{"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","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.673","pdf_url":null,"source":null,"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"},"type":"conference-paper","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/A5070862393","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/A5100628037","display_name":"Jialei Wang","orcid":"https://orcid.org/0000-0001-9581-0855"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jialei Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002111548","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/A5100351175","display_name":"Yan Liu","orcid":"https://orcid.org/0000-0003-4242-4840"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100618443","display_name":"Heng Lu","orcid":"https://orcid.org/0009-0009-9236-8825"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heng Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Wei Xue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Xue","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":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T11309","display_name":"Music and Audio Processing","score":0.996999979019165,"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":0.996999979019165,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9812999963760376,"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"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9726999998092651,"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/high-fidelity","display_name":"High fidelity","score":0.8691881895065308},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7098100185394287},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49184298515319824},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.4288710057735443},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4134734570980072},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.33436673879623413},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2428317666053772},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.2416365146636963},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.14692029356956482},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11688157916069031}],"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","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.673","pdf_url":null,"source":null,"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":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4214484837","https://openalex.org/W2770826937","https://openalex.org/W3096216989","https://openalex.org/W2092939625","https://openalex.org/W3024531078","https://openalex.org/W4403577965","https://openalex.org/W1485007384","https://openalex.org/W2351240864","https://openalex.org/W4404047562","https://openalex.org/W1965270928"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}