{"id":"https://openalex.org/W4417117965","doi":"https://doi.org/10.18653/v1/2026.acl-long.62","title":"ControlAudio: Tackling Text-Guided, Timing-Indicated and Intelligible Audio Generation via Progressive Diffusion Modeling","display_name":"ControlAudio: Tackling Text-Guided, Timing-Indicated and Intelligible Audio Generation via Progressive Diffusion Modeling","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4417117965","doi":"https://doi.org/10.18653/v1/2026.acl-long.62"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.62","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.62","pdf_url":"https://aclanthology.org/2026.acl-long.62.pdf","source":null,"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"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.62.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yuxuan Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxuan Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061402916","display_name":"Zehua Chen","orcid":"https://orcid.org/0009-0000-2294-7447"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zehua Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073017662","display_name":"Zeqian Ju","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeqian Ju","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101237516","display_name":"Yusheng Dai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yusheng Dai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101473085","display_name":"Weibei Dou","orcid":"https://orcid.org/0000-0001-8555-2776"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weibei Dou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103865065","display_name":"Jun Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05672403,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1394","last_page":"1413"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.4138000011444092,"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/T10860","display_name":"Speech and Audio Processing","score":0.4138000011444092,"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":0.18629999458789825,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.10620000213384628,"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/inference","display_name":"Inference","score":0.6097000241279602},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5893999934196472},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4343000054359436},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4172999858856201},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4077000021934509},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.38510000705718994},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3278999924659729},{"id":"https://openalex.org/keywords/approximate-inference","display_name":"Approximate inference","score":0.32269999384880066},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.32109999656677246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8019000291824341},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6097000241279602},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5893999934196472},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5504999756813049},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46799999475479126},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4343000054359436},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4172999858856201},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4077000021934509},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.38510000705718994},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.32269999384880066},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.27230000495910645},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26930001378059387},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25119999051094055}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.62","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.62","pdf_url":"https://aclanthology.org/2026.acl-long.62.pdf","source":null,"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:2510.08878","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.08878","pdf_url":"https://arxiv.org/pdf/2510.08878","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,"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.2510.08878","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.08878","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,"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.62","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.62","pdf_url":"https://aclanthology.org/2026.acl-long.62.pdf","source":null,"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":[],"awards":[{"id":"https://openalex.org/G2599639279","display_name":null,"funder_award_id":"U24A20342","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4942433383","display_name":null,"funder_award_id":"62550004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6348164415","display_name":null,"funder_award_id":"92570001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8171804304","display_name":null,"funder_award_id":"JYB2025XDXM101","funder_id":"https://openalex.org/F4320321106","funder_display_name":"Ministry of Education of the People's Republic of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321106","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417117965.pdf","grobid_xml":"https://content.openalex.org/works/W4417117965.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Text-to-audio":[0],"(TTA)":[1],"generation":[2,26,39],"with":[3,122,145],"finegrained":[4],"control":[5,10],"signals,":[6],"e.g.,":[7],"precise":[8],"timing":[9,118],"or":[11],"intelligible":[12],"speech":[13,165],"content,":[14],"has":[15],"been":[16],"explored":[17],"in":[18,86,159],"recent":[19],"works.However,":[20],"constrained":[21],"by":[22],"data":[23,75],"scarcity,":[24],"their":[25],"performance":[27,158],"at":[28,94,128],"scale":[29],"is":[30],"still":[31],"compromised.In":[32],"this":[33],"study,":[34],"we":[35,72,99,132],"recast":[36],"controllable":[37],"TTA":[38,111],"as":[40],"a":[41,47,69,74,101],"multi-task":[42],"learning":[43],"problem":[44],"and":[45,65,81,92,113,119,164,174],"introduce":[46],"progressive":[48],"diffusion":[49,102],"modeling":[50],"approach,":[51],"Con-trolAudio.Our":[52],"method":[53,77],"adeptly":[54],"fits":[55],"distributions":[56],"conditioned":[57],"on":[58,105,171],"more":[59,140],"fine-grained":[60,141],"information,":[61,142],"including":[62],"text,":[63,90],"timing,":[64,91],"phoneme":[66,120],"features,":[67],"through":[68],"step-by-step":[70],"strategy.First,":[71],"propose":[73,133],"construction":[76],"spanning":[78],"both":[79,172],"annotation":[80],"simulation,":[82],"augmenting":[83],"condition":[84],"information":[85],"the":[87,95,117,129,146],"sequence":[88],"of":[89,150,161],"phoneme.Second,":[93],"model":[96],"training":[97],"stage,":[98,131],"pretrain":[100],"transformer":[103],"(DiT)":[104],"large-scale":[106],"text-audio":[107],"pairs,":[108],"achieving":[109],"scalable":[110],"generation,":[112,136],"then":[114],"incrementally":[115],"integrate":[116],"features":[121],"unified":[123],"semantic":[124],"representations,":[125],"expanding":[126],"controllability.Finally,":[127],"inference":[130],"progressively":[134],"guided":[135],"which":[137],"sequentially":[138],"emphasizes":[139],"aligning":[143],"inherently":[144],"coarse-tofine":[147],"sampling":[148],"nature":[149],"DiT.Extensive":[151],"experiments":[152],"show":[153],"that":[154],"ControlAudio":[155],"achieves":[156],"stateof-the-art":[157],"terms":[160],"temporal":[162],"accuracy":[163],"clarity,":[166],"significantly":[167],"outperforming":[168],"existing":[169],"methods":[170],"objective":[173],"subjective":[175],"evaluations.Demo":[176],"samples":[177],"are":[178],"available":[179],"at:":[180]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-14T00:00:00"}