{"id":"https://openalex.org/W4388117482","doi":"https://doi.org/10.23919/eusipco58844.2023.10290115","title":"Facetron: A Multi-Speaker Face-to-Speech Model Based on Cross-Modal Latent Representations","display_name":"Facetron: A Multi-Speaker Face-to-Speech Model Based on Cross-Modal Latent Representations","publication_year":2023,"publication_date":"2023-09-04","ids":{"openalex":"https://openalex.org/W4388117482","doi":"https://doi.org/10.23919/eusipco58844.2023.10290115"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco58844.2023.10290115","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/eusipco58844.2023.10290115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},"type":"article","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/A5074612173","display_name":"Seyun Um","orcid":"https://orcid.org/0000-0002-2229-6741"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Seyun Um","raw_affiliation_strings":["Yonsei University,Dept. of Electrical and Electronic Engineering,Seoul,Korea","Dept. of Electrical and Electronic Engineering, Yonsei University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University,Dept. of Electrical and Electronic Engineering,Seoul,Korea","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"Dept. of Electrical and Electronic Engineering, Yonsei University, Seoul, Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100462783","display_name":"Jihyun Kim","orcid":"https://orcid.org/0000-0002-8071-3435"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jihyun Kim","raw_affiliation_strings":["Yonsei University,Dept. of Electrical and Electronic Engineering,Seoul,Korea","Dept. of Electrical and Electronic Engineering, Yonsei University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University,Dept. of Electrical and Electronic Engineering,Seoul,Korea","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"Dept. of Electrical and Electronic Engineering, Yonsei University, Seoul, Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100413513","display_name":"Ji\u2010Hyun Lee","orcid":"https://orcid.org/0000-0002-9864-5485"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jihyun Lee","raw_affiliation_strings":["Yonsei University,Dept. of Electrical and Electronic Engineering,Seoul,Korea","Dept. of Electrical and Electronic Engineering, Yonsei University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University,Dept. of Electrical and Electronic Engineering,Seoul,Korea","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"Dept. of Electrical and Electronic Engineering, Yonsei University, Seoul, Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056128107","display_name":"Hong-Goo Kang","orcid":"https://orcid.org/0000-0002-6554-0783"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hong-Goo Kang","raw_affiliation_strings":["Yonsei University,Dept. of Electrical and Electronic Engineering,Seoul,Korea","Dept. of Electrical and Electronic Engineering, Yonsei University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University,Dept. of Electrical and Electronic Engineering,Seoul,Korea","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"Dept. of Electrical and Electronic Engineering, Yonsei University, Seoul, Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5074612173"],"corresponding_institution_ids":["https://openalex.org/I193775966"],"apc_list":null,"apc_paid":null,"fwci":0.2033,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.4644176,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"281","last_page":"285"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.998199999332428,"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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9936000108718872,"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":0.7576606273651123},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.743445634841919},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6527109146118164},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.6271984577178955},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.529619038105011},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.501962423324585},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.4562183618545532},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4300858974456787},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.42240506410598755},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4060383439064026},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35967904329299927},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17665383219718933}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7576606273651123},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.743445634841919},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6527109146118164},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6271984577178955},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.529619038105011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.501962423324585},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.4562183618545532},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4300858974456787},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.42240506410598755},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4060383439064026},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35967904329299927},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17665383219718933},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco58844.2023.10290115","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/eusipco58844.2023.10290115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2015143272","https://openalex.org/W2096733369","https://openalex.org/W2127141656","https://openalex.org/W2327501763","https://openalex.org/W2471520273","https://openalex.org/W2578229578","https://openalex.org/W2585824449","https://openalex.org/W2952746495","https://openalex.org/W2963936489","https://openalex.org/W2964352155","https://openalex.org/W2972563022","https://openalex.org/W2979157532","https://openalex.org/W3015645837","https://openalex.org/W3015841875","https://openalex.org/W3035626590","https://openalex.org/W3092028330","https://openalex.org/W3096650361","https://openalex.org/W3096806995","https://openalex.org/W3097206152","https://openalex.org/W4224926225","https://openalex.org/W4298112588","https://openalex.org/W6783867762","https://openalex.org/W6785471559","https://openalex.org/W6810209978"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W4238433571","https://openalex.org/W2967848559","https://openalex.org/W4299831724","https://openalex.org/W4283803360"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,91],"propose":[4],"a":[5,19,56,70,78],"multi-speaker":[6],"face-to-speech":[7],"waveform":[8],"generation":[9],"model":[10,114],"that":[11],"also":[12],"works":[13],"for":[14],"unseen":[15],"speaker":[16,27,61,98],"conditions.":[17],"Using":[18],"generative":[20],"adversarial":[21],"network":[22],"(GAN)":[23],"with":[24,77],"linguistic":[25,48],"and":[26,59,88,122],"characteristic":[28,62],"features":[29,49,63,85],"as":[30],"auxiliary":[31],"conditions,":[32],"our":[33,112],"method":[34],"directly":[35],"converts":[36],"face":[37,67,71,105],"images":[38,68],"into":[39],"speech":[40,95],"waveforms":[41,96],"under":[42],"an":[43],"end-to-end":[44],"training":[45],"framework.":[46],"The":[47],"are":[50,64,86],"extracted":[51],"from":[52,66],"lip":[53],"movements":[54],"using":[55,69],"lip-reading":[57],"model,":[58],"the":[60,103,109],"predicted":[65],"encoder":[72],"trained":[73],"through":[74],"cross-modal":[75],"learning":[76],"pre-trained":[79],"acoustic":[80],"model.":[81],"Since":[82],"these":[83],"two":[84],"uncorrelated":[87],"controlled":[89],"independently,":[90],"can":[92],"flexibly":[93],"synthesize":[94],"whose":[97],"characteristics":[99],"vary":[100],"depending":[101],"on":[102],"input":[104],"images.":[106],"We":[107],"show":[108],"superiority":[110],"of":[111,120],"proposed":[113],"over":[115],"conventional":[116],"methods":[117],"in":[118],"terms":[119],"objective":[121],"subjective":[123],"evaluation":[124],"results.":[125]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}