{"id":"https://openalex.org/W4408356308","doi":"https://doi.org/10.1109/icassp49660.2025.10890708","title":"Latent Diffusion Bridges for Unsupervised Musical Audio Timbre Transfer","display_name":"Latent Diffusion Bridges for Unsupervised Musical Audio Timbre Transfer","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408356308","doi":"https://doi.org/10.1109/icassp49660.2025.10890708"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890708","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890708","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/A5076690986","display_name":"Michele Mancusi","orcid":"https://orcid.org/0000-0003-1591-7076"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Michele Mancusi","raw_affiliation_strings":["Sony Europe B.V.,Stuttgart,Germany"],"affiliations":[{"raw_affiliation_string":"Sony Europe B.V.,Stuttgart,Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114367677","display_name":"Yurii Halychanskyi","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yurii Halychanskyi","raw_affiliation_strings":["University of Illinois Urbana-Champaign,Urbana,IL,USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign,Urbana,IL,USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069612434","display_name":"Kin Wai Cheuk","orcid":"https://orcid.org/0000-0003-3213-8242"},"institutions":[{"id":"https://openalex.org/I4210121096","display_name":"Dexerials (Japan)","ror":"https://ror.org/03p330m15","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210121096"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kin Wai Cheuk","raw_affiliation_strings":["Sony Al,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Sony Al,Tokyo,Japan","institution_ids":["https://openalex.org/I4210121096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030929567","display_name":"Eloi Moliner","orcid":"https://orcid.org/0000-0001-5719-326X"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Eloi Moliner","raw_affiliation_strings":["Aalto University,Acoustics Lab, DICE,Espoo,Finland"],"affiliations":[{"raw_affiliation_string":"Aalto University,Acoustics Lab, DICE,Espoo,Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044626752","display_name":"Chieh-Hsin Lai","orcid":"https://orcid.org/0009-0009-3059-929X"},"institutions":[{"id":"https://openalex.org/I4210121096","display_name":"Dexerials (Japan)","ror":"https://ror.org/03p330m15","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210121096"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chieh-Hsin Lai","raw_affiliation_strings":["Sony Al,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Sony Al,Tokyo,Japan","institution_ids":["https://openalex.org/I4210121096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010554448","display_name":"Stefan Uhlich","orcid":"https://orcid.org/0000-0003-3158-4945"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stefan Uhlich","raw_affiliation_strings":["Sony Europe B.V.,Stuttgart,Germany"],"affiliations":[{"raw_affiliation_string":"Sony Europe B.V.,Stuttgart,Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031164776","display_name":"Junghyun Koo","orcid":"https://orcid.org/0009-0004-4468-0367"},"institutions":[{"id":"https://openalex.org/I4210121096","display_name":"Dexerials (Japan)","ror":"https://ror.org/03p330m15","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210121096"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junghyun Koo","raw_affiliation_strings":["Sony Al,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Sony Al,Tokyo,Japan","institution_ids":["https://openalex.org/I4210121096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017282176","display_name":"Marco A. Mart\u00ednez-Ram\u00edrez","orcid":null},"institutions":[{"id":"https://openalex.org/I4210121096","display_name":"Dexerials (Japan)","ror":"https://ror.org/03p330m15","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210121096"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marco A. Mart\u00ednez-Ram\u00edrez","raw_affiliation_strings":["Sony Al,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Sony Al,Tokyo,Japan","institution_ids":["https://openalex.org/I4210121096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103537853","display_name":"Wei\u2010Hsiang Liao","orcid":"https://orcid.org/0000-0003-4113-1894"},"institutions":[{"id":"https://openalex.org/I4210121096","display_name":"Dexerials (Japan)","ror":"https://ror.org/03p330m15","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210121096"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Wei-Hsiang Liao","raw_affiliation_strings":["Sony Al,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Sony Al,Tokyo,Japan","institution_ids":["https://openalex.org/I4210121096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006089763","display_name":"Giorgio Fabbro","orcid":"https://orcid.org/0000-0002-6302-9033"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Giorgio Fabbro","raw_affiliation_strings":["Sony Europe B.V.,Stuttgart,Germany"],"affiliations":[{"raw_affiliation_string":"Sony Europe B.V.,Stuttgart,Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088754502","display_name":"Yuki