{"id":"https://openalex.org/W7166886664","doi":"https://doi.org/10.18653/v1/2026.acl-long.173","title":"FC-TTS: Style and Timbre Control in Zero-Shot Text-to-Speech with Disentangled Speech Representations","display_name":"FC-TTS: Style and Timbre Control in Zero-Shot Text-to-Speech with Disentangled Speech Representations","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166886664","doi":"https://doi.org/10.18653/v1/2026.acl-long.173"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.173","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.173","pdf_url":"https://aclanthology.org/2026.acl-long.173.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.173.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045637107","display_name":"Yoonhyung Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoonhyung Lee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010227336","display_name":"Hyunsin Park","orcid":"https://orcid.org/0000-0003-3556-5792"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyunsin Park","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139808284","display_name":"Jinhwan Park","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinhwan Park","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139754256","display_name":"Jinkyu Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinkyu Lee","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":0.87488031,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3772","last_page":"3791"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7026000022888184,"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":0.7026000022888184,"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/T10860","display_name":"Speech and Audio Processing","score":0.0471000000834465,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.039400000125169754,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.6069999933242798},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5529999732971191},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.5152999758720398},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.24289999902248383}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.6069999933242798},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5568000078201294},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5529999732971191},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5475999712944031},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.5152999758720398},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3589000105857849},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.35339999198913574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33160001039505005},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.24289999902248383},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.24220000207424164}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.173","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.173","pdf_url":"https://aclanthology.org/2026.acl-long.173.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.173","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.173","pdf_url":"https://aclanthology.org/2026.acl-long.173.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/10","display_name":"Reduced inequalities","score":0.6681801676750183}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166886664.pdf","grobid_xml":"https://content.openalex.org/works/W7166886664.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,13],"zero-shot":[3,87,147],"text-to-speech":[4],"(TTS)":[5],"have":[6,36],"enabled":[7],"accurate":[8],"imitation":[9],"of":[10,15,94,133,156],"reference":[11,103],"speech":[12,39,43],"terms":[14],"both":[16],"speaking":[17],"style":[18,95,157],"and":[19,50,76,96,125,136,145,153,158],"speaker":[20],"timbre.However,":[21],"achieving":[22],"disentangled":[23,38,92,113],"control":[24,60,78,93],"over":[25],"these":[26],"aspects":[27],"from":[28,61,110],"separate":[29,62],"references":[30],"remains":[31,79],"a":[32,53,86],"challenging":[33],"task.Several":[34],"studies":[35],"proposed":[37],"representations":[40,69],"that":[41,90,107,140],"decompose":[42],"into":[44,70],"interpretable":[45],"attributes":[46],"(e.g.,":[47],"timbre,":[48],"prosody,":[49],"content),":[51],"providing":[52],"promising":[54],"foundation":[55],"for":[56],"TTS":[57,71,88],"with":[58],"attribute":[59,134],"references.Yet,":[63],"how":[64],"to":[65,73],"effectively":[66],"integrate":[67],"such":[68],"systems":[72,106],"achieve":[74],"independent":[75,154],"precise":[77],"underexplored.In":[80],"this":[81],"paper,":[82],"we":[83],"present":[84],"FC-TTS,":[85],"framework":[89],"enables":[91],"timbre":[97],"by":[98],"conditioning":[99],"on":[100],"two":[101],"distinct":[102],"utterances.Unlike":[104],"existing":[105],"inherit":[108],"limitations":[109],"those":[111],"pre-trained":[112],"representations,":[114],"FC-TTS":[115,141],"introduces":[116],"key":[117],"design":[118],"strategies,":[119],"including":[120],"architectural":[121],"choices,":[122],"training":[123,127],"framework,":[124],"auxiliary":[126],"objectives,":[128],"which":[129],"improve":[130],"the":[131],"reliability":[132],"separation":[135],"dual-reference":[137],"control.Experiments":[138],"show":[139],"achieves":[142],"high-fidelity":[143],"synthesis":[144],"competitive":[146],"naturalness,":[148],"while":[149],"uniquely":[150],"supporting":[151],"consistent":[152],"manipulation":[155],"timbre.":[159]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}