{"id":"https://openalex.org/W4210489562","doi":"https://doi.org/10.1109/asru51503.2021.9687866","title":"Hearing Faces: Target Speaker Text-to-Speech Synthesis from a Face","display_name":"Hearing Faces: Target Speaker Text-to-Speech Synthesis from a Face","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4210489562","doi":"https://doi.org/10.1109/asru51503.2021.9687866"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9687866","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687866","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5007140698","display_name":"Bjorn Pluster","orcid":null},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Bjorn Pluster","raw_affiliation_strings":["Knowledge Technology, University of Hamburg,Department of Informatics"],"affiliations":[{"raw_affiliation_string":"Knowledge Technology, University of Hamburg,Department of Informatics","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102025003","display_name":"Cornelius Weber","orcid":"https://orcid.org/0000-0001-5163-938X"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Cornelius Weber","raw_affiliation_strings":["Knowledge Technology, University of Hamburg,Department of Informatics"],"affiliations":[{"raw_affiliation_string":"Knowledge Technology, University of Hamburg,Department of Informatics","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023714181","display_name":"Leyuan Qu","orcid":"https://orcid.org/0000-0001-6694-5355"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Leyuan Qu","raw_affiliation_strings":["Knowledge Technology, University of Hamburg,Department of Informatics"],"affiliations":[{"raw_affiliation_string":"Knowledge Technology, University of Hamburg,Department of Informatics","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033486668","display_name":"Stefan Wermter","orcid":"https://orcid.org/0000-0003-1343-4775"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Wermter","raw_affiliation_strings":["Knowledge Technology, University of Hamburg,Department of Informatics"],"affiliations":[{"raw_affiliation_string":"Knowledge Technology, University of Hamburg,Department of Informatics","institution_ids":["https://openalex.org/I159176309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5007140698"],"corresponding_institution_ids":["https://openalex.org/I159176309"],"apc_list":null,"apc_paid":null,"fwci":0.6881,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75218267,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"757","last_page":"764"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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/computer-science","display_name":"Computer science","score":0.832556962966919},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7786859273910522},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7032167911529541},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6339902877807617},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6025856137275696},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5797348022460938},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5422313213348389},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.44206202030181885},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.43116313219070435},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4279497265815735},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.41243934631347656},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3808916509151459},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10460641980171204}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.832556962966919},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7786859273910522},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7032167911529541},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6339902877807617},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6025856137275696},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5797348022460938},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5422313213348389},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.44206202030181885},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.43116313219070435},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4279497265815735},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.41243934631347656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3808916509151459},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10460641980171204},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9687866","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687866","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6100000143051147}],"awards":[],"funders":[{"id":"https://openalex.org/F4320308022","display_name":"California Department of Fish and Game","ror":"https://ror.org/02v6w2r95"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1836465849","https://openalex.org/W2066078528","https://openalex.org/W2071522329","https://openalex.org/W2077881910","https://openalex.org/W2096733369","https://openalex.org/W2129142580","https://openalex.org/W2157331557","https://openalex.org/W2227324914","https://openalex.org/W2341528187","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2619368999","https://openalex.org/W2794490148","https://openalex.org/W2889326414","https://openalex.org/W2890964092","https://openalex.org/W2891205112","https://openalex.org/W2903739847","https://openalex.org/W2922538097","https://openalex.org/W2962780374","https://openalex.org/W2962918445","https://openalex.org/W2963082324","https://openalex.org/W2963300588","https://openalex.org/W2963839617","https://openalex.org/W2963887950","https://openalex.org/W2964073455","https://openalex.org/W2964171275","https://openalex.org/W2964243274","https://openalex.org/W2964350391","https://openalex.org/W2970006822","https://openalex.org/W2972443522","https://openalex.org/W2979157532","https://openalex.org/W2984737709","https://openalex.org/W2998572311","https://openalex.org/W3015338123","https://openalex.org/W3016160783","https://openalex.org/W3024805917","https://openalex.org/W3033411150","https://openalex.org/W3094040572","https://openalex.org/W3096028031","https://openalex.org/W3096214032","https://openalex.org/W3096806995","https://openalex.org/W3101998545","https://openalex.org/W3109496323","https://openalex.org/W3147966746","https://openalex.org/W4289665794","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6638667902","https://openalex.org/W6694260854","https://openalex.org/W6738277540","https://openalex.org/W6739901393","https://openalex.org/W6750489868","https://openalex.org/W6754420807","https://openalex.org/W6767111847","https://openalex.org/W6778823374","https://openalex.org/W6784310668"],"related_works":["https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W2108985546","https://openalex.org/W2433276473","https://openalex.org/W2077992636","https://openalex.org/W1537411440","https://openalex.org/W2535215250","https://openalex.org/W2049083033","https://openalex.org/W290673751","https://openalex.org/W2017702615"],"abstract_inverted_index":{"The":[0],"existence":[1],"of":[2,28,87,123,161,169],"a":[3,8,46,72,81,88,94,115],"learnable":[4],"cross-modal":[5,47],"association":[6],"between":[7],"person's":[9],"face":[10,35,74,83],"and":[11,18,91,97,126,136,164],"their":[12,101],"voice":[13,89,96,153],"is":[14],"recently":[15],"becoming":[16],"more":[17,19,116],"evident.":[20],"This":[21,130],"provides":[22],"the":[23,26,106,121,159],"basis":[24],"for":[25,138,171],"task":[27,43],"target":[29],"speaker":[30,62],"text-to-speech":[31],"(TTS)":[32],"synthesis":[33,135],"from":[34,80,100],"ref-erence.":[36],"In":[37],"this":[38,42,111],"paper,":[39],"we":[40,113],"approach":[41,131],"by":[44],"proposing":[45],"model":[48,128,142,163],"architecture":[49,118],"combining":[50],"existing":[51,108],"unimodal":[52],"models.":[53],"We":[54,69,157],"use":[55,114,122],"Tacotron":[56],"2":[57],"multi-speaker":[58],"TTS":[59],"with":[60],"auditory":[61],"embeddings":[63,79],"based":[64],"on":[65,110],"Global":[66],"Style":[67],"Tokens.":[68],"trans-fer":[70],"learn":[71],"FaceNet":[73],"encoder":[75],"to":[76,104],"predict":[77,93],"these":[78],"static":[82],"image":[84],"reference":[85,90],"instead":[86],"thus":[92],"speaker's":[95],"speaking":[98],"characteristics":[99],"face.":[102],"Compared":[103],"Face2Speech,":[105],"only":[107],"work":[109],"task,":[112],"modular":[117],"that":[119],"allows":[120,137],"openly":[124],"available":[125],"pretrained":[127],"components.":[129],"enables":[132],"high-quality":[133],"speech":[134],"an":[139],"easily":[140],"extensible":[141],"architecture.":[143],"Ex-perimental":[144],"results":[145],"show":[146],"good":[147],"matching":[148],"ability":[149],"while":[150],"retaining":[151],"better":[152],"naturalness":[154],"than":[155],"Face2Speech.":[156],"examine":[158],"limitations":[160],"our":[162],"discuss":[165],"multiple":[166],"possible":[167],"av-enues":[168],"improvement":[170],"future":[172],"work.":[173]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}