{"id":"https://openalex.org/W4392909604","doi":"https://doi.org/10.1109/icassp48485.2024.10446431","title":"In-Context Prompt Editing for Conditional Audio Generation","display_name":"In-Context Prompt Editing for Conditional Audio Generation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909604","doi":"https://doi.org/10.1109/icassp48485.2024.10446431"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446431","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5021305048","display_name":"Ernie Chang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ernie Chang","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104260168","display_name":"Pin-Jie Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Pin-Jie Lin","raw_affiliation_strings":["Saarland University,Language Science and Technology","Language Science and Technology, Saarland University"],"affiliations":[{"raw_affiliation_string":"Saarland University,Language Science and Technology","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"Language Science and Technology, Saarland University","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100421802","display_name":"Yang Li","orcid":"https://orcid.org/0000-0003-4022-7341"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Li","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104345534","display_name":"Sidd Srinivasan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sidd Srinivasan","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012026156","display_name":"Ga\u00ebl Le Lan","orcid":"https://orcid.org/0000-0002-1493-5777"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gael Le Lan","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019683792","display_name":"David Kant","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Kant","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103247973","display_name":"Yangyang Shi","orcid":"https://orcid.org/0000-0001-5297-4155"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yangyang Shi","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031485831","display_name":"Forrest Iandola","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Forrest Iandola","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016704219","display_name":"Vikas Chandra","orcid":"https://orcid.org/0009-0005-4996-8455"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vikas Chandra","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5021305048"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7471,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65353108,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5320","last_page":"5324"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9898999929428101,"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":0.9898999929428101,"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/T10860","display_name":"Speech and Audio Processing","score":0.987500011920929,"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":0.9708999991416931,"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":0.7659797668457031},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5393685102462769},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4278488755226135}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7659797668457031},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5393685102462769},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4278488755226135},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446431","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2123402141","https://openalex.org/W2132069633","https://openalex.org/W2945761034","https://openalex.org/W2965373594","https://openalex.org/W2970641574","https://openalex.org/W2972478942","https://openalex.org/W2998702515","https://openalex.org/W4221143046","https://openalex.org/W4288089799","https://openalex.org/W4292779060","https://openalex.org/W4318351475","https://openalex.org/W4318752004","https://openalex.org/W4319653572","https://openalex.org/W4322718191","https://openalex.org/W4367359628","https://openalex.org/W4367369802","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4385567149","https://openalex.org/W6769627184","https://openalex.org/W6778883912","https://openalex.org/W6809646742"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Distributional":[0],"shift":[1],"is":[2,22],"a":[3,72,95],"central":[4],"challenge":[5],"in":[6,25,60,77],"the":[7,29,41,47,51,61,103,111,117,120,124,136],"deployment":[8],"of":[9,43,50,126],"machine":[10],"learning":[11],"models":[12],"as":[13,63,84,106,139],"they":[14],"can":[15],"be":[16],"ill-equipped":[17],"for":[18,56],"real-world":[19],"data.":[20],"This":[21],"particularly":[23],"evident":[24],"text-to-audio":[26],"generation":[27,59],"where":[28],"encoded":[30],"representations":[31],"are":[32,66],"easily":[33],"undermined":[34],"by":[35],"unseen":[36],"prompts,":[37,83,129],"which":[38,130],"leads":[39],"to":[40,86,109,135],"degradation":[42,76],"generated":[44,78],"audio":[45,58,74,79,121],"\u2014":[46],"limited":[48],"set":[49,88,125],"text-audio":[52],"pairs":[53],"remains":[54],"inadequate":[55],"conditional":[57],"wild":[62],"user":[64,82,112,128],"prompts":[65],"under-specified.":[67],"In":[68],"particular,":[69],"we":[70,93],"observe":[71],"consistent":[73],"quality":[75,122],"samples":[80],"with":[81,133],"opposed":[85],"training":[87,104,137],"prompts.":[89,113],"To":[90],"this":[91],"end,":[92],"present":[94],"retrieval-based":[96],"in-context":[97],"prompt":[98],"editing":[99],"framework":[100,118],"that":[101,116],"leverages":[102],"captions":[105,138],"demonstrative":[107],"exemplars":[108],"revisit":[110],"We":[114],"show":[115],"enhanced":[119],"across":[123],"collected":[127],"were":[131],"edited":[132],"reference":[134],"exemplars.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
