{"id":"https://openalex.org/W4408355556","doi":"https://doi.org/10.1109/icassp49660.2025.10887821","title":"AudioEditor: A Training-Free Diffusion-Based Audio Editing Framework","display_name":"AudioEditor: A Training-Free Diffusion-Based Audio Editing Framework","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355556","doi":"https://doi.org/10.1109/icassp49660.2025.10887821"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887821","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5111267026","display_name":"Yuhang Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhang Jia","raw_affiliation_strings":["Nankai University,TMCC, College of Computer Science,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,TMCC, College of Computer Science,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100350358","display_name":"Yang Chen","orcid":"https://orcid.org/0000-0001-6204-9334"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Chen","raw_affiliation_strings":["Lingxi (Beijing) Technology Co., Ltd.,Beijing,China","Nankai University,TMCC, College of Computer Science,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lingxi (Beijing) Technology Co., Ltd.,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"Nankai University,TMCC, College of Computer Science,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033737287","display_name":"Jinghua Zhao","orcid":"https://orcid.org/0000-0002-9741-6998"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinghua Zhao","raw_affiliation_strings":["Nankai University,TMCC, College of Computer Science,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,TMCC, College of Computer Science,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shiwan Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiwan Zhao","raw_affiliation_strings":["Nankai University,TMCC, College of Computer Science,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,TMCC, College of Computer Science,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wenjia Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenjia Zeng","raw_affiliation_strings":["Lingxi (Beijing) Technology Co., Ltd.,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lingxi (Beijing) Technology Co., Ltd.,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069849719","display_name":"Chen Yong","orcid":"https://orcid.org/0000-0001-5485-531X"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Chen","raw_affiliation_strings":["Lingxi (Beijing) Technology Co., Ltd.,Beijing,China","Nankai University,TMCC, College of Computer Science,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lingxi (Beijing) Technology Co., Ltd.,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"Nankai University,TMCC, College of Computer Science,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088716214","display_name":"Yong Qin","orcid":"https://orcid.org/0000-0002-6519-8316"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Qin","raw_affiliation_strings":["Nankai University,TMCC, College of Computer Science,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,TMCC, College of Computer Science,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.04533557,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9969000220298767,"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":0.9969000220298767,"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":0.9707000255584717,"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/computer-science","display_name":"Computer science","score":0.775102972984314},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5550282597541809},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4985232353210449},{"id":"https://openalex.org/keywords/hands-free","display_name":"Hands free","score":0.4633199870586395},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.42882102727890015},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.335331529378891}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.775102972984314},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5550282597541809},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4985232353210449},{"id":"https://openalex.org/C3018339088","wikidata":"https://www.wikidata.org/wiki/Q28460","display_name":"Hands free","level":2,"score":0.4633199870586395},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.42882102727890015},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.335331529378891},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887821","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W349236604","https://openalex.org/W2048695508","https://openalex.org/W2526050071","https://openalex.org/W2945761034","https://openalex.org/W3094550259","https://openalex.org/W3162331882","https://openalex.org/W4312933868","https://openalex.org/W4386076532","https://openalex.org/W4387969125","https://openalex.org/W4396877837","https://openalex.org/W4400033239","https://openalex.org/W4402753991","https://openalex.org/W4403674737","https://openalex.org/W4403780831","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6790978476","https://openalex.org/W6795288823","https://openalex.org/W6799880410","https://openalex.org/W6838639034","https://openalex.org/W6840815571","https://openalex.org/W6841366371","https://openalex.org/W6848729602","https://openalex.org/W6849109464","https://openalex.org/W6849416043","https://openalex.org/W6851290578","https://openalex.org/W6852971826","https://openalex.org/W6861586093","https://openalex.org/W6861588666","https://openalex.org/W6862532553","https://openalex.org/W6866287167","https://openalex.org/W6868939136"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4366179611","https://openalex.org/W2996078371"],"abstract_inverted_index":{"Diffusion-based":[0],"text-to-audio":[1],"(TTA)":[2],"generation":[3],"has":[4,32],"made":[5],"substantial":[6],"progress,":[7],"leveraging":[8],"latent":[9],"diffusion":[10],"model":[11,104],"(LDM)":[12],"to":[13,74,105],"produce":[14],"high-quality,":[15],"diverse":[16],"and":[17,47,99,116,130],"instruction-relevant":[18],"audios.":[19],"However,":[20],"beyond":[21],"generation,":[22],"the":[23,49,63,90,103,120],"task":[24],"of":[25,65,122],"audio":[26,75,85,108,127],"editing":[27,38,86],"remains":[28],"equally":[29],"important":[30],"but":[31],"received":[33],"comparatively":[34],"little":[35],"attention.":[36],"Audio":[37],"tasks":[39],"face":[40],"two":[41],"primary":[42],"challenges:":[43],"executing":[44,111],"precise":[45],"edits":[46],"preserving":[48],"unedited":[50],"sections.":[51],"While":[52],"workflows":[53],"based":[54],"on":[55,89],"LDMs":[56],"have":[57,70],"effectively":[58],"addressed":[59],"these":[60],"challenges":[61],"in":[62,124],"field":[64],"image":[66],"processing,":[67],"similar":[68],"approaches":[69],"been":[71],"scarcely":[72],"applied":[73],"editing.":[76],"In":[77],"this":[78],"paper,":[79],"we":[80],"introduce":[81],"AudioEditor,":[82],"a":[83],"training-free":[84],"framework":[87],"built":[88],"pretrained":[91],"diffusion-based":[92],"TTA":[93],"model.":[94],"AudioEditor":[95,123],"incorporates":[96],"Null-text":[97],"Inversion":[98],"EOT-suppression":[100],"methods,":[101],"enabling":[102],"preserve":[106],"original":[107],"features":[109],"while":[110],"accurate":[112],"edits.":[113,128],"Comprehensive":[114],"objective":[115],"subjective":[117],"experiments":[118],"validate":[119],"effectiveness":[121],"delivering":[125],"high-quality":[126],"Code":[129],"demo":[131],"can":[132],"be":[133],"found":[134],"at":[135],"https://github.com/NKU-HLT/AudioEditor.":[136]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
