{"id":"https://openalex.org/W7138355437","doi":"https://doi.org/10.1609/aaai.v40i3.37204","title":"Melodia: Training-Free Music Editing Guided by Attention Probing in Diffusion Models","display_name":"Melodia: Training-Free Music Editing Guided by Attention Probing in Diffusion Models","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138355437","doi":"https://doi.org/10.1609/aaai.v40i3.37204"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i3.37204","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i3.37204","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i3.37204","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129693635","display_name":"Yi Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028125561","display_name":"Haowen Li","orcid":"https://orcid.org/0000-0003-2746-4000"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haowen Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129743854","display_name":"Tianxiang Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianxiang Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129690899","display_name":"Boyu Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boyu Cao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129689109","display_name":"Xiaohan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaohan Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037735790","display_name":"Liqun Chen","orcid":"https://orcid.org/0000-0003-2680-4907"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liqun Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129680112","display_name":"Qi Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.23084322,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"3","first_page":"2209","last_page":"2217"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.6804999709129333,"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":0.6804999709129333,"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":0.20919999480247498,"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":0.01269999984651804,"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/process","display_name":"Process (computing)","score":0.5303000211715698},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.508899986743927},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.48350000381469727},{"id":"https://openalex.org/keywords/musical-composition","display_name":"Musical composition","score":0.4291999936103821},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.37290000915527344},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.37049999833106995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7839999794960022},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5303000211715698},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.508899986743927},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.48350000381469727},{"id":"https://openalex.org/C109568592","wikidata":"https://www.wikidata.org/wiki/Q207628","display_name":"Musical composition","level":3,"score":0.4291999936103821},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.37290000915527344},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.37049999833106995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3555000126361847},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3386000096797943},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.3352000117301941},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3215000033378601},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C73520026","wikidata":"https://www.wikidata.org/wiki/Q7229091","display_name":"Pop music automation","level":4,"score":0.2870999872684479},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2809999883174896},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C34259666","wikidata":"https://www.wikidata.org/wiki/Q1122550","display_name":"Computer music","level":3,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i3.37204","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i3.37204","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i3.37204","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i3.37204","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6632328629493713,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Text-to-music":[0],"generation":[1,211],"technology":[2],"is":[3],"progressing":[4],"rapidly,":[5],"creating":[6],"new":[7],"opportunities":[8],"for":[9,66,100,217],"musical":[10,82,152],"composition":[11],"and":[12,30,39,84,138,181,196,213],"editing.":[13],"However,":[14],"existing":[15,67],"music":[16,68,108,146,176,210,218],"editing":[17,69,177],"methods":[18],"often":[19],"fail":[20],"to":[21,143,173],"preserve":[22],"the":[23,64,102,106,113,135,156,164],"source":[24,107,145,165],"music's":[25],"temporal":[26,103],"structure,":[27],"including":[28],"melody":[29],"rhythm,":[31],"when":[32],"altering":[33],"particular":[34,132],"attributes":[35],"like":[36],"instrument,":[37],"genre,":[38],"mood.":[40],"To":[41],"address":[42],"this":[43,45,118],"challenge,":[44],"paper":[46],"conducts":[47],"an":[48,140],"in-depth":[49],"probing":[50],"analysis":[51],"on":[52,86],"attention":[53,141],"maps":[54,77,88,97,130],"within":[55,209],"AudioLDM":[56],"2,":[57],"a":[58,73,123],"diffusion-based":[59],"model":[60],"commonly":[61],"used":[62],"as":[63],"backbone":[65],"methods.":[70,178],"We":[71],"reveal":[72],"key":[74],"finding:":[75],"cross-attention":[76],"encompass":[78],"details":[79],"regarding":[80],"distinct":[81],"characteristics,":[83],"interventions":[85],"these":[87],"frequently":[89],"result":[90],"in":[91,131,191],"ineffective":[92],"modifications.":[93],"In":[94],"contrast,":[95],"self-attention":[96,129],"are":[98],"essential":[99],"preserving":[101,155],"structure":[104,158],"of":[105,151,163,193,206],"during":[109,134],"its":[110],"conversion":[111],"into":[112],"target":[114],"music.":[115,166],"Building":[116],"upon":[117],"understanding,":[119],"we":[120,168],"present":[121],"Melodia,":[122],"training-free":[124],"technique":[125],"that":[126,185],"selectively":[127],"manipulates":[128],"layers":[133],"denoising":[136],"process":[137],"leverages":[139],"repository":[142],"store":[144],"information,":[147],"achieving":[148],"accurate":[149],"modification":[150],"characteristics":[153],"while":[154],"original":[157],"without":[159],"requiring":[160],"textual":[161,194],"descriptions":[162],"Additionally,":[167],"propose":[169],"two":[170],"novel":[171],"metrics":[172],"better":[174],"evaluate":[175],"Both":[179],"objective":[180],"subjective":[182],"experiments":[183],"demonstrate":[184],"our":[186],"approach":[187],"achieves":[188],"superior":[189],"results":[190],"terms":[192],"adherence":[195],"structural":[197],"integrity":[198],"across":[199],"various":[200],"datasets.":[201],"This":[202],"research":[203],"enhances":[204],"comprehension":[205],"internal":[207],"mechanisms":[208],"models":[212],"provides":[214],"improved":[215],"control":[216],"creation.":[219]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-18T00:00:00"}