{"id":"https://openalex.org/W7166828534","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1891","title":"Masked Text-to-Audio Flow-Matching and Reward Feedback Optimization","display_name":"Masked Text-to-Audio Flow-Matching and Reward Feedback Optimization","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166828534","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1891"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1891","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1891","pdf_url":"https://aclanthology.org/2026.findings-acl.1891.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1891.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139831505","display_name":"Rongjie Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rongjie Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139831901","display_name":"Dongchao Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongchao Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139726814","display_name":"Wenxiang Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenxiang Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139756723","display_name":"Huadai Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huadai Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009897266","display_name":"Xize Cheng","orcid":"https://orcid.org/0000-0001-9708-3225"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xize Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139815751","display_name":"Zehan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zehan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139730851","display_name":"Zhou Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139831090","display_name":"Xixin Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xixin Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5121085903","display_name":"Helen M. Meng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Helen M. Meng","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":0.86021161,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"37953","last_page":"37966"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.3100999891757965,"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":0.3100999891757965,"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":0.16249999403953552,"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/T12031","display_name":"Speech and dialogue systems","score":0.061500001698732376,"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/control-theory","display_name":"Control theory (sociology)","score":0.4004000127315521},{"id":"https://openalex.org/keywords/feedback-control","display_name":"Feedback control","score":0.34700000286102295},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.33059999346733093},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.31459999084472656},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.31150001287460327},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.295199990272522}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5338000059127808},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4004000127315521},{"id":"https://openalex.org/C3018651601","wikidata":"https://www.wikidata.org/wiki/Q183635","display_name":"Feedback control","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.31150001287460327},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29499998688697815},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C186886427","wikidata":"https://www.wikidata.org/wiki/Q5441213","display_name":"Feedback loop","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2556000053882599},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1891","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1891","pdf_url":"https://aclanthology.org/2026.findings-acl.1891.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1891","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1891","pdf_url":"https://aclanthology.org/2026.findings-acl.1891.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G782430798","display_name":null,"funder_award_id":"62306260","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"},{"id":"https://openalex.org/F4320321920","display_name":"Innovation and Technology Commission","ror":"https://ror.org/04vf9tr09"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166828534.pdf","grobid_xml":"https://content.openalex.org/works/W7166828534.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Flow-matching":[0],"generative":[1,40],"models":[2],"have":[3],"created":[4],"significant":[5],"milestones":[6],"in":[7,55,112],"text-to-audio":[8,45,113],"generation,":[9,114],"powered":[10],"by":[11],"scalable":[12,24],"training":[13,56],"with":[14,38,64],"increased":[15],"data,":[16],"computational":[17],"resources,":[18],"and":[19,57,67,79,90,102,131],"model":[20,125],"size,":[21],"while":[22],"their":[23],"inference":[25,70],"remains":[26],"less":[27],"explored.In":[28],"this":[29],"work,":[30],"we":[31,75,93],"propose":[32],"MaskAudioFlow,":[33],"a":[34],"continuous":[35,60],"flow-matching":[36,65],"transformer":[37],"masked":[39,72,121],"modeling":[41],"designed":[42],"for":[43],"scaling":[44,116],"inferencetime":[46],"prediction.Specifically,":[47],"MaskAudioFlow":[48,95,108],"1)":[49],"masks":[50],"spans":[51],"of":[52],"audio":[53],"frames":[54],"approximates":[58],"the":[59,86,123],"velocity":[61],"vector":[62],"field":[63],"objective,":[66],"2)":[68],"performs":[69],"via":[71],"prediction,":[73],"where":[74],"mask":[76],"out":[77],"generation":[78,89],"re-predict":[80],"them":[81],"through":[82,119],"iterative":[83,120],"decoding.To":[84],"reduce":[85],"gap":[87],"between":[88],"human":[91],"preferences,":[92],"fine-tune":[94],"using":[96],"reward":[97],"signals":[98],"from":[99],"text-audio":[100,128],"correspondence":[101],"perceptual":[103,133],"aesthetics.Experimental":[104],"results":[105],"demonstrate":[106],"that":[107],"achieves":[109],"state-of-the-art":[110],"performance":[111],"effectively":[115],"inference-time":[117],"computation":[118],"prediction.Moreover,":[122],"preference-tuned":[124],"demonstrates":[126],"superior":[127],"alignment":[129],"faithfulness":[130],"enhanced":[132],"aesthetics.":[134],"1":[135]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}