{"id":"https://openalex.org/W4415192575","doi":"https://doi.org/10.18653/v1/2026.acl-long.654","title":"MeanAudio: Fast and Faithful Text-to-Audio Generation with Mean Flows","display_name":"MeanAudio: Fast and Faithful Text-to-Audio Generation with Mean Flows","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4415192575","doi":"https://doi.org/10.18653/v1/2026.acl-long.654"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.654","doi":"https://doi.org/10.18653/v1/2026.acl-long.654","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.654","pdf_url":"https://aclanthology.org/2026.acl-long.654.pdf","source":{"id":"https://openalex.org/S4363608652","display_name":"Annual Meeting of the Association for Computational Linguistics (ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.acl-long.654.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104326367","display_name":"Xiquan Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiquan Li","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence , X-LANCE Lab Department of Computer Science , Shanghai Jiao Tong University , China","SJTU Paris Elite Institute of Technology , Shanghai Jiao Tong University , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence , X-LANCE Lab Department of Computer Science , Shanghai Jiao Tong University , China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"SJTU Paris Elite Institute of Technology , Shanghai Jiao Tong University , China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Junxi Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junxi Liu","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence , X-LANCE Lab Department of Computer Science , Shanghai Jiao Tong University , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence , X-LANCE Lab Department of Computer Science , Shanghai Jiao Tong University , China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114117046","display_name":"Yuzhe Liang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuzhe Liang","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence , X-LANCE Lab Department of Computer Science , Shanghai Jiao Tong University , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence , X-LANCE Lab Department of Computer Science , Shanghai Jiao Tong University , China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108896784","display_name":"Zhikang Niu","orcid":"https://orcid.org/0009-0007-1880-7434","observed_orcids":["https://orcid.org/0009-0007-1880-7434"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhikang Niu","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence , X-LANCE Lab Department of Computer Science , Shanghai Jiao Tong University , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence , X-LANCE Lab Department of Computer Science , Shanghai Jiao Tong University , China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082539414","display_name":"Wenxi Chen","orcid":"https://orcid.org/0000-0001-9329-7277","observed_orcids":["https://orcid.org/0000-0001-9329-7277"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxi Chen","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence , X-LANCE Lab Department of Computer Science , Shanghai Jiao Tong University , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence , X-LANCE Lab Department of Computer Science , Shanghai Jiao Tong University , China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100329117","display_name":"Xie Chen","orcid":"https://orcid.org/0000-0001-7423-617X","observed_orcids":["https://orcid.org/0000-0001-7423-617X"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie Chen","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence , X-LANCE Lab Department of Computer Science , Shanghai Jiao Tong University , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence , X-LANCE Lab Department of Computer Science , Shanghai Jiao Tong University , China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":27.1126,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.99340464,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"14378","last_page":"14393"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.5806000232696533,"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":0.5806000232696533,"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/T11309","display_name":"Music and Audio Processing","score":0.2101999968290329,"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":0.15230000019073486,"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/text-to-audio-generation","display_name":"text-to-audio generation","score":0.996999979019165},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.5490000247955322},{"id":"https://openalex.org/keywords/inference-speed","display_name":"inference speed","score":0.5059999823570251},{"id":"https://openalex.org/keywords/flux-transformer","display_name":"flux transformer","score":0.656000018119812},{"id":"https://openalex.org/keywords/curriculum-learning","display_name":"curriculum learning","score":0.5699999928474426},{"id":"https://openalex.org/keywords/real-time-factor","display_name":"real-time