{"id":"https://openalex.org/W4408345963","doi":"https://doi.org/10.1109/icassp49660.2025.10889667","title":"Face-StyleSpeech: Enhancing Zero-shot Speech Synthesis from Face Images with Improved Face-to-Speech Mapping","display_name":"Face-StyleSpeech: Enhancing Zero-shot Speech Synthesis from Face Images with Improved Face-to-Speech Mapping","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345963","doi":"https://doi.org/10.1109/icassp49660.2025.10889667"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889667","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889667","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/A5018777306","display_name":"Minki Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Minki Kang","raw_affiliation_strings":["KAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I157485424","https://openalex.org/I4210099236"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054823037","display_name":"Wooseok Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wooseok Han","raw_affiliation_strings":["AITRICS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AITRICS","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086698569","display_name":"Eunho Yang","orcid":"https://orcid.org/0000-0003-2188-0169"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Eunho Yang","raw_affiliation_strings":["KAIST, AITRICS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST, AITRICS","institution_ids":["https://openalex.org/I157485424","https://openalex.org/I4210099236"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4136,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.76599898,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"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/T11448","display_name":"Face recognition and analysis","score":0.9975000023841858,"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"}},"topics":[{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9975000023841858,"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/T10860","display_name":"Speech and Audio Processing","score":0.9947999715805054,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9855999946594238,"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/face","display_name":"Face (sociological concept)","score":0.773176908493042},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6670555472373962},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5428611636161804},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5258351564407349},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.4879454970359802},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.47623804211616516},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4182160496711731},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3338136374950409},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06434312462806702}],"concepts":[{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.773176908493042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6670555472373962},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5428611636161804},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5258351564407349},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.4879454970359802},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.47623804211616516},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4182160496711731},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3338136374950409},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06434312462806702},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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},{"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/icassp49660.2025.10889667","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889667","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":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2551572271","https://openalex.org/W2604379605","https://openalex.org/W2726515241","https://openalex.org/W2752796333","https://openalex.org/W2808631503","https://openalex.org/W3096806995","https://openalex.org/W3196001064","https://openalex.org/W4221159457","https://openalex.org/W4224920206","https://openalex.org/W4225746985","https://openalex.org/W4372259784","https://openalex.org/W4372263908","https://openalex.org/W4385572372","https://openalex.org/W4385823191","https://openalex.org/W6748588790","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6791353385","https://openalex.org/W6795261426","https://openalex.org/W6795807602","https://openalex.org/W6805710207","https://openalex.org/W6847363464","https://openalex.org/W6849956205","https://openalex.org/W6852870047"],"related_works":["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","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"Generating":[0],"speech":[1,40,85,119],"from":[2,57,120],"a":[3,31,43,58,62,121],"face":[4,44,59,73,95,99,122],"image":[5,45,60,123],"is":[6,80],"crucial":[7],"for":[8,127],"developing":[9],"virtual":[10],"humans":[11],"capable":[12],"of":[13],"interacting":[14],"using":[15],"their":[16],"unique":[17],"voices,":[18],"without":[19],"relying":[20],"on":[21,42,103,133],"pre-recorded":[22],"human":[23],"speech.":[24,49],"In":[25],"this":[26],"paper,":[27],"we":[28],"propose":[29],"Face-StyleSpeech,":[30],"zero-shot":[32],"TextTo-Speech":[33],"(TTS)":[34],"synthesis":[35],"model":[36,70,84],"that":[37,52,88,113],"generates":[38,116],"natural":[39,118],"conditioned":[41],"rather":[46],"than":[47,124],"reference":[48],"We":[50],"hypothesize":[51],"learning":[53],"entire":[54],"prosodic":[55],"features":[56,106],"poses":[61],"significant":[63],"challenge.":[64],"To":[65],"address":[66],"this,":[67],"our":[68,134],"TTS":[69],"incorporates":[71],"both":[72],"and":[74],"prosody":[75,78],"encoders.":[76],"The":[77],"encoder":[79,100],"specifically":[81],"designed":[82],"to":[83,101],"style":[86],"characteristics":[87],"are":[89,131],"not":[90],"fully":[91],"captured":[92],"by":[93],"the":[94,98],"image,":[96],"allowing":[97],"focus":[102],"extracting":[104],"speaker-specific":[105],"such":[107],"as":[108],"timbre.":[109],"Experimental":[110],"results":[111],"demonstrate":[112],"Face-StyleSpeech":[114],"effectively":[115],"more":[117],"baselines,":[125],"even":[126],"unseen":[128],"faces.":[129],"Samples":[130],"available":[132],"demo":[135],"page.1":[136]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}