The":[134],"source":[135],"code,":[136],"weights,":[138],"demos":[141],"are":[142],"available":[143],"at:":[144],"https://github.com/KyungsuKim42/tokensynth":[145]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}