{"id":"https://openalex.org/W4313023760","doi":"https://doi.org/10.1109/tmm.2022.3214100","title":"AnyoneNet: Synchronized Speech and Talking Head Generation for Arbitrary Persons","display_name":"AnyoneNet: Synchronized Speech and Talking Head Generation for Arbitrary Persons","publication_year":2022,"publication_date":"2022-10-12","ids":{"openalex":"https://openalex.org/W4313023760","doi":"https://doi.org/10.1109/tmm.2022.3214100"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2022.3214100","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3214100","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repository.tudelft.nl/file/File_843d48cd-4a93-44c3-b86a-9add2963a69e","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021472684","display_name":"Xinsheng Wang","orcid":"https://orcid.org/0000-0003-1826-7419"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]},{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["CN","NL"],"is_corresponding":false,"raw_author_name":"Xinsheng Wang","raw_affiliation_strings":["School of Software Engineering, Xi'an Jiaotong University, Xi'an, China","School of Computer Science, Northwestern Polytechnical University, Xi'an, China","Multimedia Computing Group, Delft University of Technology, Delft, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-1826-7419","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049213273","display_name":"Qicong Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qicong Xie","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068185614","display_name":"Jihua Zhu","orcid":"https://orcid.org/0000-0002-3081-8781"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jihua Zhu","raw_affiliation_strings":["School of Software Engineering, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-3081-8781","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-8234-0823","affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048860892","display_name":"Odette Scharenborg","orcid":"https://orcid.org/0000-0003-0693-8852"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Odette Scharenborg","raw_affiliation_strings":["Multimedia Computing Group, Delft University of Technology, Delft, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-0693-8852","affiliations":[{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6222,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.84674087,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"25","issue":null,"first_page":"6717","last_page":"6728"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9987999796867371,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9979000091552734,"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":0.8608144521713257},{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.7782400846481323},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7415875792503357},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5973705053329468},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.591752290725708},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.566710889339447},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5103580355644226},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4940986931324005},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4213502109050751}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8608144521713257},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.7782400846481323},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7415875792503357},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5973705053329468},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.591752290725708},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.566710889339447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5103580355644226},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4940986931324005},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4213502109050751},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2022.3214100","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3214100","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:tudelft.nl:uuid:1b2be59d-96be-4a86-a3b4-487653ced666","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:1b2be59d-96be-4a86-a3b4-487653ced666","pdf_url":"https://repository.tudelft.nl/file/File_843d48cd-4a93-44c3-b86a-9add2963a69e","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"}],"best_oa_location":{"id":"pmh:oai:tudelft.nl:uuid:1b2be59d-96be-4a86-a3b4-487653ced666","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:1b2be59d-96be-4a86-a3b4-487653ced666","pdf_url":"https://repository.tudelft.nl/file/File_843d48cd-4a93-44c3-b86a-9add2963a69e","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7599999904632568}],"awards":[{"id":"https://openalex.org/G3586343731","display_name":null,"funder_award_id":"2021GY-025","funder_id":"https://openalex.org/F4320336350","funder_display_name":"Key Research and Development Projects of Shaanxi Province"},{"id":"https://openalex.org/G7946923305","display_name":null,"funder_award_id":"2021GXLH-Z-097","funder_id":"https://openalex.org/F4320336350","funder_display_name":"Key Research and Development Projects of Shaanxi Province"}],"funders":[{"id":"https://openalex.org/F4320336350","display_name":"Key Research and Development Projects of