{"id":"https://openalex.org/W4409156681","doi":"https://doi.org/10.1109/ieeeconf60004.2024.10943019","title":"Instrumental Timbre Transfer Based on Disentangled Representation of Timbre and Pitch","display_name":"Instrumental Timbre Transfer Based on Disentangled Representation of Timbre and Pitch","publication_year":2024,"publication_date":"2024-10-27","ids":{"openalex":"https://openalex.org/W4409156681","doi":"https://doi.org/10.1109/ieeeconf60004.2024.10943019"},"language":"en","primary_location":{"id":"doi:10.1109/ieeeconf60004.2024.10943019","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf60004.2024.10943019","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 58th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100391268","display_name":"Lin Ye","orcid":"https://orcid.org/0000-0002-9647-0271"},"institutions":[{"id":"https://openalex.org/I119449181","display_name":"Technische Universit\u00e4t Ilmenau","ror":"https://ror.org/01weqhp73","country_code":"DE","type":"education","lineage":["https://openalex.org/I119449181"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lin Ye","raw_affiliation_strings":["Ilmenau University of Technology,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ilmenau University of Technology,Germany","institution_ids":["https://openalex.org/I119449181"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087435726","display_name":"Gerald Schuller","orcid":"https://orcid.org/0000-0003-0591-4365"},"institutions":[{"id":"https://openalex.org/I119449181","display_name":"Technische Universit\u00e4t Ilmenau","ror":"https://ror.org/01weqhp73","country_code":"DE","type":"education","lineage":["https://openalex.org/I119449181"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerald Schuller","raw_affiliation_strings":["Ilmenau University of Technology,Department of Electrical Engineering and Information Technology,Ilmenau,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ilmenau University of Technology,Department of Electrical Engineering and Information Technology,Ilmenau,Germany","institution_ids":["https://openalex.org/I119449181"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037680930","display_name":"Muhammad Imran","orcid":"https://orcid.org/0000-0003-3549-6221"},"institutions":[{"id":"https://openalex.org/I119449181","display_name":"Technische Universit\u00e4t Ilmenau","ror":"https://ror.org/01weqhp73","country_code":"DE","type":"education","lineage":["https://openalex.org/I119449181"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Muhammad Imran","raw_affiliation_strings":["Ilmenau University of Technology,Department of Electrical Engineering and Information Technology,Ilmenau,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ilmenau University of Technology,Department of Electrical Engineering and Information Technology,Ilmenau,Germany","institution_ids":["https://openalex.org/I119449181"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I119449181"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1423","last_page":"1426"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.992900013923645,"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":0.992900013923645,"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/timbre","display_name":"Timbre","score":0.9446131587028503},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5605061650276184},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5585256814956665},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5015909671783447},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.14838358759880066},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.10817420482635498},{"id":"https://openalex.org/keywords/literature","display_name":"Literature","score":0.07853367924690247}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.9446131587028503},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5605061650276184},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5585256814956665},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5015909671783447},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.14838358759880066},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.10817420482635498},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.07853367924690247},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ieeeconf60004.2024.10943019","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf60004.2024.10943019","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 58th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2519091744","https://openalex.org/W2962721334","https://openalex.org/W3127854286","https://openalex.org/W3161927506","https://openalex.org/W3196700074","https://openalex.org/W4312120655"],"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":{"Timbre":[0],"transfer":[1,46,59,80,144],"is":[2],"a":[3,53,61],"complex":[4],"audio":[5,130],"synthesis":[6],"task":[7],"that":[8],"changes":[9],"the":[10,22,30,68,74,79,92,136],"distinctive":[11],"perceptual":[12],"attribute":[13],"of":[14,32,81,98],"one":[15],"instrument":[16],"to":[17,28],"resemble":[18],"another":[19],"while":[20,90],"preserving":[21,91],"underlying":[23],"musical":[24,86],"content.":[25],"In":[26],"order":[27],"investigate":[29],"possibility":[31],"effective":[33],"representation":[34],"for":[35,55,119,138],"pitch":[36,94,109],"and":[37,51,76,88,111,132,141],"timbre,":[38],"this":[39],"paper":[40],"explores":[41],"recent":[42],"advances":[43],"in":[44,127],"timbre":[45,58,75,120,143],"using":[47,60],"deep":[48],"learning":[49],"models,":[50],"presents":[52],"framework":[54],"multiple-to-multiple":[56],"instrumental":[57],"beta-variational":[62],"autoencoder":[63],"<tex":[64],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[65],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\beta$</tex>-VAE).":[66],"Through":[67],"dual-encoder":[69],"system,":[70],"it":[71],"effectively":[72],"disentangles":[73],"pitch,":[77],"enabling":[78],"timbral":[82],"characteristics":[83],"across":[84],"different":[85],"notes":[87],"instruments":[89],"original":[93],"information.":[95],"The":[96],"performance":[97],"our":[99],"approach,":[100],"evaluated":[101],"through":[102],"metrics":[103],"including":[104],"Frechet":[105],"Audio":[106],"Distance":[107],"(FAD),":[108],"accuracy,":[110],"Structural":[112],"Similarity":[113],"Index":[114],"(SSIM),":[115],"suggests":[116],"its":[117],"effectiveness":[118],"conversions.":[121],"This":[122],"research":[123],"offers":[124],"potential":[125],"applications":[126],"music":[128],"production,":[129],"synthesis,":[131],"sound":[133],"design,":[134],"paving":[135],"way":[137],"more":[139],"adaptable":[140],"efficient":[142],"solutions.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
