{"id":"https://openalex.org/W4416034188","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.879","title":"O_O-VC: Synthetic Data-Driven One-to-One Alignment for Any-to-Any Voice Conversion","display_name":"O_O-VC: Synthetic Data-Driven One-to-One Alignment for Any-to-Any Voice Conversion","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034188","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.879"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.879","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.879","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.09061","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054031088","display_name":"Huu Tuong Tu","orcid":"https://orcid.org/0000-0002-9820-1972"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huu Tuong Tu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037002951","display_name":"Huan Vu","orcid":"https://orcid.org/0000-0002-0785-6907"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huan Vu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027771274","display_name":"Nguy\u1ec5n C\u00e1t H\u1ed3","orcid":"https://orcid.org/0000-0002-8388-9399"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cuong Tien Nguyen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101522535","display_name":"Dien Hy Ngo","orcid":"https://orcid.org/0009-0002-2227-7062"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dien Hy Ngo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101435787","display_name":"Nguy\u1ec5n Th\u1ecb Thu Trang","orcid":"https://orcid.org/0000-0002-5015-082X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen Thi Thu Trang","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":0.29765391,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"16197","last_page":"16208"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8690000176429749,"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":0.8690000176429749,"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/T10863","display_name":"Voice and Speech Disorders","score":0.03579999879002571,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.0215000007301569,"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/feature","display_name":"Feature (linguistics)","score":0.26460000872612},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2484000027179718},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.23280000686645508},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.22859999537467957}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5654000043869019},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3917999863624573},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3587999939918518},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.31790000200271606},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2484000027179718},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.23280000686645508},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.22859999537467957},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.22349999845027924},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.22110000252723694}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.879","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.879","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.09061","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.09061","pdf_url":"https://arxiv.org/pdf/2510.09061","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:arXiv.org:2510.09061","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.09061","pdf_url":"https://arxiv.org/pdf/2510.09061","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.09061","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.09061","pdf_url":"https://arxiv.org/pdf/2510.09061","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Traditional":[0],"voice":[1,84,118],"conversion":[2,85,119,165],"(VC)":[3],"methods":[4],"typically":[5],"attempt":[6],"to":[7,21,34,81,91,123],"separate":[8],"speaker":[9,74,157],"identity":[10,75],"and":[11,98,126,131,152],"linguistic":[12,69,107],"information":[13,35],"into":[14],"distinct":[15],"representations,":[16],"which":[17],"are":[18,76],"then":[19],"combined":[20],"reconstruct":[22],"the":[23,67,83,89],"audio.":[24],"However,":[25],"effectively":[26,101],"disentangling":[27],"these":[28],"factors":[29],"remains":[30],"challenging,":[31],"often":[32],"leading":[33],"loss":[36],"during":[37],"training.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42,110],"propose":[43],"a":[44,54,93,112,144,153],"new":[45,127],"approach":[46],"that":[47,65,120,139],"leverages":[48],"synthetic":[49,62],"speech":[50],"data":[51,63],"generated":[52],"by":[53],"high-quality,":[55],"pretrained":[56],"multispeaker":[57],"text-to-speech":[58],"(TTS)":[59],"model.":[60,86],"Specifically,":[61],"pairs":[64,80],"share":[66],"same":[68],"content":[70],"but":[71],"differ":[72],"in":[73,133,148,156],"used":[77],"as":[78],"input-output":[79],"train":[82],"This":[87],"enables":[88],"model":[90],"learn":[92],"direct":[94],"mapping":[95],"between":[96],"source":[97],"target":[99],"voices,":[100],"capturing":[102],"speaker-specific":[103],"characteristics":[104],"while":[105],"preserving":[106],"content.":[108],"Additionally,":[109],"introduce":[111],"flexible":[113],"training":[114],"strategy":[115],"for":[116],"any-to-any":[117],"generalizes":[121],"well":[122],"unseen":[124],"speakers":[125],"languages,":[128],"enhancing":[129],"adaptability":[130],"performance":[132],"zero-shot":[134],"scenarios.":[135],"Our":[136],"experiments":[137],"show":[138],"our":[140],"proposed":[141],"method":[142],"achieves":[143],"16.35%":[145],"relative":[146],"reduction":[147],"word":[149],"error":[150],"rate":[151],"5.91%":[154],"improvement":[155],"cosine":[158],"similarity,":[159],"outperforming":[160],"several":[161],"state-of-the-art":[162],"methods.":[163],"Voice":[164],"samples":[166],"can":[167],"be":[168],"accessed":[169],"at:":[170],"https://oovc-emnlp-2025.github.io/":[171]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-14T00:00:00"}