Shaanxi Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4313023760.pdf","grobid_xml":"https://content.openalex.org/works/W4313023760.grobid-xml"},"referenced_works_count":93,"referenced_works":["https://openalex.org/W1492383498","https://openalex.org/W1779294284","https://openalex.org/W2096733369","https://openalex.org/W2115252128","https://openalex.org/W2117418893","https://openalex.org/W2120847449","https://openalex.org/W2146991130","https://openalex.org/W2150183867","https://openalex.org/W2194775991","https://openalex.org/W2468212864","https://openalex.org/W2519091744","https://openalex.org/W2551572271","https://openalex.org/W2572640303","https://openalex.org/W2574456902","https://openalex.org/W2594690981","https://openalex.org/W2738406145","https://openalex.org/W2782422271","https://openalex.org/W2808631503","https://openalex.org/W2808706139","https://openalex.org/W2901997113","https://openalex.org/W2904787397","https://openalex.org/W2944294033","https://openalex.org/W2946200149","https://openalex.org/W2949662773","https://openalex.org/W2962963674","https://openalex.org/W2963066677","https://openalex.org/W2963073614","https://openalex.org/W2963081548","https://openalex.org/W2963290645","https://openalex.org/W2963300588","https://openalex.org/W2963609956","https://openalex.org/W2963975282","https://openalex.org/W2964073455","https://openalex.org/W2964095416","https://openalex.org/W2964243274","https://openalex.org/W2964559396","https://openalex.org/W2965764938","https://openalex.org/W2970006822","https://openalex.org/W2972986505","https://openalex.org/W2979157532","https://openalex.org/W2981087920","https://openalex.org/W2988907666","https://openalex.org/W2990452356","https://openalex.org/W3006410788","https://openalex.org/W3008823916","https://openalex.org/W3010434693","https://openalex.org/W3015580115","https://openalex.org/W3015826515","https://openalex.org/W3015922793","https://openalex.org/W3019952993","https://openalex.org/W3023706973","https://openalex.org/W3081492798","https://openalex.org/W3087121792","https://openalex.org/W3092028330","https://openalex.org/W3093595890","https://openalex.org/W3096086473","https://openalex.org/W3097538987","https://openalex.org/W3097792222","https://openalex.org/W3101631197","https://openalex.org/W3104792420","https://openalex.org/W3107666850","https://openalex.org/W3109114891","https://openalex.org/W3120163087","https://openalex.org/W3144035034","https://openalex.org/W3161782335","https://openalex.org/W3174763799","https://openalex.org/W3186090335","https://openalex.org/W3192072773","https://openalex.org/W3194357576","https://openalex.org/W3196584150","https://openalex.org/W4206908380","https://openalex.org/W4249866455","https://openalex.org/W4287761884","https://openalex.org/W4298174729","https://openalex.org/W6677618333","https://openalex.org/W6737896281","https://openalex.org/W6748181857","https://openalex.org/W6748573829","https://openalex.org/W6751750676","https://openalex.org/W6752888775","https://openalex.org/W6753855596","https://openalex.org/W6756197946","https://openalex.org/W6763832098","https://openalex.org/W6767111847","https://openalex.org/W6767264202","https://openalex.org/W6772157574","https://openalex.org/W6774285787","https://openalex.org/W6776963518","https://openalex.org/W6779337556","https://openalex.org/W6780226713","https://openalex.org/W6783867762","https://openalex.org/W6784683243","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2056853153","https://openalex.org/W2057559274","https://openalex.org/W2005087563","https://openalex.org/W2378111931","https://openalex.org/W4243161226","https://openalex.org/W2950647290","https://openalex.org/W2620829895","https://openalex.org/W2356918560","https://openalex.org/W1968481813","https://openalex.org/W2392886708"],"abstract_inverted_index":{"Automatically":[0],"generating":[1,225],"videos":[2,38,98,157,193],"in":[3,12,19,197,206],"which":[4,64,136,198],"synthesized":[5,203],"speech":[6,35,81,94,189],"is":[7,77,118,175,184,205],"synchronized":[8,34,93,188],"with":[9,208],"lip":[10,170],"movements":[11,171],"a":[13,45,71,103,108,119,141,162],"talking":[14,60,96,110,155,191,216,227],"head":[15,61,97,111,156,173,192,217,228],"has":[16],"great":[17],"potential":[18],"many":[20],"human-computer":[21],"interaction":[22],"scenarios.":[23],"In":[24,55],"this":[25],"paper,":[26],"we":[27],"present":[28],"an":[29,50],"automatic":[30],"method":[31,76,88,165,183,218,223],"to":[32,57,139,186],"generate":[33,153,187],"and":[36,44,95,107,172,190,212],"talking-head":[37],"on":[39,144,224],"the":[40,68,74,86,90,126,145,148,154,159,181,199,202,209,213,220],"basis":[41,146],"of":[42,49,70,79,92,134,147,201],"text":[43],"single":[46],"face":[47,131,150,160],"image":[48],"arbitrary":[51,195],"person":[52],"as":[53],"input.":[54],"contrast":[56],"previous":[58],"text-driven":[59],"generation":[62,91,112],"methods,":[63],"can":[65,167],"only":[66],"synthesize":[67,140],"voice":[69,143,204],"specific":[72],"person,":[73],"proposed":[75,87,115,182,214],"capable":[78],"synthesizing":[80],"for":[82,194],"any":[83],"person.":[84],"Specifically,":[85],"decomposes":[89],"into":[99],"two":[100],"stages,":[101],"i.e.,":[102],"text-to-speech":[104],"(TTS)":[105],"stage":[106],"speech-driven":[109],"stage.":[113],"The":[114],"TTS":[116,122],"module":[117],"face-conditioned":[120],"multi-speaker":[121],"model":[123],"that":[124,166,180],"gets":[125],"speaker":[127],"identity":[128],"information":[129],"from":[130,158],"images":[132],"instead":[133],"speech,":[135],"allows":[137],"us":[138],"personalized":[142],"input":[149,210],"image.":[151],"To":[152],"images,":[161],"facial":[163],"landmark-based":[164,215,222],"predict":[168],"both":[169],"rotations":[174],"proposed.":[176],"Extensive":[177],"experiments":[178],"demonstrate":[179],"able":[185],"persons,":[196],"timbre":[200],"harmony":[207],"face,":[211],"outperforms":[219],"state-of-the-art":[221],"natural":[226],"videos.":[229]},"counts_by_year":[{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-26T07:53:14.480251","created_date":"2025-10-10T00:00:00"}