{"id":"https://openalex.org/W4392908962","doi":"https://doi.org/10.1109/icassp48485.2024.10446947","title":"Talking Face Generation for Impression Conversion Considering Speech Semantics","display_name":"Talking Face Generation for Impression Conversion Considering Speech Semantics","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392908962","doi":"https://doi.org/10.1109/icassp48485.2024.10446947"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446947","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446947","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5109312183","display_name":"Saki Mizuno","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Saki Mizuno","raw_affiliation_strings":["NTT Corporation,NTT Computer & Data Science Laboratories,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,NTT Computer & Data Science Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079710814","display_name":"Nobukatsu Hojo","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobukatsu Hojo","raw_affiliation_strings":["NTT Corporation,NTT Computer & Data Science Laboratories,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,NTT Computer & Data Science Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078963513","display_name":"Kazutoshi Shinoda","orcid":"https://orcid.org/0000-0003-1941-6172"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazutoshi Shinoda","raw_affiliation_strings":["NTT Corporation,NTT Computer & Data Science Laboratories,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,NTT Computer & Data Science Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103222069","display_name":"Keita Suzuki","orcid":"https://orcid.org/0009-0006-7963-3952"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keita Suzuki","raw_affiliation_strings":["NTT Corporation,NTT Computer & Data Science Laboratories,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,NTT Computer & Data Science Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027118468","display_name":"Mana Ihori","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mana Ihori","raw_affiliation_strings":["NTT Corporation,NTT Computer & Data Science Laboratories,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,NTT Computer & Data Science Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049917170","display_name":"Hiroshi Sat\u014d","orcid":"https://orcid.org/0000-0002-5899-1340"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Sato","raw_affiliation_strings":["NTT Corporation,NTT Computer & Data Science Laboratories,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,NTT Computer & Data Science Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009756622","display_name":"Tomohiro Tanaka","orcid":"https://orcid.org/0000-0001-7442-4912"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Tanaka","raw_affiliation_strings":["NTT Corporation,NTT Computer & Data Science Laboratories,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,NTT Computer & Data Science Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016817412","display_name":"Naotaka Kawata","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naotaka Kawata","raw_affiliation_strings":["NTT Corporation,NTT Computer & Data Science Laboratories,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,NTT Computer & Data Science Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024724493","display_name":"Satoshi Kobashikawa","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Kobashikawa","raw_affiliation_strings":["NTT Corporation,NTT Computer & Data Science Laboratories,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,NTT Computer & Data Science Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060644399","display_name":"Ryo Masumura","orcid":"https://orcid.org/0000-0002-2415-4149"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Masumura","raw_affiliation_strings":["NTT Corporation,NTT Computer & Data Science Laboratories,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,NTT Computer & Data Science Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03234859,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"8411","last_page":"8415"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9970999956130981,"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":0.9970999956130981,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.909600019454956,"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/impression","display_name":"Impression","score":0.8046688437461853},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7313399314880371},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.6781452298164368},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5695865750312805},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4919142723083496},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4489966928958893},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3869876563549042},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.21618247032165527},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2085341215133667},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.13041892647743225}],"concepts":[{"id":"https://openalex.org/C2776684213","wikidata":"https://www.wikidata.org/wiki/Q6007582","display_name":"Impression","level":2,"score":0.8046688437461853},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7313399314880371},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6781452298164368},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5695865750312805},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4919142723083496},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4489966928958893},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3869876563549042},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.21618247032165527},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2085341215133667},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.13041892647743225},{"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/icassp48485.2024.10446947","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446947","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2030931454","https://openalex.org/W2085521728","https://openalex.org/W2145421863","https://openalex.org/W2149602309","https://openalex.org/W2567184693","https://openalex.org/W2726515241","https://openalex.org/W2783495074","https://openalex.org/W2808631503","https://openalex.org/W3008823916","https://openalex.org/W3015737168","https://openalex.org/W3019952993","https://openalex.org/W3034241236","https://openalex.org/W3089177030","https://openalex.org/W3089393278","https://openalex.org/W3099284785","https://openalex.org/W3109114891","https://openalex.org/W3128611391","https://openalex.org/W3197199219","https://openalex.org/W4200631136","https://openalex.org/W4206517532","https://openalex.org/W4206556736","https://openalex.org/W4281779270","https://openalex.org/W4283818626","https://openalex.org/W4285122440","https://openalex.org/W4312444931","https://openalex.org/W4366308854","https://openalex.org/W4372268734","https://openalex.org/W4385823372","https://openalex.org/W6631190155","https://openalex.org/W6767264202","https://openalex.org/W6783543296"],"related_works":["https://openalex.org/W2327021330","https://openalex.org/W2316594088","https://openalex.org/W2397440126","https://openalex.org/W2409084359","https://openalex.org/W68571419","https://openalex.org/W4392328073","https://openalex.org/W2317327847","https://openalex.org/W2989908193","https://openalex.org/W2052573402","https://openalex.org/W2083361043"],"abstract_inverted_index":{"This":[0],"study":[1],"investigates":[2],"the":[3,31,38,46,60,65,75,127,131,136,140,144],"talking":[4,51],"face":[5,52],"generation":[6,53],"method":[7,27,133],"to":[8,13,29,58,119],"convert":[9],"a":[10,15,41,88,95],"speaker\u2019s":[11,42],"video":[12,43],"give":[14],"target":[16,145],"impression,":[17],"such":[18],"as":[19],"\u201cfavorable\u201d":[20],"or":[21],"\u201cconsiderate\u201d.":[22],"Such":[23],"an":[24,112],"impression":[25,39,116],"conversion":[26,91],"needs":[28],"consider":[30,71],"input":[32,107],"speech":[33,56,63,72,76,103],"semantics":[34,73],"because":[35,74],"they":[36,69],"affect":[37],"of":[40,64,102,106,139,143],"along":[44],"with":[45,115],"facial":[47,89,141],"expression.":[48],"Conventional":[49],"emotional":[50],"methods":[54],"utilize":[55],"information":[57],"synchronize":[59],"lip":[61],"and":[62],"output":[66],"video.":[67,146],"However,":[68],"cannot":[70],"representations":[77],"contain":[78],"only":[79],"phonetic":[80],"information.":[81],"To":[82],"solve":[83],"this":[84],"problem,":[85],"we":[86],"propose":[87],"expression":[90],"model":[92],"that":[93,130],"uses":[94],"semantic":[96],"vector":[97],"obtained":[98],"from":[99],"BERT":[100],"embeddings":[101],"recognition":[104],"results":[105,124],"speech.":[108],"We":[109],"first":[110],"constructed":[111],"audio-visual":[113],"dataset":[114,128],"labels":[117],"assigned":[118],"each":[120],"utterance.":[121],"The":[122],"evaluation":[123],"based":[125],"on":[126],"showed":[129],"proposed":[132],"could":[134],"improve":[135],"estimation":[137],"accuracy":[138],"expressions":[142]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}