{"id":"https://openalex.org/W4416799995","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249151","title":"Face-Conditioned Large-Scale Text-to-Speech via Speaker Embedding Prediction from Facial Images","display_name":"Face-Conditioned Large-Scale Text-to-Speech via Speaker Embedding Prediction from Facial Images","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799995","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249151"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249151","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249151","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5120619744","display_name":"Umi Okamoto","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Umi Okamoto","raw_affiliation_strings":["Nagoya Institute of Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology,Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103835523","display_name":"Sei Ueno","orcid":"https://orcid.org/0000-0002-2255-3154"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sei Ueno","raw_affiliation_strings":["Nagoya Institute of Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology,Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035473671","display_name":"Akinobu Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akinobu Lee","raw_affiliation_strings":["Nagoya Institute of Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology,Japan","institution_ids":["https://openalex.org/I197274945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197274945"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32304204,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1116","last_page":"1121"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.47769999504089355,"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":0.47769999504089355,"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":0.44690001010894775,"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":0.02979999966919422,"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/embedding","display_name":"Embedding","score":0.6032000184059143},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.574999988079071},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5134999752044678},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43479999899864197},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.42829999327659607},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.41749998927116394},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4174000024795532},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3531000018119812}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7351999878883362},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7192000150680542},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6032000184059143},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.574999988079071},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5134999752044678},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4828999936580658},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43479999899864197},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.42829999327659607},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.41749998927116394},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4174000024795532},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3285999894142151},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.29660001397132874},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.28200000524520874},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.26910001039505005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249151","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249151","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":11,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W3095410713","https://openalex.org/W3096806995","https://openalex.org/W3097777922","https://openalex.org/W4224920206","https://openalex.org/W4372259784","https://openalex.org/W4372263908","https://openalex.org/W4408345963","https://openalex.org/W4415433644"],"related_works":[],"abstract_inverted_index":{"Zero-shot":[0],"text-to-speech":[1],"(TTS)":[2],"models":[3,40],"have":[4],"been":[5],"successful":[6],"due":[7],"to":[8,93,101,128],"large-scale":[9,74,86],"datasets":[10],"and":[11,24,32,46,65,78,130,167],"parameter":[12],"size.":[13],"Scaling":[14],"up":[15],"face-conditioned":[16,69],"TTS":[17,81,96,126],"models,":[18],"which":[19,52,122],"generate":[20],"speech":[21,30,58],"from":[22,106],"text":[23],"facial":[25,171],"images,":[26],"may":[27],"also":[28],"improve":[29,62],"quality":[31,48,64],"speaker":[33,66,75,103,109,156],"consistency.":[34],"However,":[35],"the":[36,44,63,94,107,125,131,136,145,153,169,174],"effectiveness":[37],"of":[38,49,68,124],"such":[39],"is":[41,99],"hindered":[42],"by":[43],"scarcity":[45],"low":[47],"audio-visual":[50,113],"data,":[51],"often":[53],"contain":[54],"noise":[55],"in":[56,173],"either":[57],"or":[59],"images.":[60],"To":[61],"consistency":[67],"TTS,":[70],"we":[71],"introduce":[72],"a":[73,79,90],"embedding":[76,110],"model":[77,127],"speechconditioned":[80],"model,":[82,111],"both":[83],"trained":[84,100],"with":[85],"data.":[87],"We":[88,117],"add":[89],"face":[91,137,146],"encoder":[92,147],"speech-conditioned":[95],"model.":[97],"It":[98],"predict":[102],"embeddings":[104],"extracted":[105],"largescale":[108],"using":[112],"data":[114],"for":[115,135],"finetuning.":[116],"conduct":[118],"detailed":[119],"investigations":[120],"into":[121],"parts":[123],"fine-tune":[129],"loss":[132],"functions":[133],"used":[134],"encoder.":[138],"Experimental":[139],"results":[140],"show":[141],"that":[142,161],"fine-tuning":[143],"only":[144],"yields":[148],"lower":[149],"WER,":[150],"while":[151],"updating":[152],"decoder":[154],"improves":[155],"similarity.":[157],"Subjective":[158],"evaluations":[159],"confirm":[160],"our":[162],"method":[163],"achieves":[164],"high":[165],"MOS":[166],"reflects":[168],"speaker's":[170],"characteristics":[172],"generated":[175],"speech.":[176]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}