{"id":"https://openalex.org/W4409916798","doi":"https://doi.org/10.1109/tce.2025.3565518","title":"Audio-Driven Talking Face Generation With Segmented Static Facial References for Customized Health Device Interactions","display_name":"Audio-Driven Talking Face Generation With Segmented Static Facial References for Customized Health Device Interactions","publication_year":2025,"publication_date":"2025-04-29","ids":{"openalex":"https://openalex.org/W4409916798","doi":"https://doi.org/10.1109/tce.2025.3565518"},"language":"en","primary_location":{"id":"doi:10.1109/tce.2025.3565518","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tce.2025.3565518","pdf_url":null,"source":{"id":"https://openalex.org/S126824455","display_name":"IEEE Transactions on Consumer Electronics","issn_l":"0098-3063","issn":["0098-3063","1558-4127"],"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 Consumer Electronics","raw_type":"journal-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/A5052793870","display_name":"Z. Wang","orcid":"https://orcid.org/0000-0003-1728-9106"},"institutions":[{"id":"https://openalex.org/I75920027","display_name":"Shaanxi University of Chinese Medicine","ror":"https://ror.org/021r98132","country_code":"CN","type":"education","lineage":["https://openalex.org/I75920027"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zige Wang","raw_affiliation_strings":["Shaanxi University of Chinese Medicine, Xianyang, China"],"affiliations":[{"raw_affiliation_string":"Shaanxi University of Chinese Medicine, Xianyang, China","institution_ids":["https://openalex.org/I75920027"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104136191","display_name":"Yuansheng Wang","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":"Yashuai Wang","raw_affiliation_strings":["Lab of ASGO, Northwestern Polytechnical University, Xi&#x2019;an, China","Northwestern Polytechnical University, Xi&#x2019;an, China"],"affiliations":[{"raw_affiliation_string":"Lab of ASGO, Northwestern Polytechnical University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Northwestern Polytechnical University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102771621","display_name":"Tianyu Liu","orcid":"https://orcid.org/0000-0002-9098-5944"},"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":"Tianyu Liu","raw_affiliation_strings":["Lab of ASGO, Northwestern Polytechnical University, Xi&#x2019;an, China","Northwestern Polytechnical University, Xi&#x2019;an, China"],"affiliations":[{"raw_affiliation_string":"Lab of ASGO, Northwestern Polytechnical University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Northwestern Polytechnical University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100364068","display_name":"Peng Zhang","orcid":"https://orcid.org/0000-0001-9690-7026"},"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":"Peng Zhang","raw_affiliation_strings":["Lab of ASGO, Northwestern Polytechnical University, Xi&#x2019;an, China","Northwestern Polytechnical University, Xi&#x2019;an, China"],"affiliations":[{"raw_affiliation_string":"Lab of ASGO, Northwestern Polytechnical University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Northwestern Polytechnical University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"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":["Lab of ASGO, Northwestern Polytechnical University, Xi&#x2019;an, China","Northwestern Polytechnical University, Xi&#x2019;an, China"],"affiliations":[{"raw_affiliation_string":"Lab of ASGO, Northwestern Polytechnical University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Northwestern Polytechnical University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101863641","display_name":"Yangming Guo","orcid":"https://orcid.org/0009-0001-5095-5206"},"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":"Yangming Guo","raw_affiliation_strings":["Northwestern Polytechnical