{"id":"https://openalex.org/W4392903258","doi":"https://doi.org/10.1109/icassp48485.2024.10447897","title":"On the Open Prompt Challenge in Conditional Audio Generation","display_name":"On the Open Prompt Challenge in Conditional Audio Generation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903258","doi":"https://doi.org/10.1109/icassp48485.2024.10447897"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447897","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447897","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/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/A5093192269","display_name":"Mahi Luthra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mahi Luthra","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113145193","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/A5034208747","display_name":"Varun Nagaraja","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Varun Nagaraja","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":"middle","author":{"id":"https://openalex.org/A5085241696","display_name":"Zechun Liu","orcid":"https://orcid.org/0000-0001-5856-2506"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zechun Liu","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031088292","display_name":"Zhaoheng Ni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaoheng Ni","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109628225","display_name":"Changsheng Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changsheng Zhao","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":"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":11,"corresponding_author_ids":["https://openalex.org/A5021305048"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7501,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65242531,"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":"5315","last_page":"5319"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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/computer-science","display_name":"Computer science","score":0.843605637550354},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6222752928733826},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5858547687530518},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5648194551467896},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.53817218542099},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.49566543102264404},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.44251227378845215},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4396754503250122},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3601676821708679},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3344643712043762},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2347184419631958}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.843605637550354},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6222752928733826},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5858547687530518},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5648194551467896},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.53817218542099},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.49566543102264404},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.44251227378845215},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4396754503250122},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3601676821708679},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3344643712043762},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2347184419631958},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447897","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447897","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2139450036","https://openalex.org/W2963532001","https://openalex.org/W2979826702","https://openalex.org/W4293138840","https://openalex.org/W4300980117","https://openalex.org/W4307079201","https://openalex.org/W4308014717","https://openalex.org/W4311991106","https://openalex.org/W4318351475","https://openalex.org/W4318752004","https://openalex.org/W4367359628","https://openalex.org/W4367369802","https://openalex.org/W4372266552","https://openalex.org/W6748230616","https://openalex.org/W6777469961","https://openalex.org/W6790978476","https://openalex.org/W6842239938","https://openalex.org/W6845479124","https://openalex.org/W6846739993","https://openalex.org/W6847076894","https://openalex.org/W6847753483","https://openalex.org/W6849105126","https://openalex.org/W6849109464","https://openalex.org/W6852922743"],"related_works":["https://openalex.org/W3125011624","https://openalex.org/W1508631387","https://openalex.org/W2370917603","https://openalex.org/W2952760143","https://openalex.org/W2017776670","https://openalex.org/W2347897961","https://openalex.org/W2340870721","https://openalex.org/W2358318464","https://openalex.org/W2979236518","https://openalex.org/W2119384858"],"abstract_inverted_index":{"Text-to-audio":[0],"generation":[1,21],"(TTA)":[2],"produces":[3],"audio":[4,13,20,84,125,144],"from":[5,10],"a":[6,48,68,81],"text":[7,33],"description,":[8],"learning":[9,123],"pairs":[11],"of":[12,83],"samples":[14],"and":[15,50,75,112,130,142],"hand-annotated":[16],"text.":[17],"However,":[18],"commercializing":[19],"is":[22,80],"challenging":[23],"as":[24,47,101,117],"user-input":[25],"prompts":[26,62,74,108],"are":[27,63,90],"often":[28],"under-specified":[29],"when":[30],"compared":[31],"to":[32,36,67,100],"descriptions":[34,85],"used":[35],"train":[37],"TTA":[38,45,88],"models.":[39],"In":[40],"this":[41,104],"work,":[42],"we":[43,98,106,134],"treat":[44],"models":[46,89,111],"\"blackbox\"":[49],"address":[51],"the":[52],"user":[53,73],"prompt":[54],"challenge":[55],"with":[56,109],"two":[57],"key":[58],"insights:":[59],"(1)":[60],"User":[61],"generally":[64],"under-specified,":[65],"leading":[66],"large":[69],"alignment":[70,116,141],"gap":[71],"between":[72],"training":[76],"prompts.":[77],"(2)":[78],"There":[79],"distribution":[82],"for":[86,124],"which":[87,97],"better":[91],"at":[92],"generating":[93],"higher":[94],"quality":[95],"audio,":[96],"refer":[99],"\"audionese\".":[102],"To":[103],"end,":[105],"rewrite":[107],"instruction-tuned":[110],"propose":[113],"utilizing":[114],"text-audio":[115,140],"feedback":[118],"signals":[119],"via":[120],"margin":[121],"ranking":[122],"improvements.":[126],"On":[127],"both":[128,139],"objective":[129],"subjective":[131],"human":[132],"evaluations,":[133],"observed":[135],"marked":[136],"improvements":[137],"in":[138],"music":[143],"quality.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