factor","score":0.8080000281333923},{"id":"https://openalex.org/keywords/sound-synthesis","display_name":"sound synthesis","score":0.6470000147819519}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7074999809265137},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6977999806404114},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5541999936103821},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5449000000953674},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.522599995136261},{"id":"https://openalex.org/C147297375","wikidata":"https://www.wikidata.org/wiki/Q6674930","display_name":"Look-ahead","level":2,"score":0.4823000133037567},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.450300008058548},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45019999146461487},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3781999945640564},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.36559998989105225},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.32989999651908875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32829999923706055},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.31060001254081726},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2648000121116638},{"id":"https://openalex.org/C164620267","wikidata":"https://www.wikidata.org/wiki/Q376953","display_name":"Adder","level":3,"score":0.26330000162124634},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.25380000472068787}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.654","doi":"https://doi.org/10.18653/v1/2026.acl-long.654","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.654","pdf_url":"https://aclanthology.org/2026.acl-long.654.pdf","source":{"id":"https://openalex.org/S4363608652","display_name":"Annual Meeting of the Association for Computational Linguistics (ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.06098","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.06098","pdf_url":"https://arxiv.org/pdf/2508.06098","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2508.06098","doi":"https://doi.org/10.48550/arxiv.2508.06098","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.06098","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.654","doi":"https://doi.org/10.18653/v1/2026.acl-long.654","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.654","pdf_url":"https://aclanthology.org/2026.acl-long.654.pdf","source":{"id":"https://openalex.org/S4363608652","display_name":"Annual Meeting of the Association for Computational Linguistics (ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3278014984","display_name":null,"funder_award_id":"U23B2018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8721642152","display_name":null,"funder_award_id":"2021SHZDZX0102","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/W4415192575.pdf","grobid_xml":"https://content.openalex.org/works/W4415192575.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2],"witnessed":[3],"remarkable":[4],"progress":[5],"in":[6,123,155],"Text-to-Audio":[7],"Generation":[8],"(TTA),":[9],"providing":[10],"sound":[11,59],"creators":[12],"with":[13,60,71,85],"powerful":[14],"tools":[15],"to":[16],"transform":[17],"inspirations":[18],"into":[19],"vivid":[20],"audio.Yet":[21],"despite":[22],"these":[23],"advances,":[24],"current":[25],"TTA":[26,148],"systems":[27],"often":[28],"suffer":[29],"from":[30],"slow":[31],"inference":[32,78],"speed,":[33,79],"which":[34],"greatly":[35],"hinders":[36],"the":[37,68],"efficiency":[38],"and":[39,51,93,96,106],"smoothness":[40],"of":[41,56,133],"audio":[42,125],"creation.In":[43],"this":[44],"paper,":[45],"we":[46,116],"present":[47],"MeanAudio,":[48],"a":[49,112,129,136,142],"fast":[50],"faithful":[52],"textto-audio":[53],"generator":[54],"capable":[55],"rendering":[57],"realistic":[58],"only":[61],"one":[62],"function":[63],"evaluation":[64,114],"(1-NFE).MeanAudio":[65],"leverages:":[66],"(i)":[67],"MeanFlow":[69],"objective":[70],"guided":[72],"velocity":[73],"target":[74],"that":[75,102,118],"significantly":[76],"accelerates":[77],"(ii)":[80],"an":[81,98],"enhanced":[82],"Flux-style":[83],"transformer":[84],"dual":[86],"text":[87],"encoders":[88],"for":[89],"better":[90],"semantic":[91],"alignment":[92],"synthesis":[94,163],"quality,":[95],"(iii)":[97],"efficient":[99],"instantaneous-to-mean":[100],"curriculum":[101],"speeds":[103],"up":[104],"convergence":[105],"enables":[107],"training":[108],"on":[109,135],"consumer-grade":[110],"GPUs.Through":[111],"comprehensive":[113],"study,":[115],"demonstrate":[117],"MeanAudio":[119,150],"achieves":[120,128],"state-of-the-art":[121],"performance":[122,154],"single-step":[124],"generation.Specifically,":[126],"it":[127],"real-time":[130],"factor":[131],"(RTF)":[132],"0.013":[134],"single":[137],"NVIDIA":[138],"RTX":[139],"3090,":[140],"yielding":[141],"100x":[143],"speedup":[144],"over":[145],"SOTA":[146],"diffusion-based":[147],"systems.Moreover,":[149],"also":[151],"shows":[152],"strong":[153],"multi-step":[156],"generation,":[157],"enabling":[158],"smooth":[159],"transitions":[160],"across":[161],"successive":[162],"steps.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-15T00:00:00"}