University, Xi&#x2019;an, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5052793870"],"corresponding_institution_ids":["https://openalex.org/I75920027"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09189183,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"71","issue":"2","first_page":"5404","last_page":"5413"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9822999835014343,"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":0.9822999835014343,"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":0.6408638954162598},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5274627208709717},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41751429438591003},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4173818826675415}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6408638954162598},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5274627208709717},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41751429438591003},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4173818826675415},{"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:10.1109/tce.2025.3565518","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tce.2025.3565518","pdf_url":null,"source":{"id":"https://openalex.org/S126824455","display_name":"IEEE Transactions on Consumer Electronics","issn_l":"0098-3063","issn":["0098-3063","1558-4127"],"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 Consumer Electronics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1509031088","https://openalex.org/W1958813769","https://openalex.org/W2008682880","https://openalex.org/W2036311310","https://openalex.org/W2099471712","https://openalex.org/W2551572271","https://openalex.org/W2594690981","https://openalex.org/W2808631503","https://openalex.org/W2963081548","https://openalex.org/W2963290645","https://openalex.org/W2981767644","https://openalex.org/W3003662786","https://openalex.org/W3014285442","https://openalex.org/W3082767564","https://openalex.org/W3216543548","https://openalex.org/W3216666832","https://openalex.org/W4301600672","https://openalex.org/W4385597705","https://openalex.org/W4386071653","https://openalex.org/W4386767017","https://openalex.org/W4387250129","https://openalex.org/W4387935946","https://openalex.org/W4389665206","https://openalex.org/W4390154864","https://openalex.org/W4391375463","https://openalex.org/W4399125962","https://openalex.org/W4399266740","https://openalex.org/W4401357754","https://openalex.org/W4409601591"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0],"a":[1,186],"variety":[2],"of":[3,23,57,117,140],"human-machine":[4],"interaction":[5],"(HMI)":[6],"applications,":[7,185],"the":[8,21,38,44,49,55,62,66,72,96,107,115,118,129,138,141,147,155,166,173,193,197],"high-level":[9],"techniques":[10],"based":[11],"on":[12,146,192],"audio-driven":[13],"talking":[14],"face":[15],"generation":[16],"are":[17,90,158],"often":[18],"challenged":[19],"by":[20,36,61,133],"issues":[22],"temporal":[24,45,130],"misalignment":[25],"and":[26,71,85,121,149,168],"low-quality":[27],"outputs.":[28,143],"Recent":[29],"solutions":[30],"have":[31,152],"sought":[32],"to":[33,53,92,127,160],"improve":[34,93],"synchronization":[35],"maximizing":[37],"similarity":[39],"between":[40,65],"audio-visual":[41],"pairs.":[42],"However,":[43],"disturbances":[46],"introduced":[47],"during":[48,95],"inference":[50,97,119,163],"phase":[51],"continue":[52],"limit":[54],"enhancement":[56],"generative":[58],"performance.":[59],"Inspired":[60],"intrinsic":[63],"connection":[64],"segmented":[67],"static":[68,124],"facial":[69,125],"image":[70],"stable":[73],"appearance":[74],"representation,":[75],"in":[76,182],"this":[77],"study,":[78],"two":[79],"strategies,":[80],"Manual":[81],"Temporal":[82],"Segmentation":[83],"(MTS)":[84],"Static":[86],"Facial":[87],"Reference":[88],"(SFR),":[89],"proposed":[91,156,198],"performance":[94,164],"stage.":[98],"The":[99],"corresponding":[100],"functionality":[101],"consists":[102],"of:":[103],"MTS":[104],"involves":[105],"segmenting":[106],"input":[108],"video":[109],"into":[110],"several":[111],"clips,":[112],"effectively":[113],"reducing":[114],"complexity":[116],"process,":[120],"SFR":[122],"utilizes":[123],"references":[126],"mitigate":[128],"noise":[131],"generated":[132,142],"dynamic":[134],"sequences,":[135],"thereby":[136],"enhancing":[137],"quality":[139],"Substantial":[144],"experiments":[145],"LRS2":[148],"VoxCeleb2":[150],"datasets":[151],"demonstrated":[153],"that":[154],"strategies":[157],"able":[159],"significantly":[161],"enhance":[162],"with":[165,196],"LSE-C":[167],"LSE-D":[169],"metrics,":[170],"without":[171],"altering":[172],"network":[174],"architecture":[175],"or":[176],"training":[177],"strategy.":[178],"For":[179],"effectiveness":[180],"validation":[181],"realistic":[183],"scenario":[184],"deployment":[187],"has":[188],"also":[189],"been":[190],"conducted":[191],"healthcare":[194],"devices":[195],"solution.":[199]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
