{"id":"https://openalex.org/W7166804570","doi":"https://doi.org/10.18653/v1/2026.acl-long.2165","title":"BatonVoice: An Operationalist Framework for Enhancing Controllable Speech Synthesis with Linguistic Intelligence from LLMs","display_name":"BatonVoice: An Operationalist Framework for Enhancing Controllable Speech Synthesis with Linguistic Intelligence from LLMs","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166804570","doi":"https://doi.org/10.18653/v1/2026.acl-long.2165"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.2165","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2165","pdf_url":"https://aclanthology.org/2026.acl-long.2165.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":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.2165.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139797702","display_name":"Yue Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139847246","display_name":"Ruotian Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruotian Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139774318","display_name":"Xingyu Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingyu Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139851349","display_name":"Zhengliang Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengliang Shi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135857399","display_name":"Morunliu Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Morunliu Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062286064","display_name":"Wanshun Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wanshun Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023324549","display_name":"Huang Liu","orcid":"https://orcid.org/0000-0002-8886-2339"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139738528","display_name":"Jiadi Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiadi Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139848895","display_name":"Xin He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139767950","display_name":"Qu Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qu Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053535587","display_name":"Qingxuan Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingxuan Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139841900","display_name":"Fanghua Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fanghua Ye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139842492","display_name":"Juntao Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juntao Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139810701","display_name":"Zhaopeng Tu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaopeng Tu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139819026","display_name":"Xiaolong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaolong Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139770400","display_name":"Liefeng Bo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liefeng Bo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139762730","display_name":"Min Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Zhang","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":0.79423343,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"46683","last_page":"46697"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.2815999984741211,"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":0.2815999984741211,"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/T10028","display_name":"Topic Modeling","score":0.1868000030517578,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.17319999635219574,"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/computational-linguistics","display_name":"Computational linguistics","score":0.4169999957084656},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.37119999527931213},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.30230000615119934},{"id":"https://openalex.org/keywords/pragmatics","display_name":"Pragmatics","score":0.2768000066280365},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.27149999141693115}],"concepts":[{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.66839998960495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5501999855041504},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46880000829696655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4339999854564667},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.4169999957084656},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.37119999527931213},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.31369999051094055},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2939000129699707},{"id":"https://openalex.org/C11693617","wikidata":"https://www.wikidata.org/wiki/Q181839","display_name":"Pragmatics","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.2165","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2165","pdf_url":"https://aclanthology.org/2026.acl-long.2165.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"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.2165","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2165","pdf_url":"https://aclanthology.org/2026.acl-long.2165.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":[{"id":"https://metadata.un.org/sdg/4","score":0.7107959985733032,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166804570.pdf","grobid_xml":"https://content.openalex.org/works/W7166804570.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Yue":[0],"Wang,":[1],"Ruotian":[2],"Ma,":[3],"Xingyu":[4],"Chen,":[5,11],"Zhengliang":[6],"Shi,":[7],"Morunliu":[8],"Yang,":[9,19],"Wanshun":[10],"Huang":[12],"Liu,":[13],"Jiadi":[14],"Yao,":[15],"Xin":[16],"He,":[17],"Qu":[18],"Qingxuan":[20],"Jiang,":[21],"Fanghua":[22],"Ye,":[23],"Juntao":[24],"Li,":[25,29],"Zhaopeng":[26],"Tu,":[27],"Xiaolong":[28],"Liefeng":[30],"Bo,":[31],"Min":[32],"Zhang.":[33],"Proceedings":[34],"of":[35,40],"the":[36,41],"64th":[37],"Annual":[38],"Meeting":[39],"Association":[42],"for":[43],"Computational":[44],"Linguistics":[45],"(Volume":[46],"1:":[47],"Long":[48],"Papers).":[49],"2026.":[50]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
