{"id":"https://openalex.org/W4362598673","doi":"https://doi.org/10.48550/arxiv.2304.00830","title":"AUDIT: Audio Editing by Following Instructions with Latent Diffusion Models","display_name":"AUDIT: Audio Editing by Following Instructions with Latent Diffusion Models","publication_year":2023,"publication_date":"2023-04-03","ids":{"openalex":"https://openalex.org/W4362598673","doi":"https://doi.org/10.48550/arxiv.2304.00830"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2304.00830","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.00830","pdf_url":"https://arxiv.org/pdf/2304.00830","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2304.00830","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090055283","display_name":"Yuancheng Wang","orcid":"https://orcid.org/0000-0002-6253-8311"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wang, Yuancheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073017662","display_name":"Zeqian Ju","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ju, Zeqian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385893","display_name":"Xu Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Xu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114859990","display_name":"Lei He","orcid":"https://orcid.org/0009-0001-7753-4700"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Lei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102765381","display_name":"Zhizheng Wu","orcid":"https://orcid.org/0009-0001-1192-9857"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Zhizheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101544241","display_name":"Jiang Bian","orcid":"https://orcid.org/0000-0002-9472-600X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bian, Jiang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100329353","display_name":"Sheng Zhao","orcid":"https://orcid.org/0000-0002-9624-5381"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Sheng","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5090055283"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9932000041007996,"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":0.9932000041007996,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9521999955177307,"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/T10860","display_name":"Speech and Audio Processing","score":0.9488000273704529,"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/computer-science","display_name":"Computer science","score":0.8429040908813477},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5165582895278931},{"id":"https://openalex.org/keywords/audit","display_name":"Audit","score":0.4720892608165741},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.46151089668273926},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.32637667655944824},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09149324893951416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8429040908813477},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5165582895278931},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.4720892608165741},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.46151089668273926},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.32637667655944824},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09149324893951416},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2304.00830","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.00830","pdf_url":"https://arxiv.org/pdf/2304.00830","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2304.00830","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2304.00830","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2304.00830","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.00830","pdf_url":"https://arxiv.org/pdf/2304.00830","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4362598673.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2366107444","https://openalex.org/W4388145910","https://openalex.org/W2381570729","https://openalex.org/W1976205134","https://openalex.org/W4248336175","https://openalex.org/W2031260042","https://openalex.org/W2391445434","https://openalex.org/W3009369890"],"abstract_inverted_index":{"Audio":[0],"editing":[1,28,59,65,108,136,210],"is":[2,90],"applicable":[3],"for":[4,133,207],"various":[5],"purposes,":[6],"such":[7],"as":[8,151,194],"adding":[9],"background":[10],"sound":[11],"effects,":[12],"replacing":[13],"a":[14,31,82,140],"musical":[15],"instrument,":[16],"and":[17,33,61,138,145,153,179,204],"repairing":[18],"damaged":[19],"audio.":[20,44],"Recently,":[21],"some":[22,50],"diffusion-based":[23],"methods":[24,47],"achieved":[25],"zero-shot":[26],"audio":[27,72,107,135,150,192,209],"by":[29,172],"using":[30,143],"diffusion":[32,113,141],"denoising":[34],"process":[35],"conditioned":[36],"on":[37,58,111],"the":[38,42,86,174,177],"text":[39,195],"description":[40,84],"of":[41,85,189],"output":[43,87,131,155,180],"However,":[45],"these":[46],"still":[48],"have":[49,54],"problems:":[51],"1)":[52,122],"they":[53,68,80],"not":[55,76,91],"been":[56],"trained":[57],"tasks":[60,137,211],"cannot":[62],"ensure":[63],"good":[64],"effects;":[66],"2)":[67,158],"can":[69,160],"erroneously":[70],"modify":[71,165],"segments":[73,166],"that":[74,167],"do":[75],"require":[77],"editing;":[78],"3)":[79,182],"need":[81,168],"complete":[83],"audio,":[88,130],"which":[89],"always":[92],"available":[93,221],"or":[94],"necessary":[95],"in":[96,201],"practical":[97],"scenarios.":[98],"In":[99],"this":[100],"work,":[101],"we":[102,123],"propose":[103],"AUDIT,":[104],"an":[105],"instruction-guided":[106],"model":[109,142],"based":[110],"latent":[112],"models.":[114],"Specifically,":[115],"AUDIT":[116,197],"has":[117],"three":[118],"main":[119],"design":[120],"features:":[121],"construct":[124],"triplet":[125],"training":[126],"data":[127],"(instruction,":[128],"input":[129,146,178],"audio)":[132],"different":[134],"train":[139],"instruction":[144],"(to":[147],"be":[148,170],"edited)":[149],"conditions":[152],"generating":[154],"(edited)":[156],"audio;":[157,181],"it":[159,183],"automatically":[161],"learn":[162],"to":[163,169],"only":[164,184],"edited":[171],"comparing":[173],"difference":[175],"between":[176],"needs":[185],"edit":[186],"instructions":[187],"instead":[188],"full":[190],"target":[191],"descriptions":[193],"input.":[196],"achieves":[198],"state-of-the-art":[199],"results":[200],"both":[202],"objective":[203],"subjective":[205],"metrics":[206],"several":[208],"(e.g.,":[212],"adding,":[213],"dropping,":[214],"replacement,":[215],"inpainting,":[216],"super-resolution).":[217],"Demo":[218],"samples":[219],"are":[220],"at":[222],"https://audit-demo.github.io/.":[223]},"counts_by_year":[{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2023-04-06T00:00:00"}