{"id":"https://openalex.org/W4415721251","doi":"https://doi.org/10.1007/978-981-95-2725-0_6","title":"HFSD-V2C: Zero-Shot Visual Voice Cloning Via Hierarchical Face-Styled Diffusion Model","display_name":"HFSD-V2C: Zero-Shot Visual Voice Cloning Via Hierarchical Face-Styled Diffusion Model","publication_year":2025,"publication_date":"2025-10-31","ids":{"openalex":"https://openalex.org/W4415721251","doi":"https://doi.org/10.1007/978-981-95-2725-0_6"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-95-2725-0_6","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-95-2725-0_6","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/A5100761725","display_name":"Yaping Liu","orcid":"https://orcid.org/0000-0002-8986-634X"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yaping Liu","raw_affiliation_strings":["Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China","Yunnan Key Laboratory of Artificial Intelligence, Kunming, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]},{"raw_affiliation_string":"Yunnan Key Laboratory of Artificial Intelligence, Kunming, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102915267","display_name":"Linqin Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linqin Wang","raw_affiliation_strings":["Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China","Yunnan Key Laboratory of Artificial Intelligence, Kunming, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]},{"raw_affiliation_string":"Yunnan Key Laboratory of Artificial Intelligence, Kunming, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017471172","display_name":"Shengxiang Gao","orcid":"https://orcid.org/0000-0002-2980-8420"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengxiang Gao","raw_affiliation_strings":["Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China","Yunnan Key Laboratory of Artificial Intelligence, Kunming, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]},{"raw_affiliation_string":"Yunnan Key Laboratory of Artificial Intelligence, Kunming, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100619287","display_name":"Zhengtao Yu","orcid":"https://orcid.org/0000-0002-4012-461X"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengtao Yu","raw_affiliation_strings":["Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China","Yunnan Key Laboratory of Artificial Intelligence, Kunming, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]},{"raw_affiliation_string":"Yunnan Key Laboratory of Artificial Intelligence, Kunming, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068973438","display_name":"Ling Dong","orcid":"https://orcid.org/0000-0003-1612-6671"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ling Dong","raw_affiliation_strings":["Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China","Yunnan Key Laboratory of Artificial Intelligence, Kunming, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]},{"raw_affiliation_string":"Yunnan Key Laboratory of Artificial Intelligence, Kunming, China","institution_ids":["https://openalex.org/I4210100255"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100761725"],"corresponding_institution_ids":["https://openalex.org/I10660446","https://openalex.org/I4210100255"],"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":0.77971602,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"76","last_page":"88"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.4207000136375427,"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":0.4207000136375427,"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":0.22540000081062317,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.21529999375343323,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.7404000163078308},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.460099995136261},{"id":"https://openalex.org/keywords/cloning","display_name":"Cloning (programming)","score":0.4291999936103821},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4104999899864197},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.39079999923706055},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.3203999996185303},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.3192000091075897},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3174999952316284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8550999760627747},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7404000163078308},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6902999877929688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47380000352859497},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.460099995136261},{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.4291999936103821},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4104999899864197},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.39079999923706055},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.3203999996185303},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.2849999964237213},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2727000117301941},{"id":"https://openalex.org/C124913957","wikidata":"https://www.wikidata.org/wiki/Q1232548","display_name":"Zoom","level":3,"score":0.26809999346733093},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-981-95-2725-0_6","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-95-2725-0_6","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":19,"referenced_works":["https://openalex.org/W2107860279","https://openalex.org/W2747874407","https://openalex.org/W2963307811","https://openalex.org/W2963609956","https://openalex.org/W2963801643","https://openalex.org/W2963839617","https://openalex.org/W3015383493","https://openalex.org/W3096806995","https://openalex.org/W3119221111","https://openalex.org/W3204420730","https://openalex.org/W3216976702","https://openalex.org/W4224920206","https://openalex.org/W4285019302","https://openalex.org/W4294435344","https://openalex.org/W4313065316","https://openalex.org/W4372263908","https://openalex.org/W4385571418","https://openalex.org/W4386057728","https://openalex.org/W4391020683"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-31T00:00:00"}