Mitsufuji","orcid":"https://orcid.org/0000-0002-6806-6140"},"institutions":[{"id":"https://openalex.org/I4210121096","display_name":"Dexerials (Japan)","ror":"https://ror.org/03p330m15","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210121096"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Mitsufuji","raw_affiliation_strings":["Sony Al,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Sony Al,Tokyo,Japan","institution_ids":["https://openalex.org/I4210121096"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5076690986"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05859495,"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/T11309","display_name":"Music and Audio Processing","score":0.9955000281333923,"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":0.9955000281333923,"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":0.9944000244140625,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9761000275611877,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9116912484169006},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6640126705169678},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5380493998527527},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.47670266032218933},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.06695204973220825}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.9116912484169006},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6640126705169678},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5380493998527527},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.47670266032218933},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.06695204973220825},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890708","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890708","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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W3918136","https://openalex.org/W2963539064","https://openalex.org/W3127854286","https://openalex.org/W3167139504","https://openalex.org/W3196700074","https://openalex.org/W3208394868","https://openalex.org/W4225281045","https://openalex.org/W4307323391","https://openalex.org/W4372259754","https://openalex.org/W4372263311","https://openalex.org/W4372341905","https://openalex.org/W4388444434","https://openalex.org/W4390874265","https://openalex.org/W4392904313","https://openalex.org/W4401023606","https://openalex.org/W4401023668","https://openalex.org/W4403127034","https://openalex.org/W4409095656","https://openalex.org/W6755310453","https://openalex.org/W6757028937","https://openalex.org/W6767111847","https://openalex.org/W6779823529","https://openalex.org/W6780323268","https://openalex.org/W6786375611","https://openalex.org/W6805386329","https://openalex.org/W6810146603","https://openalex.org/W6838452192","https://openalex.org/W6844035133","https://openalex.org/W6850942011","https://openalex.org/W6853096648","https://openalex.org/W6854248540","https://openalex.org/W6856407115","https://openalex.org/W6861317999","https://openalex.org/W6861586093","https://openalex.org/W6868771744","https://openalex.org/W6872701750"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"Music":[0],"timbre":[1,101,110,174],"transfer":[2,111],"is":[3,51,65,84],"a":[4,27,54,58,63],"challenging":[5],"task":[6],"that":[7,124,152],"involves":[8],"modifying":[9],"the":[10,37,68,73,87,92,153,157,166],"timbral":[11],"characteristics":[12],"of":[13,42,168,173],"an":[14],"audio":[15,46,75,94],"signal":[16],"while":[17],"preserving":[18],"its":[19,77],"melodic":[20],"structure.":[21],"In":[22],"this":[23,96],"paper,":[24],"we":[25,150],"propose":[26],"novel":[28],"method":[29,126],"based":[30],"on":[31,53],"dual":[32],"diffusion":[33,49],"bridges,":[34],"trained":[35,52],"using":[36],"CocoChorales":[38],"Dataset,":[39],"which":[40],"consists":[41],"unpaired":[43],"monophonic":[44],"single-instrument":[45],"data.":[47],"Each":[48],"model":[50,64,70,83,89],"specific":[55],"instrument":[56],"with":[57],"Gaussian":[59,79,97,117,158],"prior.":[60],"During":[61],"inference,":[62],"designated":[66,85],"as":[67,86,114,137],"source":[69],"to":[71,76,90,145,164],"map":[72],"input":[74],"corresponding":[78],"prior,":[80,98,159],"and":[81,116,134,147,171],"another":[82],"target":[88,93],"reconstruct":[91],"from":[95,156],"thereby":[99],"facilitating":[100],"transfer.":[102],"We":[103],"compare":[104],"our":[105,125],"approach":[106],"against":[107],"existing":[108],"unsupervised":[109],"models":[112],"such":[113],"VAEGAN":[115,146],"Flow":[118],"Bridges":[119],"(GFB).":[120],"Experimental":[121],"results":[122],"demonstrate":[123],"achieves":[127],"both":[128],"better":[129],"Fr\u00e9chet":[130],"Audio":[131],"Distance":[132],"(FAD)":[133],"melody":[135,169],"preservation,":[136],"reflected":[138],"by":[139],"lower":[140],"pitch":[141],"distances":[142],"(DPD)":[143],"compared":[144],"GFB.":[148],"Additionally,":[149],"discover":[151],"noise":[154],"level":[155],"\u03c3,":[160],"can":[161],"be":[162],"adjusted":[163],"control":[165],"degree":[167],"preservation":[170],"amount":[172],"transferred.":[175]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}
