{"id":"https://openalex.org/W4408355059","doi":"https://doi.org/10.1109/icassp49660.2025.10889831","title":"CASC-XVC: Zero-Shot Cross-Lingual Voice Conversion with Content Accordant and Speaker Contrastive Losses","display_name":"CASC-XVC: Zero-Shot Cross-Lingual Voice Conversion with Content Accordant and Speaker Contrastive Losses","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355059","doi":"https://doi.org/10.1109/icassp49660.2025.10889831"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889831","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100637325","display_name":"Hanjie Guo","orcid":"https://orcid.org/0000-0002-6493-8853"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han-Jie Guo","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R.China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067982618","display_name":"Hui-Peng Du","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui-Peng Du","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R.China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004434747","display_name":"Zheng-Yan Sheng","orcid":"https://orcid.org/0009-0002-0638-5530"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng-Yan Sheng","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R.China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100430194","display_name":"Liping Chen","orcid":"https://orcid.org/0000-0002-9421-1049"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li-Ping Chen","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R.China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045907056","display_name":"Yang Ai","orcid":"https://orcid.org/0000-0001-6668-022X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Ai","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R.China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R.China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9975000023841858,"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":0.9975000023841858,"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":0.9728000164031982,"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/speech-recognition","display_name":"Speech recognition","score":0.6128485202789307},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6029335856437683},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5714025497436523},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4211325943470001},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2123216688632965},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.058638542890548706}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6128485202789307},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6029335856437683},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5714025497436523},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4211325943470001},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2123216688632965},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.058638542890548706},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889831","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320330944","display_name":"Nature","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2576309025","https://openalex.org/W2884225676","https://openalex.org/W2963242190","https://openalex.org/W2998572311","https://openalex.org/W3024869864","https://openalex.org/W3098557217","https://openalex.org/W3194172310","https://openalex.org/W3197991492","https://openalex.org/W3198429080","https://openalex.org/W3211358952","https://openalex.org/W4224928197","https://openalex.org/W4287889585","https://openalex.org/W4319862209","https://openalex.org/W4367281575","https://openalex.org/W4372260053","https://openalex.org/W4392902857","https://openalex.org/W4392903127","https://openalex.org/W6714644935","https://openalex.org/W6762533536","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6796464841","https://openalex.org/W6803547063","https://openalex.org/W6805710207","https://openalex.org/W6847363464","https://openalex.org/W6857579053","https://openalex.org/W6858032378"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574"],"abstract_inverted_index":{"Cross-lingual":[0],"voice":[1],"conversion":[2],"(XVC)":[3],"is":[4],"a":[5,64,91,159],"technology":[6],"that":[7,166],"modifies":[8],"speaker":[9,74],"identity":[10],"while":[11],"preserving":[12],"linguistic":[13],"content":[14,70,151],"in":[15,35,101,109,131,172],"scenarios":[16],"where":[17],"the":[18,43,52,55,82,87,106,110,125,132],"source":[19],"and":[20,42,73,116,155,162],"target":[21],"speakers":[22,100],"use":[23,137],"different":[24,102,144],"languages.":[25],"Previous":[26],"non-parallel":[27],"disentanglement-based":[28],"methods":[29],"face":[30],"severe":[31],"training-testing":[32],"inconsistency":[33],"issues":[34],"XVC":[36,66,173],"tasks":[37],"due":[38],"to":[39,104,122],"language":[40],"mismatch":[41],"lack":[44,126],"of":[45,54,84,97,127],"multilingual":[46],"parallel":[47,129],"data,":[48],"which":[49],"inevitably":[50],"compromise":[51],"quality":[53],"synthesized":[56],"speech.":[57],"In":[58],"this":[59,79],"paper,":[60],"we":[61,136],"propose":[62],"CASC-XVC,":[63],"zero-shot":[65],"method":[67,80],"incorporating":[68],"with":[69,124,147],"accordant":[71],"(CA)":[72],"contrastive":[75],"(SC)":[76],"losses.":[77],"Specifically,":[78],"adopts":[81],"framework":[83],"FreeVC-s":[85],"as":[86],"backbone.":[88],"We":[89],"design":[90],"cross-lingual":[92],"fine-tuning":[93,133],"process":[94],"employing":[95],"pairs":[96],"utterances":[98],"from":[99],"languages":[103,145],"update":[105],"modules":[107],"used":[108],"inference":[111],"stage.":[112],"A":[113],"CA":[114],"loss":[115,119],"an":[117],"SC":[118],"are":[120],"introduced":[121],"deal":[123],"true":[128],"targets":[130],"process.":[134],"Moreover,":[135],"shared":[138],"self-supervised":[139],"learning":[140],"(SSL)":[141],"representations":[142],"across":[143],"along":[146],"information":[148],"perturbation":[149],"for":[150],"disentanglement.":[152],"Both":[153],"subjective":[154],"objective":[156],"results":[157],"on":[158],"bilingual":[160],"(English":[161],"Chinese)":[163],"dataset":[164],"demonstrate":[165],"our":[167],"approach":[168],"achieves":[169],"significant":[170],"improvements":[171],"tasks.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}