{"id":"https://openalex.org/W4404931742","doi":"https://doi.org/10.1007/978-3-031-78172-8_18","title":"StableTalk: Advancing Audio-to-Talking Face Generation with\u00a0Stable Diffusion and Vision Transformer","display_name":"StableTalk: Advancing Audio-to-Talking Face Generation with\u00a0Stable Diffusion and Vision Transformer","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4404931742","doi":"https://doi.org/10.1007/978-3-031-78172-8_18"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-78172-8_18","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-78172-8_18","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5068705264","display_name":"Fatemeh Nazarieh","orcid":"https://orcid.org/0000-0001-6917-6969"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Fatemeh Nazarieh","raw_affiliation_strings":["School of Computer Science and Electronic Engineering, University of Surrey, Guildford, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Electronic Engineering, University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041062049","display_name":"Josef T. Kittler","orcid":"https://orcid.org/0000-0002-3437-9456"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Josef Kittler","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK","Institute for People-Centred AI, University of Surrey, Guildford, UK","School of Computer Science and Electronic Engineering, University of Surrey, Guildford, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Institute for People-Centred AI, University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"School of Computer Science and Electronic Engineering, University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100778579","display_name":"Muhammad Awais","orcid":"https://orcid.org/0000-0002-1122-0709"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Muhammad Awais Rana","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK","Institute for People-Centred AI, University of Surrey, Guildford, UK","School of Computer Science and Electronic Engineering, University of Surrey, Guildford, UK"],"raw_orcid":"https://orcid.org/0000-0002-1122-0709","affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Institute for People-Centred AI, University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"School of Computer Science and Electronic Engineering, University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054401662","display_name":"Diptesh Kanojia","orcid":"https://orcid.org/0000-0001-8814-0080"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Diptesh Kanojia","raw_affiliation_strings":["Institute for People-Centred AI, University of Surrey, Guildford, UK","School of Computer Science and Electronic Engineering, University of Surrey, Guildford, UK"],"raw_orcid":"https://orcid.org/0000-0001-8814-0080","affiliations":[{"raw_affiliation_string":"Institute for People-Centred AI, University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"School of Computer Science and Electronic Engineering, University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025299678","display_name":"Zhenhua Feng","orcid":"https://orcid.org/0000-0002-4485-4249"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]},{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Zhenhua Feng","raw_affiliation_strings":["School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China","School of Computer Science and Electronic Engineering, University of Surrey, Guildford, UK"],"raw_orcid":"https://orcid.org/0000-0002-4485-4249","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]},{"raw_affiliation_string":"School of Computer Science and Electronic Engineering, University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5068705264"],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48340249,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"271","last_page":"286"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9986000061035156,"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":0.9980999827384949,"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":0.8002753257751465},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5782176852226257},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.551701545715332},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.47984763979911804},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46591901779174805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41199174523353577},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.27071383595466614},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.05826699733734131},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.054091185331344604}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8002753257751465},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5782176852226257},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.551701545715332},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47984763979911804},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46591901779174805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41199174523353577},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.27071383595466614},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.05826699733734131},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.054091185331344604},{"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-78172-8_18","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-78172-8_18","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2030931454","https://openalex.org/W2133665775","https://openalex.org/W2532790758","https://openalex.org/W2738406145","https://openalex.org/W2962785568","https://openalex.org/W2963426391","https://openalex.org/W2963981733","https://openalex.org/W2964559396","https://openalex.org/W2973049979","https://openalex.org/W2990452356","https://openalex.org/W2991044292","https://openalex.org/W3019952993","https://openalex.org/W3081492798","https://openalex.org/W3096831136","https://openalex.org/W3101631197","https://openalex.org/W3109114891","https://openalex.org/W3110537409","https://openalex.org/W3196525293","https://openalex.org/W3211147706","https://openalex.org/W4200377113","https://openalex.org/W4206706211","https://openalex.org/W4221045030","https://openalex.org/W4223483730","https://openalex.org/W4224918181","https://openalex.org/W4226148126","https://openalex.org/W4281725242","https://openalex.org/W4312933868","https://openalex.org/W4317951215","https://openalex.org/W4386075487","https://openalex.org/W4386076643","https://openalex.org/W4386598334","https://openalex.org/W4390730260","https://openalex.org/W4394597549","https://openalex.org/W6791705549","https://openalex.org/W6857500072"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}
