{"id":"https://openalex.org/W4415538198","doi":"https://doi.org/10.1145/3746027.3755377","title":"MelodyEdit: Zero-shot Music Editing with Disentangled Inversion Control","display_name":"MelodyEdit: Zero-shot Music Editing with Disentangled Inversion Control","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538198","doi":"https://doi.org/10.1145/3746027.3755377"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3755377","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755377","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5070862393","display_name":"Huadai Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Huadai Liu","raw_affiliation_strings":["HKUST, Hong Kong, China and Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0004-5782-5641","affiliations":[{"raw_affiliation_string":"HKUST, Hong Kong, China and Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113082571","display_name":"Jialei Wang","orcid":"https://orcid.org/0009-0002-2786-3896"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jialei Wang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-2786-3896","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089900108","display_name":"Xiangtai Li","orcid":"https://orcid.org/0000-0002-0550-8247"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangtai Li","raw_affiliation_strings":["ByteDance Inc., Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-0550-8247","affiliations":[{"raw_affiliation_string":"ByteDance Inc., Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396375","display_name":"Wen Wang","orcid":"https://orcid.org/0000-0002-0356-1968"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen Wang","raw_affiliation_strings":["Alibaba Group, Sunnyvale, California, USA"],"raw_orcid":"https://orcid.org/0000-0002-0356-1968","affiliations":[{"raw_affiliation_string":"Alibaba Group, Sunnyvale, California, USA","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100428431","display_name":"Qian Chen","orcid":"https://orcid.org/0000-0001-6939-7438"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Chen","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-6939-7438","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011787904","display_name":"Rongjie Huang","orcid":"https://orcid.org/0000-0002-1695-9000"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongjie Huang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-1695-9000","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yang Liu","orcid":"https://orcid.org/0009-0005-8246-0741"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-8246-0741","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011203946","display_name":"Jiayang Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayang Xu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-2557-2438","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-6121-0384","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100652844","display_name":"Wei Xue","orcid":"https://orcid.org/0000-0002-4942-7748"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wei Xue","raw_affiliation_strings":["HKUST, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-4942-7748","affiliations":[{"raw_affiliation_string":"HKUST, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10083","last_page":"10092"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9994000196456909,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.978600025177002,"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/inversion","display_name":"Inversion (geology)","score":0.6223999857902527},{"id":"https://openalex.org/keywords/melody","display_name":"Melody","score":0.5163999795913696},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.4884999990463257},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.460099995136261},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4309000074863434},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.3781000077724457}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7594000101089478},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.6223999857902527},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.5163999795913696},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.4884999990463257},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.460099995136261},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4530999958515167},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4309000074863434},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.3781000077724457},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31299999356269836},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3025999963283539}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3755377","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755377","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-167663","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-167663","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W4312740349","https://openalex.org/W4372266552","https://openalex.org/W4385527149","https://openalex.org/W4386057725","https://openalex.org/W4386076215","https://openalex.org/W4386076532","https://openalex.org/W4386113271","https://openalex.org/W4390872297","https://openalex.org/W4390873195","https://openalex.org/W4390873319","https://openalex.org/W4390873489","https://openalex.org/W4392903114","https://openalex.org/W4398226295","https://openalex.org/W4402112510","https://openalex.org/W4402753991","https://openalex.org/W4411245083"],"related_works":[],"abstract_inverted_index":{"Text-guided":[0],"diffusion":[1,27,83],"models":[2],"revolutionize":[3],"audio":[4,9,17],"generation":[5],"by":[6,98],"adapting":[7],"source":[8,95],"to":[10,88,118],"specific":[11],"text":[12],"prompts.":[13],"However,":[14],"existing":[15,33],"zero-shot":[16,59,151],"editing":[18,34,61,138,146,155,164],"methods":[19,35],"such":[20],"as":[21],"DDIM":[22,99],"inversion":[23,161],"accumulate":[24],"errors":[25],"across":[26],"steps,":[28],"reducing":[29],"the":[30,82,90,94,105,110,121,128],"effectiveness.":[31],"Moreover,":[32],"struggle":[36],"with":[37,113,140],"conducting":[38],"complex":[39],"non-rigid":[40],"music":[41,60,137,154],"edits":[42],"while":[43],"maintaining":[44],"content":[45,167],"integrity":[46],"and":[47,76,109,124,152,166],"high":[48],"fidelity.":[49],"To":[50],"address":[51],"these":[52],"challenges,":[53],"we":[54],"propose":[55],"MelodyEdit,":[56],"a":[57,135],"novel":[58],"system":[62],"based":[63],"on":[64],"innovative":[65],"Disentangled":[66,77,79],"Inversion":[67,80],"Control":[68,75,103],"(DIC)":[69],"technique,":[70],"which":[71],"comprises":[72],"Harmonized":[73,101],"Attention":[74,102],"Inversion.":[78],"disentangles":[81],"process":[84],"into":[85],"triple":[86],"branches":[87],"rectify":[89],"deviated":[91],"path":[92],"of":[93],"branch":[96],"caused":[97],"inversion.":[100],"unifies":[104],"mutual":[106],"self-attention":[107],"control":[108,112],"cross-attention":[111],"an":[114],"intermediate":[115],"Harmonic":[116],"Branch":[117],"progressively":[119],"generate":[120],"desired":[122],"harmonic":[123],"melodic":[125],"information":[126],"in":[127,163],"target":[129],"music.":[130],"We":[131],"also":[132],"introduce":[133],"ZoME-Bench,":[134],"comprehensive":[136],"benchmark":[139],"1,100":[141],"samples":[142],"covering":[143],"ten":[144],"distinct":[145],"categories.":[147],"ZoME-Bench":[148],"facilitates":[149],"both":[150],"instruction-based":[153],"tasks.":[156],"Our":[157],"method":[158],"outperforms":[159],"state-of-the-art":[160],"techniques":[162],"fidelity":[165],"preservation.":[168]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}
