{"id":"https://openalex.org/W4410358627","doi":"https://doi.org/10.1109/access.2025.3570124","title":"Automatic Timbre Transformation Using Enhanced Diffusion Model","display_name":"Automatic Timbre Transformation Using Enhanced Diffusion Model","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4410358627","doi":"https://doi.org/10.1109/access.2025.3570124"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3570124","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3570124","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3570124","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109542115","display_name":"Cheng-Han Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Cheng-Han Wu","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Central University, Taoyuan, Taiwan","Department of Computer Science and Information Engineering, National Central University, Taoyuan City, Taiwan"],"raw_orcid":"https://orcid.org/0009-0003-7469-2484","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Central University, Taoyuan, Taiwan","institution_ids":["https://openalex.org/I22265921"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Central University, Taoyuan City, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014884429","display_name":"Pimpa Cheewaprakobkit","orcid":"https://orcid.org/0000-0002-7888-2053"},"institutions":[{"id":"https://openalex.org/I4210099732","display_name":"Asia Pacific International University","ror":"https://ror.org/00m2sk374","country_code":"TH","type":"education","lineage":["https://openalex.org/I4210099732"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Pimpa Cheewaprakobkit","raw_affiliation_strings":["Faculty of Information Technology, Asia-Pacific International University, Saraburi, Thailand","Faculty of Information Technology, Asia Pacific International University, Saraburi, Thailand"],"raw_orcid":"https://orcid.org/0000-0002-7888-2053","affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Asia-Pacific International University, Saraburi, Thailand","institution_ids":["https://openalex.org/I4210099732"]},{"raw_affiliation_string":"Faculty of Information Technology, Asia Pacific International University, Saraburi, Thailand","institution_ids":["https://openalex.org/I4210099732"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081089928","display_name":"Timothy K. Shih","orcid":"https://orcid.org/0000-0003-4154-4752"},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Timothy K. Shih","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Central University, Taoyuan, Taiwan","Department of Computer Science and Information Engineering, National Central University, Taoyuan City, Taiwan"],"raw_orcid":"https://orcid.org/0000-0003-4154-4752","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Central University, Taoyuan, Taiwan","institution_ids":["https://openalex.org/I22265921"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Central University, Taoyuan City, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050545513","display_name":"Yu-Cheng Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I99908691","display_name":"Yuan Ze University","ror":"https://ror.org/01fv1ds98","country_code":"TW","type":"education","lineage":["https://openalex.org/I99908691"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Cheng Lin","raw_affiliation_strings":["Department of Computer Science and Engineering, Yuan Ze University, Taoyuan, Taiwan","Department of Computer Science and Engineering, Yuan-Ze University, Taoyuan City, Taiwan"],"raw_orcid":"https://orcid.org/0000-0003-2967-0764","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Yuan Ze University, Taoyuan, Taiwan","institution_ids":["https://openalex.org/I99908691"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Yuan-Ze University, Taoyuan City, Taiwan","institution_ids":["https://openalex.org/I99908691"]}]},{"author_position":"last","author":{"id":null,"display_name":"Bing-Ze Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Bing-Ze Liu","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Central University, Taoyuan, Taiwan","Department of Computer Science and Information Engineering, National Central University, Taoyuan City, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Central University, Taoyuan, Taiwan","institution_ids":["https://openalex.org/I22265921"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Central University, Taoyuan City, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07761982,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"91642","last_page":"91654"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9760000109672546,"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":0.9760000109672546,"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":0.9399999976158142,"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/transformation","display_name":"Transformation (genetics)","score":0.657843291759491},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6366949081420898},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.597346842288971},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.544525146484375}],"concepts":[{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.657843291759491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6366949081420898},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.597346842288971},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.544525146484375},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3570124","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3570124","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:7029ef9327d14a7e9a8cb4fb46741566","is_oa":true,"landing_page_url":"https://doaj.org/article/7029ef9327d14a7e9a8cb4fb46741566","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 91642-91654 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3570124","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3570124","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1562274619","https://openalex.org/W2526050071","https://openalex.org/W2765293924","https://openalex.org/W2956530858","https://openalex.org/W2962866891","https://openalex.org/W2972478942","https://openalex.org/W3196700074","https://openalex.org/W3202145349","https://openalex.org/W4205275928","https://openalex.org/W4221136397","https://openalex.org/W4293038948","https://openalex.org/W4372263311","https://openalex.org/W4387727414","https://openalex.org/W4400788245","https://openalex.org/W4401980590","https://openalex.org/W4402044753","https://openalex.org/W4402426651","https://openalex.org/W4402910060","https://openalex.org/W4403087461","https://openalex.org/W4407984563","https://openalex.org/W6733551481","https://openalex.org/W6757817989","https://openalex.org/W6768465061","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6809884996","https://openalex.org/W6810689344","https://openalex.org/W6852824296","https://openalex.org/W6856125517","https://openalex.org/W6873525430"],"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":{"We":[0],"present":[1],"a":[2,24,56,59,63],"novel":[3],"timbre":[4,121,130,148],"transfer":[5,131],"model":[6,54,111],"that":[7,109],"uses":[8],"an":[9],"enhanced":[10],"diffusion":[11],"architecture":[12],"to":[13,30,33,48,91],"convert":[14],"music":[15,134,145],"from":[16],"various":[17],"instruments":[18],"into":[19],"Erhu":[20,81,120],"timbre.":[21,82],"The":[22,66],"Erhu,":[23],"traditional":[25],"Chinese":[26],"instrument,":[27],"is":[28],"difficult":[29],"simulate":[31],"due":[32],"its":[34,50],"rich":[35],"vibrato":[36],"and":[37,62,71,104,116,136,147],"smooth":[38],"note":[39],"transitions.":[40],"Existing":[41],"Musical":[42],"Instrument":[43],"Digital":[44],"Interface":[45],"systems":[46],"struggle":[47],"capture":[49],"nuanced":[51],"dynamics.":[52],"Our":[53],"integrates":[55],"Pitch":[57],"Encoder,":[58,61],"Loudness":[60],"Diffusion":[64],"Decoder.":[65],"encoders":[67],"extract":[68],"pitch":[69,100,114],"features":[70],"dynamic":[72],"loudness":[73],"variations,":[74],"guiding":[75],"the":[76,88,126],"decoder":[77],"in":[78,119,133],"generating":[79],"realistic":[80],"By":[83],"extracting":[84],"general":[85],"musical":[86],"features,":[87],"system":[89],"generalizes":[90],"unseen":[92],"input":[93],"types":[94],"without":[95],"retraining.":[96],"Evaluations":[97],"based":[98],"on":[99,143],"accuracy,":[101],"cosine":[102],"similarity,":[103],"Fr\u00e9chet":[105],"Audio":[106],"Distance":[107],"show":[108],"our":[110],"achieves":[112],"96%":[113],"accuracy":[115],"high":[117],"fidelity":[118],"reproduction.":[122],"This":[123],"study":[124],"demonstrates":[125],"potential":[127],"of":[128],"diffusion-based":[129],"models":[132],"generation":[135,146],"provides":[137],"new":[138],"directions":[139],"for":[140],"future":[141],"work":[142],"both":[144],"transfer.":[149]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
