{"id":"https://openalex.org/W4412945331","doi":"https://doi.org/10.18653/v1/2025.acl-long.673","title":"FlashAudio: Rectified Flow for Fast and High-Fidelity Text-to-Audio Generation","display_name":"FlashAudio: Rectified Flow for Fast and High-Fidelity Text-to-Audio Generation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945331","doi":"https://doi.org/10.18653/v1/2025.acl-long.673"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.673","doi":"https://doi.org/10.18653/v1/2025.acl-long.673","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.673","pdf_url":"https://aclanthology.org/2025.acl-long.673.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2025.acl-long.673.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070862393","display_name":"Huadai Liu","orcid":"https://orcid.org/0009-0004-5782-5641","observed_orcids":["https://orcid.org/0009-0004-5782-5641"]},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN","HK","KY"],"is_corresponding":false,"raw_author_name":"Huadai Liu","raw_affiliation_strings":["Hong Kong University of Science and Technology","Tongyi Lab , Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Tongyi Lab , Alibaba Group","institution_ids":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100628037","display_name":"Jialei Wang","orcid":"https://orcid.org/0000-0001-9581-0855","observed_orcids":["https://orcid.org/0000-0001-9581-0855"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jialei Wang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002111548","display_name":"Rongjie Huang","orcid":"https://orcid.org/0009-0004-2827-9485","observed_orcids":["https://orcid.org/0009-0004-2827-9485"]},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rongjie Huang","raw_affiliation_strings":["Fundamental AI Research (FAIR) , Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fundamental AI Research (FAIR) , Meta","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yang Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100618443","display_name":"Heng Lu","orcid":"https://orcid.org/0009-0009-9236-8825","observed_orcids":["https://orcid.org/0009-0009-9236-8825"]},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN","KY"],"is_corresponding":false,"raw_author_name":"Heng Lu","raw_affiliation_strings":["Tongyi Lab , Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab , Alibaba Group","institution_ids":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384","observed_orcids":["https://orcid.org/0000-0001-6121-0384","https://orcid.org/0000-0002-6651-1802"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100652844","display_name":"Wei Xue","orcid":"https://orcid.org/0000-0002-4942-7748","observed_orcids":["https://orcid.org/0000-0002-4942-7748"]},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wei Xue","raw_affiliation_strings":["Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8993,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.85489344,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"13694","last_page":"13710"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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/T10860","display_name":"Speech and Audio Processing","score":0.00039999998989515007,"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/T11309","display_name":"Music and Audio Processing","score":0.00019999999494757503,"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/text-to-speech","display_name":"text-to-speech","score":0.8930000066757202},{"id":"https://openalex.org/keywords/audio-generation","display_name":"audio generation","score":0.7099999785423279},{"id":"https://openalex.org/keywords/rectified-flow","display_name":"rectified flow","score":0.8339999914169312},{"id":"https://openalex.org/keywords/flow-based-generative-models","display_name":"flow-based generative models","score":0.6399999856948853},{"id":"https://openalex.org/keywords/high-fidelity-audio","display_name":"high-fidelity audio","score":0.7870000004768372},{"id":"https://openalex.org/keywords/fast-inference","display_name":"fast inference","score":0.5450000166893005}],"concepts":[{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.8691881895065308},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7098100185394287},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49184298515319824},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.4288710057735443},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4134734570980072},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.33436673879623413},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2428317666053772},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2416365146636963},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.14692029356956482},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11688157916069031},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.673","doi":"https://doi.org/10.18653/v1/2025.acl-long.673","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.673","pdf_url":"https://aclanthology.org/2025.acl-long.673.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.673","doi":"https://doi.org/10.18653/v1/2025.acl-long.673","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.673","pdf_url":"https://aclanthology.org/2025.acl-long.673.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4331663528","display_name":null,"funder_award_id":"62206234","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6072681302","display_name":null,"funder_award_id":"62222211","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945331.pdf","grobid_xml":"https://content.openalex.org/works/W4412945331.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4403791956","https://openalex.org/W4415433990","https://openalex.org/W7196942016","https://openalex.org/W7202374882","https://openalex.org/W7133245521","https://openalex.org/W7220746160","https://openalex.org/W4402111476","https://openalex.org/W4412944824","https://openalex.org/W4415433492","https://openalex.org/W4402112245"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,99],"latent":[3],"diffusion":[4,49],"models":[5,145],"(LDMs)":[6],"have":[7],"markedly":[8],"enhanced":[9],"text-toaudio":[10],"generation,":[11],"yet":[12],"their":[13,36],"iterative":[14],"sampling":[15,149,157],"processes":[16],"impose":[17],"substantial":[18],"computational":[19],"demands,":[20],"limiting":[21],"practical":[22],"deployment.While":[23],"recent":[24],"methods":[25],"utilizing":[26],"consistency-based":[27],"distillation":[28],"aim":[29],"to":[30,59,91,104,128],"achieve":[31],"few-step":[32],"or":[33],"single-step":[34],"inference,":[35],"one-step":[37,139],"performance":[38,141],"is":[39],"constrained":[40],"by":[41,111,125],"curved":[42],"trajectories,":[43],"preventing":[44],"them":[45],"from":[46],"surpassing":[47],"traditional":[48],"models.In":[50],"this":[51],"work,":[52],"we":[53,116],"introduce":[54],"FlashAudio":[55,76],"with":[56,84,146],"rectified":[57,82],"flows":[58],"learn":[60],"straight":[61],"flow":[62,83,90],"for":[63],"fast":[64],"simulation.To":[65],"alleviate":[66],"the":[67,78,93,106,112,122,143],"inefficient":[68],"timesteps":[69],"allocation":[70],"and":[71,87,154],"suboptimal":[72],"distribution":[73,80],"of":[74,81,96,148,159],"noise,":[75],"optimizes":[77],"time":[79],"Bifocal":[85],"Samplers":[86],"proposes":[88],"immiscible":[89],"minimize":[92],"total":[94],"distance":[95],"data-noise":[97],"pairs":[98],"a":[100,129,156,165],"batch":[101],"vias":[102],"assignment.Furthermore,":[103],"address":[105],"amplified":[107],"accumulation":[108],"error":[109],"caused":[110],"classifierfree":[113],"guidance":[114,123],"(CFG),":[115],"propose":[117],"Anchored":[118],"Optimization,":[119],"which":[120],"refines":[121],"scale":[124],"anchoring":[126],"it":[127],"reference":[130],"trajectory.Experimental":[131],"results":[132],"on":[133,151,164],"text-to-audio":[134],"generation":[135,140],"demonstrate":[136],"that":[137],"FlashAudio's":[138],"surpasses":[142],"diffusion-based":[144],"hundreds":[147],"steps":[150],"audio":[152],"quality":[153],"enables":[155],"speed":[158],"400x":[160],"faster":[161],"than":[162],"real-time":[163],"single":[166],"NVIDIA":[167],"4090Ti":[168],"GPU.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2025-10-10T00:00:00"}