{"id":"https://openalex.org/W4392909615","doi":"https://doi.org/10.1109/icassp48485.2024.10447898","title":"Retrieval-Augmented Text-to-Audio Generation","display_name":"Retrieval-Augmented Text-to-Audio Generation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909615","doi":"https://doi.org/10.1109/icassp48485.2024.10447898"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447898","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447898","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/A5101889011","display_name":"Yi Yuan","orcid":"https://orcid.org/0000-0002-7121-0983"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Yi Yuan","raw_affiliation_strings":["University of Surrey,School of Computer Science and Electronic Engineering,UK","School of Computer Science and Electronic Engineering, University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"University of Surrey,School of Computer Science and Electronic Engineering,UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"School of Computer Science and Electronic Engineering, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089924305","display_name":"Haohe Liu","orcid":"https://orcid.org/0000-0003-1036-7888"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Haohe Liu","raw_affiliation_strings":["University of Surrey,School of Computer Science and Electronic Engineering,UK","School of Computer Science and Electronic Engineering, University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"University of Surrey,School of Computer Science and Electronic Engineering,UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"School of Computer Science and Electronic Engineering, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080214850","display_name":"Xubo Liu","orcid":"https://orcid.org/0000-0002-2558-0959"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xubo Liu","raw_affiliation_strings":["University of Surrey,School of Computer Science and Electronic Engineering,UK","School of Computer Science and Electronic Engineering, University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"University of Surrey,School of Computer Science and Electronic Engineering,UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"School of Computer Science and Electronic Engineering, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103097683","display_name":"Qiushi Huang","orcid":"https://orcid.org/0009-0004-1441-7090"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Qiushi Huang","raw_affiliation_strings":["University of Surrey,School of Computer Science and Electronic Engineering,UK","School of Computer Science and Electronic Engineering, University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"University of Surrey,School of Computer Science and Electronic Engineering,UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"School of Computer Science and Electronic Engineering, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066967599","display_name":"Mark D. Plumbley","orcid":"https://orcid.org/0000-0002-9708-1075"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark D. Plumbley","raw_affiliation_strings":["University of Surrey,School of Computer Science and Electronic Engineering,UK","School of Computer Science and Electronic Engineering, University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"University of Surrey,School of Computer Science and Electronic Engineering,UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"School of Computer Science and Electronic Engineering, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["University of Surrey,School of Computer Science and Electronic Engineering,UK","School of Computer Science and Electronic Engineering, University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"University of Surrey,School of Computer Science and Electronic Engineering,UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"School of Computer Science and Electronic Engineering, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101889011"],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":7.1531,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.97829539,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"581","last_page":"585"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9926999807357788,"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":0.9926999807357788,"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":0.9793000221252441,"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":0.9771999716758728,"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":0.7649841904640198},{"id":"https://openalex.org/keywords/augmented-reality","display_name":"Augmented reality","score":0.4574945867061615},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3967725932598114},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.39211973547935486},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36257725954055786},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33979809284210205},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3313445448875427}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7649841904640198},{"id":"https://openalex.org/C153715457","wikidata":"https://www.wikidata.org/wiki/Q254183","display_name":"Augmented reality","level":2,"score":0.4574945867061615},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3967725932598114},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.39211973547935486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36257725954055786},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33979809284210205},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3313445448875427}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447898","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447898","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6100000143051147}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321979","display_name":"University of Surrey","ror":"https://ror.org/00ks66431"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2012210378","https://openalex.org/W2593116425","https://openalex.org/W3036167779","https://openalex.org/W3094550259","https://openalex.org/W3214281017","https://openalex.org/W4225744354","https://openalex.org/W4285483774","https://openalex.org/W4288089799","https://openalex.org/W4367359628","https://openalex.org/W4372260310","https://openalex.org/W4385245566","https://openalex.org/W4385328213","https://openalex.org/W4387969125","https://openalex.org/W4388118236","https://openalex.org/W4393792386","https://openalex.org/W6747491877","https://openalex.org/W6769627184","https://openalex.org/W6779823529","https://openalex.org/W6791353385","https://openalex.org/W6802805937","https://openalex.org/W6802938626","https://openalex.org/W6804678962","https://openalex.org/W6843210290","https://openalex.org/W6845479124","https://openalex.org/W6849109464","https://openalex.org/W6849416043","https://openalex.org/W6854083324","https://openalex.org/W6855691466"],"related_works":["https://openalex.org/W2172197285","https://openalex.org/W2991048842","https://openalex.org/W2750280393","https://openalex.org/W2355696739","https://openalex.org/W3158001554","https://openalex.org/W2771909920","https://openalex.org/W2957704286","https://openalex.org/W2028936041","https://openalex.org/W2179141964","https://openalex.org/W4383103690"],"abstract_inverted_index":{"Despite":[0],"recent":[1],"progress":[2],"in":[3,29,36,43,176],"text-to-audio":[4,60],"(TTA)":[5],"generation,":[6],"we":[7,66,81,154],"show":[8,155],"that":[9,156],"the":[10,44,49,99,111,125,132,146],"state-of-the-art":[11,138],"models,":[12],"such":[13,24],"as":[14,25,58,106,129],"AudioLDM,":[15],"trained":[16],"on":[17],"datasets":[18],"with":[19,119],"an":[20,77],"imbalanced":[21],"class":[22],"distribution,":[23],"AudioCaps,":[26],"are":[27,103],"biased":[28],"their":[30],"generation":[31,51],"performance.":[32,52],"Specifically,":[33,75],"they":[34],"excel":[35],"generating":[37],"common":[38],"audio":[39,161,166,171],"classes":[40],"while":[41],"underperforming":[42],"rare":[45,165],"ones,":[46],"thus":[47],"degrading":[48],"overall":[50],"We":[53,116],"refer":[54],"to":[55,91,109],"this":[56,64],"problem":[57],"long-tailed":[59],"generation.":[61],"To":[62],"address":[63],"issue,":[65],"propose":[67],"a":[68,84,137,150],"simple":[69],"retrieval-augmented":[70],"approach":[71,122],"for":[72,162],"TTA":[73,114,177],"models.":[74,115],"given":[76],"input":[78],"text":[79],"prompt,":[80],"first":[82],"leverage":[83],"Contrastive":[85],"Language":[86],"Audio":[87,140],"Pretraining":[88],"(CLAP)":[89],"model":[90],"retrieve":[92],"relevant":[93],"text-audio":[94],"pairs.":[95],"The":[96],"features":[97],"of":[98,113,143],"retrieved":[100],"audio-text":[101],"data":[102],"then":[104],"used":[105],"additional":[107],"conditions":[108],"guide":[110],"learning":[112],"enhance":[117],"AudioLDM":[118],"our":[120],"proposed":[121],"and":[123,168],"denote":[124],"resulting":[126],"augmented":[127],"system":[128],"Re-AudioLDM.":[130],"On":[131],"AudioCaps":[133],"dataset,":[134],"Re-AudioLDM":[135,157],"achieves":[136],"Frechet":[139],"Distance":[141],"(FAD)":[142],"1.37,":[144],"outperforming":[145],"existing":[147],"approaches":[148],"by":[149],"large":[151],"margin.":[152],"Furthermore,":[153],"can":[158],"generate":[159],"realistic":[160],"complex":[163],"scenes,":[164],"classes,":[167],"even":[169],"unseen":[170],"types,":[172],"indicating":[173],"its":[174],"potential":[175],"tasks.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}