{"id":"https://openalex.org/W4387969124","doi":"https://doi.org/10.1145/3581783.3613825","title":"Face-Driven Zero-Shot Voice Conversion with Memory-based Face-Voice Alignment","display_name":"Face-Driven Zero-Shot Voice Conversion with Memory-based Face-Voice Alignment","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969124","doi":"https://doi.org/10.1145/3581783.3613825"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3613825","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3613825","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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/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, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0002-0638-5530","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, 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, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-6668-022X","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030295554","display_name":"Yan\u2010Nian Chen","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":"Yan-Nian Chen","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0002-0200-9167","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, 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, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-7853-5273","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, 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":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8443","last_page":"8452"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9984999895095825,"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/T11448","display_name":"Face recognition and analysis","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.817237138748169},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6485506892204285},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5560393929481506},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47801339626312256},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.47453439235687256},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.47058525681495667},{"id":"https://openalex.org/keywords/voice-analysis","display_name":"Voice analysis","score":0.4527880549430847},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4057140648365021},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0688139796257019}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.817237138748169},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6485506892204285},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5560393929481506},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47801339626312256},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.47453439235687256},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.47058525681495667},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.4527880549430847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4057140648365021},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0688139796257019},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3613825","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3613825","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.550000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W2066078528","https://openalex.org/W2077881910","https://openalex.org/W2096733369","https://openalex.org/W2266401008","https://openalex.org/W2341528187","https://openalex.org/W2576309025","https://openalex.org/W2800448574","https://openalex.org/W2804998325","https://openalex.org/W2902070858","https://openalex.org/W2935850529","https://openalex.org/W2944294033","https://openalex.org/W2946555236","https://openalex.org/W2962788625","https://openalex.org/W2963290645","https://openalex.org/W2963539064","https://openalex.org/W2972399707","https://openalex.org/W2979157532","https://openalex.org/W2996414377","https://openalex.org/W3000145882","https://openalex.org/W3015209900","https://openalex.org/W3015338123","https://openalex.org/W3035626590","https://openalex.org/W3095361818","https://openalex.org/W3096806995","https://openalex.org/W3098557217","https://openalex.org/W3101689408","https://openalex.org/W3101998545","https://openalex.org/W3186090335","https://openalex.org/W3206945595","https://openalex.org/W3211862173","https://openalex.org/W3214606349","https://openalex.org/W4210489562","https://openalex.org/W4220653738","https://openalex.org/W4221144911","https://openalex.org/W4224920206","https://openalex.org/W4224926225","https://openalex.org/W4224928197","https://openalex.org/W4225329057","https://openalex.org/W4283818626","https://openalex.org/W4287759306","https://openalex.org/W4296068587","https://openalex.org/W4313196646","https://openalex.org/W4382202825","https://openalex.org/W6804125026"],"related_works":["https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2898292629","https://openalex.org/W4400978960"],"abstract_inverted_index":{"This":[0,58],"paper":[1],"presents":[2],"a":[3,30,38,52,61,122],"novel":[4],"task,":[5,49],"zero-shot":[6,55,124,130,178],"voice":[7,20,83,109,125,140,159],"conversion":[8,110,126,141],"based":[9],"on":[10,37,176,184],"face":[11,40,86,163],"images":[12],"(zero-shot":[13],"FaceVC),":[14],"which":[15,67],"aims":[16],"at":[17],"converting":[18],"the":[19,43,71,80,97,101,119,134,153,170,177],"characteristics":[21,84,160],"of":[22,42,82,100,158,172],"an":[23],"utterance":[24],"from":[25,85,121],"any":[26],"source":[27],"speaker":[28],"to":[29,73,95,128,150],"newly":[31],"coming":[32],"target":[33,44],"speaker,":[34],"solely":[35],"relying":[36],"single":[39],"image":[41],"speaker.":[45],"To":[46,112],"address":[47],"this":[48],"we":[50,117,168],"propose":[51],"face-voice":[53,63],"memory-based":[54,62],"FaceVC":[56,131,137,179],"method.":[57],"method":[59,175],"leverages":[60],"alignment":[64],"module,":[65],"in":[66],"slots":[68],"act":[69],"as":[70],"bridge":[72],"align":[74],"these":[75],"two":[76],"modalities,":[77],"allowing":[78],"for":[79,108],"capture":[81],"images.":[87,164],"A":[88],"mixed":[89],"supervision":[90],"strategy":[91],"is":[92],"also":[93],"introduced":[94],"mitigate":[96],"long-standing":[98],"issue":[99],"inconsistency":[102],"between":[103,136],"training":[104],"and":[105,138,145,156],"inference":[106],"phases":[107],"tasks.":[111],"obtain":[113],"speaker-independent":[114],"content-related":[115],"representations,":[116],"transfer":[118],"knowledge":[120],"pretrained":[123],"model":[127],"our":[129,173,185],"model.":[132],"Considering":[133],"differences":[135],"traditional":[139],"tasks,":[142],"systematic":[143],"subjective":[144],"objective":[146],"metrics":[147],"are":[148,182],"designed":[149],"thoroughly":[151],"evaluate":[152],"homogeneity,":[154],"diversity":[155],"consistency":[157],"controlled":[161],"by":[162],"Through":[165],"extensive":[166],"experiments,":[167],"demonstrate":[169],"superiority":[171],"proposed":[174],"task.":[180],"Samples":[181],"presented":[183],"demo":[186],"website.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
