{"id":"https://openalex.org/W4416798880","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249148","title":"Unified Timbre Transfer: A Compact Model for Real-Time Multi-Instrument Sound Morphing","display_name":"Unified Timbre Transfer: A Compact Model for Real-Time Multi-Instrument Sound Morphing","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798880","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249148"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5066123531","display_name":"Anders R. Bargum","orcid":null},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Anders R. Bargum","raw_affiliation_strings":["Aalborg University,Multisensory Experience Lab,Copenhagen,Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University,Multisensory Experience Lab,Copenhagen,Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086267956","display_name":"Naotake Masuda","orcid":"https://orcid.org/0000-0001-8064-3038"},"institutions":[{"id":"https://openalex.org/I4210113449","display_name":"Nemoto (Japan)","ror":"https://ror.org/01xzey958","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210113449"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naotake Masuda","raw_affiliation_strings":["Qosmo &#x0026; Neutone AI,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qosmo &#x0026; Neutone AI,Tokyo,Japan","institution_ids":["https://openalex.org/I4210113449"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120437469","display_name":"Bogdan Teleaga","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113449","display_name":"Nemoto (Japan)","ror":"https://ror.org/01xzey958","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210113449"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Bogdan Teleaga","raw_affiliation_strings":["Qosmo &#x0026; Neutone AI,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qosmo &#x0026; Neutone AI,Tokyo,Japan","institution_ids":["https://openalex.org/I4210113449"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120489415","display_name":"Andrew Fyfe","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113449","display_name":"Nemoto (Japan)","ror":"https://ror.org/01xzey958","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210113449"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Andrew Fyfe","raw_affiliation_strings":["Qosmo &#x0026; Neutone AI,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qosmo &#x0026; Neutone AI,Tokyo,Japan","institution_ids":["https://openalex.org/I4210113449"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016935761","display_name":"Cumhur Erkut","orcid":"https://orcid.org/0000-0003-0750-1919"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Cumhur Erkut","raw_affiliation_strings":["Aalborg University,Multisensory Experience Lab,Copenhagen,Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University,Multisensory Experience Lab,Copenhagen,Denmark","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34650868,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"270","last_page":"275"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.7462000250816345,"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":0.7462000250816345,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.07500000298023224,"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":0.07010000199079514,"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":0.9781000018119812},{"id":"https://openalex.org/keywords/morphing","display_name":"Morphing","score":0.9089000225067139},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.4984000027179718},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.42160001397132874},{"id":"https://openalex.org/keywords/sound-recording-and-reproduction","display_name":"Sound recording and reproduction","score":0.4140999913215637},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.32519999146461487},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3174999952316284},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2978000044822693},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.2838999927043915}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.9781000018119812},{"id":"https://openalex.org/C50637493","wikidata":"https://www.wikidata.org/wiki/Q1136781","display_name":"Morphing","level":2,"score":0.9089000225067139},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7114999890327454},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5128999948501587},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.4984000027179718},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.42480000853538513},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.42160001397132874},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.4140999913215637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3580000102519989},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.32519999146461487},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2904999852180481},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.2838999927043915},{"id":"https://openalex.org/C9940772","wikidata":"https://www.wikidata.org/wiki/Q557399","display_name":"Psychoacoustics","level":3,"score":0.2791000008583069},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2676999866962433},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.262800008058548},{"id":"https://openalex.org/C81299745","wikidata":"https://www.wikidata.org/wiki/Q334269","display_name":"Transfer function","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C135959358","wikidata":"https://www.wikidata.org/wiki/Q76190","display_name":"Soap bubble","level":2,"score":0.2515999972820282},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.25099998712539673},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/a49f67f0-b6a2-4d18-b6d6-4d477b09186e","is_oa":false,"landing_page_url":"https://vbn.aau.dk/da/publications/a49f67f0-b6a2-4d18-b6d6-4d477b09186e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bargum, A R, Masuda, N, Teleaga, B, Fyfe, A & Erkut, C 2025, Unified Timbre Transfer : A Compact Model for Real-Time Multi-Instrument Sound Morphing. in 2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)., 11249148, IEEE (Institute of Electrical and Electronics Engineers), pp. 270-275. https://doi.org/10.1109/APSIPAASC65261.2025.11249148","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1995268113","https://openalex.org/W2091425152","https://openalex.org/W2759171953","https://openalex.org/W2760103357","https://openalex.org/W2962721334","https://openalex.org/W2962866891","https://openalex.org/W2972478942","https://openalex.org/W2972654834","https://openalex.org/W2984862052","https://openalex.org/W3127854286","https://openalex.org/W3196700074","https://openalex.org/W4225281045","https://openalex.org/W4372260516"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,30,66],"transformer-and":[3],"diffusion-based":[4],"deep-generative":[5],"models":[6],"have":[7],"significantly":[8],"impacted":[9],"the":[10,102,121],"field":[11],"of":[12,44],"music":[13,31],"and":[14,19,38,46,50,70,91],"audio":[15,124],"synthesis.":[16],"However,":[17],"controllable":[18],"real-time":[20],"interactive":[21],"models,":[22,115],"such":[23],"as":[24],"those":[25],"used":[26],"for":[27,96,104,120],"timbre":[28,48,52,64,83],"transfer":[29,84],"production,":[32],"remain":[33],"largely":[34],"dominated":[35],"by":[36],"auto-encoders":[37],"generative":[39],"adversarial":[40],"networks.":[41],"In":[42],"pursuit":[43],"efficient":[45],"flexible":[47],"morphing":[49],"multi-instrument":[51],"transfer,":[53],"we":[54],"propose":[55],"a":[56],"simplified":[57],"modeling":[58],"approach,":[59],"utilizing":[60],"an":[61],"upsampled":[62],"two-dimensional":[63],"space":[65],"conjunction":[67],"with":[68,85],"engineered":[69],"instrument-dependent":[71],"excitation":[72],"signals.":[73],"Different":[74],"from":[75],"many":[76],"other":[77],"works,":[78],"our":[79],"model":[80,106],"enables":[81],"any-to-many":[82],"added":[86],"control":[87],"over":[88],"timbre,":[89],"pitch,":[90],"loudness.":[92],"We":[93],"additionally":[94],"allow":[95],"seamless":[97],"interpolation":[98],"between":[99],"instruments,":[100],"eliminating":[101],"need":[103],"separate":[105],"training.":[107],"Our":[108],"evaluation":[109],"shows":[110],"performance":[111],"comparable":[112],"to":[113],"specialized":[114],"making":[116],"it":[117],"highly":[118],"relevant":[119],"broader":[122],"creative":[123],"community.":[125]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-11-28T00:00:00"}
