{"id":"https://openalex.org/W4404986915","doi":"https://doi.org/10.1109/icip61757.2026.11630156","title":"Repurposing Image Diffusion Models for Training-Free Music Style Transfer on Mel-Spectrograms","display_name":"Repurposing Image Diffusion Models for Training-Free Music Style Transfer on Mel-Spectrograms","publication_year":2026,"publication_date":"2026-08-13","ids":{"openalex":"https://openalex.org/W4404986915","doi":"https://doi.org/10.1109/icip61757.2026.11630156"},"language":"en","primary_location":{"id":"doi:10.1109/icip61757.2026.11630156","doi":"https://doi.org/10.1109/icip61757.2026.11630156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip61757.2026.11630156","pdf_url":null,"source":{"id":"https://openalex.org/S4210223844","display_name":"Proceedings - International Conference on Image Processing","issn_l":"1522-4880","issn":["1522-4880","2381-8549"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.15913","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013271513","display_name":"Hee\u2010Hwan Wang","orcid":"https://orcid.org/0000-0002-7462-5834","observed_orcids":["https://orcid.org/0000-0002-7462-5834"]},"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":"Heehwan Wang","raw_affiliation_strings":["Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104264420","display_name":"Joonwoo Kwon","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joonwoo Kwon","raw_affiliation_strings":["Michigan State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100694010","display_name":"Sooyoung Kim","orcid":"https://orcid.org/0000-0003-0817-2790","observed_orcids":["https://orcid.org/0000-0003-0817-2790"]},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sooyoung Kim","raw_affiliation_strings":["Rutgers University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jungwoo Seo","orcid":null,"observed_orcids":[]},"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":"Jungwoo Seo","raw_affiliation_strings":["Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048176207","display_name":"Shinjae Yoo","orcid":"https://orcid.org/0000-0003-4378-6448","observed_orcids":["https://orcid.org/0000-0003-4378-6448"]},"institutions":[{"id":"https://openalex.org/I200870766","display_name":"Brookhaven National Laboratory","ror":"https://ror.org/02ex6cf31","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I200870766","https://openalex.org/I39565521","https://openalex.org/I4210142672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinjae Yoo","raw_affiliation_strings":["Brookhaven National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brookhaven National Laboratory","institution_ids":["https://openalex.org/I200870766"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027105734","display_name":"Yuewei Lin","orcid":"https://orcid.org/0000-0002-1429-4543","observed_orcids":["https://orcid.org/0000-0002-1429-4543"]},"institutions":[{"id":"https://openalex.org/I200870766","display_name":"Brookhaven National Laboratory","ror":"https://ror.org/02ex6cf31","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I200870766","https://openalex.org/I39565521","https://openalex.org/I4210142672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuewei Lin","raw_affiliation_strings":["Brookhaven National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brookhaven National Laboratory","institution_ids":["https://openalex.org/I200870766"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033979262","display_name":"Jiook Cha","orcid":"https://orcid.org/0000-0002-5314-7992","observed_orcids":["https://orcid.org/0000-0002-5314-7992"]},"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":"Jiook Cha","raw_affiliation_strings":["Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":0.00222758,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9340999722480774,"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":0.9340999722480774,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.05510000139474869,"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":0.00989999994635582,"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/music-style-transfer","display_name":"music style transfer","score":0.984000027179718},{"id":"https://openalex.org/keywords/image-diffusion-models","display_name":"image diffusion models","score":0.9110000133514404},{"id":"https://openalex.org/keywords/mel-spectrogram","display_name":"Mel spectrogram","score":0.8799999952316284},{"id":"https://openalex.org/keywords/classifier-free-guidance","display_name":"classifier-free guidance","score":0.8939999938011169}],"concepts":[{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6448910236358643},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5024950504302979},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48008185625076294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3297175168991089},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.1281333863735199},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.1271359920501709},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09839102625846863},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icip61757.2026.11630156","doi":"https://doi.org/10.1109/icip61757.2026.11630156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip61757.2026.11630156","pdf_url":null,"source":{"id":"https://openalex.org/S4210223844","display_name":"Proceedings - International Conference on Image Processing","issn_l":"1522-4880","issn":["1522-4880","2381-8549"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2411.15913","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2411.15913","pdf_url":"https://arxiv.org/pdf/2411.15913","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.15913","doi":"https://doi.org/10.48550/arxiv.2411.15913","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.15913","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.15913","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2411.15913","pdf_url":"https://arxiv.org/pdf/2411.15913","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4393158405","https://openalex.org/W4395443375","https://openalex.org/W4226190360","https://openalex.org/W3010671658","https://openalex.org/W2786651925","https://openalex.org/W2962775980","https://openalex.org/W4400788245","https://openalex.org/W4300065921","https://openalex.org/W7155045124","https://openalex.org/W3127854286"],"abstract_inverted_index":{"Music":[0],"style":[1,8,49,67],"transfer":[2,50],"blends":[3],"source":[4,73],"structure":[5],"with":[6],"reference":[7],"to":[9,20,86],"enable":[10],"personalized":[11],"music":[12,48],"creation.":[13],"However,":[14],"existing":[15],"zero-shot":[16],"methods":[17],"often":[18],"struggle":[19],"capture":[21],"fine-grained":[22],"audio":[23,57],"nuances,":[24],"relying":[25],"on":[26],"coarse":[27],"text":[28],"descriptions":[29],"or":[30],"requiring":[31],"expensive":[32],"task-specific":[33],"training.":[34],"We":[35],"propose":[36],"Stylus,":[37],"a":[38,82,92],"training-free":[39,133],"framework":[40],"that":[41,105,123],"repurposes":[42],"pretrained":[43],"image":[44,125],"diffusion":[45],"models":[46],"for":[47,95,131],"in":[51],"the":[52,132],"Mel-spectrogram":[53],"domain.":[54],"By":[55],"treating":[56],"as":[58],"structured":[59,136],"time-frequency":[60],"images,":[61],"Stylus":[62,106],"manipulates":[63],"self-attention":[64],"by":[65],"injecting":[66],"keys":[68],"and":[69,115,139],"values":[70],"while":[71],"preserving":[72],"structural":[74],"queries.":[75],"To":[76],"ensure":[77],"high":[78],"fidelity,":[79],"we":[80],"introduce":[81],"phase-preserving":[83],"reconstruction":[84],"strategy":[85],"mitigate":[87],"spectrogram":[88],"inversion":[89],"artifacts,":[90],"alongside":[91],"classifier-free-guidance-inspired":[93],"control":[94],"adjustable":[96],"stylization.":[97],"Extensive":[98],"evaluations":[99],"including":[100],"2,925":[101],"human":[102],"ratings":[103],"demonstrate":[104],"outperforms":[107],"state-of-the-art":[108],"baselines,":[109],"achieving":[110],"34.1%":[111],"higher":[112],"content":[113],"preservation":[114],"25.7%":[116],"better":[117],"perceptual":[118],"quality.":[119],"Our":[120],"work":[121],"validates":[122],"generic":[124],"priors":[126],"can":[127],"be":[128],"effectively":[129],"leveraged":[130],"transformation":[134],"of":[135],"Mel-spectrograms.":[137],"Code":[138],"materials":[140],"are":[141],"available":[142],"at":[143],"https://github.com/Sooyyoungg/Stylus.git.":[144]},"counts_by_year":[],"updated_date":"2026-10-06T10:28:23.643775","created_date":"2024-12-04T00:00:00"}
