{"id":"https://openalex.org/W4412945617","doi":"https://doi.org/10.18653/v1/2025.acl-long.313","title":"F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching","display_name":"F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945617","doi":"https://doi.org/10.18653/v1/2025.acl-long.313"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.313","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.313","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/A5079946802","display_name":"Yushen Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yushen Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108896784","display_name":"Zhikang Niu","orcid":"https://orcid.org/0009-0002-2709-9381"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhikang Niu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438492","display_name":"Ziyang Ma","orcid":"https://orcid.org/0000-0002-0623-9114"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyang Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068367173","display_name":"Keqi Deng","orcid":"https://orcid.org/0000-0003-1490-963X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keqi Deng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115695439","display_name":"Chunhui Wang","orcid":"https://orcid.org/0009-0009-7178-5742"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chunhui Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119204549","display_name":"JianZhao JianZhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"JianZhao JianZhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101293966","display_name":"Xie Chen","orcid":"https://orcid.org/0000-0001-7423-617X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie Chen","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":94.8972,"has_fulltext":false,"cited_by_count":69,"citation_normalized_percentile":{"value":0.99989591,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6255","last_page":"6271"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.929099977016449,"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":0.929099977016449,"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/computer-science","display_name":"Computer science","score":0.6836843490600586},{"id":"https://openalex.org/keywords/fluent","display_name":"Fluent","score":0.6061331033706665},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5027234554290771},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4756966531276703},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09541106224060059}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6836843490600586},{"id":"https://openalex.org/C2780411076","wikidata":"https://www.wikidata.org/wiki/Q5462653","display_name":"Fluent","level":3,"score":0.6061331033706665},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5027234554290771},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4756966531276703},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09541106224060059},{"id":"https://openalex.org/C500300565","wikidata":"https://www.wikidata.org/wiki/Q925667","display_name":"Computer simulation","level":2,"score":0.0},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.313","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.313","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2368171720","https://openalex.org/W2376932109","https://openalex.org/W2001405890"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":42},{"year":2025,"cited_by_count":27}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}
