{"id":"https://openalex.org/W4200371243","doi":"https://doi.org/10.1109/cisp-bmei53629.2021.9624360","title":"A Novel Speech-Driven Lip-Sync Model with CNN and LSTM","display_name":"A Novel Speech-Driven Lip-Sync Model with CNN and LSTM","publication_year":2021,"publication_date":"2021-10-23","ids":{"openalex":"https://openalex.org/W4200371243","doi":"https://doi.org/10.1109/cisp-bmei53629.2021.9624360"},"language":"en","primary_location":{"id":"doi:10.1109/cisp-bmei53629.2021.9624360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cisp-bmei53629.2021.9624360","pdf_url":null,"source":{"id":"https://openalex.org/S4363605805","display_name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2205.00916","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100451524","display_name":"Xiaohong Li","orcid":"https://orcid.org/0000-0003-1187-2042"},"institutions":[{"id":"https://openalex.org/I6507939","display_name":"China United Network Communications Group (China)","ror":"https://ror.org/028w99c90","country_code":"CN","type":"company","lineage":["https://openalex.org/I6507939"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaohong Li","raw_affiliation_strings":["AI Innovation and Application Center, China Unicom, Beijing, China"],"affiliations":[{"raw_affiliation_string":"AI Innovation and Application Center, China Unicom, Beijing, China","institution_ids":["https://openalex.org/I6507939"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389069","display_name":"Xiang Wang","orcid":"https://orcid.org/0000-0003-3893-3888"},"institutions":[{"id":"https://openalex.org/I6507939","display_name":"China United Network Communications Group (China)","ror":"https://ror.org/028w99c90","country_code":"CN","type":"company","lineage":["https://openalex.org/I6507939"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Wang","raw_affiliation_strings":["AI Innovation and Application Center, China Unicom, Beijing, China"],"affiliations":[{"raw_affiliation_string":"AI Innovation and Application Center, China Unicom, Beijing, China","institution_ids":["https://openalex.org/I6507939"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008534055","display_name":"Kai Wang","orcid":"https://orcid.org/0000-0002-7767-2329"},"institutions":[{"id":"https://openalex.org/I6507939","display_name":"China United Network Communications Group (China)","ror":"https://ror.org/028w99c90","country_code":"CN","type":"company","lineage":["https://openalex.org/I6507939"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Wang","raw_affiliation_strings":["AI Innovation and Application Center, China Unicom, Beijing, China"],"affiliations":[{"raw_affiliation_string":"AI Innovation and Application Center, China Unicom, Beijing, China","institution_ids":["https://openalex.org/I6507939"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066958531","display_name":"Shiguo Lian","orcid":"https://orcid.org/0000-0003-4308-7049"},"institutions":[{"id":"https://openalex.org/I6507939","display_name":"China United Network Communications Group (China)","ror":"https://ror.org/028w99c90","country_code":"CN","type":"company","lineage":["https://openalex.org/I6507939"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiguo Lian","raw_affiliation_strings":["AI Innovation and Application Center, China Unicom, Beijing, China"],"affiliations":[{"raw_affiliation_string":"AI Innovation and Application Center, China Unicom, Beijing, China","institution_ids":["https://openalex.org/I6507939"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100451524"],"corresponding_institution_ids":["https://openalex.org/I6507939"],"apc_list":null,"apc_paid":null,"fwci":0.1314,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.49491623,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9997000098228455,"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/T12290","display_name":"Human Motion and Animation","score":0.9800000190734863,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8013565540313721},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7640787363052368},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6524165868759155},{"id":"https://openalex.org/keywords/sync","display_name":"sync","score":0.5977810025215149},{"id":"https://openalex.org/keywords/jitter","display_name":"Jitter","score":0.5197098255157471},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.4796162545681},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.466163694858551},{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.4649800956249237},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45877206325531006},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.41799402236938477},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.4166693687438965},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.38616716861724854},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.2757292687892914},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.22609290480613708},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.09596514701843262}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8013565540313721},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7640787363052368},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6524165868759155},{"id":"https://openalex.org/C3913047","wikidata":"https://www.wikidata.org/wiki/Q1956265","display_name":"sync","level":3,"score":0.5977810025215149},{"id":"https://openalex.org/C134652429","wikidata":"https://www.wikidata.org/wiki/Q1052698","display_name":"Jitter","level":2,"score":0.5197098255157471},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.4796162545681},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.466163694858551},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.4649800956249237},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45877206325531006},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.41799402236938477},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.4166693687438965},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.38616716861724854},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.2757292687892914},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.22609290480613708},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.09596514701843262},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cisp-bmei53629.2021.9624360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cisp-bmei53629.2021.9624360","pdf_url":null,"source":{"id":"https://openalex.org/S4363605805","display_name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2205.00916","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.00916","pdf_url":"https://arxiv.org/pdf/2205.00916","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2205.00916","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.00916","pdf_url":"https://arxiv.org/pdf/2205.00916","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1922655562","https://openalex.org/W1974357398","https://openalex.org/W2148154194","https://openalex.org/W2152826865","https://openalex.org/W2271840356","https://openalex.org/W2284628133","https://openalex.org/W2289286917","https://openalex.org/W2468212864","https://openalex.org/W2519091744","https://openalex.org/W2738406145","https://openalex.org/W2769666294","https://openalex.org/W2804619907","https://openalex.org/W2807126412","https://openalex.org/W2950248412","https://openalex.org/W2981263323","https://openalex.org/W3120163087","https://openalex.org/W4245923654","https://openalex.org/W6640090968","https://openalex.org/W6694517276","https://openalex.org/W6695553435"],"related_works":["https://openalex.org/W2401811665","https://openalex.org/W1974357398","https://openalex.org/W2295574089","https://openalex.org/W2053099149","https://openalex.org/W2350195158","https://openalex.org/W1559261064","https://openalex.org/W1792455311","https://openalex.org/W2361328929","https://openalex.org/W2087756952","https://openalex.org/W3133492806"],"abstract_inverted_index":{"Generating":[0],"synchronized":[1,157],"and":[2,33,99,126,141,153],"natural":[3,154],"lip":[4,67,155],"movement":[5,64],"with":[6,71,158],"speech":[7,47,92,97],"is":[8,59,69,104,148],"one":[9],"of":[10,30,39,51,55,65,81,110,118,120,136],"the":[11,52,56,62,72,79,82,108,134],"most":[12],"important":[13],"tasks":[14],"in":[15],"creating":[16],"realistic":[17],"virtual":[18],"characters.":[19],"In":[20,75],"this":[21],"paper,":[22],"we":[23,88],"present":[24],"a":[25,40,90,100,116,121,128],"combined":[26],"deep":[27],"neural":[28],"network":[29,83],"one-dimensional":[31],"convolutions":[32],"LSTM":[34],"to":[35,77,84,95,106,132,150],"generate":[36,151],"vertex":[37,63],"displacement":[38],"3D":[41,66],"template":[42],"face":[43],"model":[44,94,147],"from":[45],"variable-length":[46],"input.":[48],"The":[49],"motion":[50],"lower":[53],"part":[54],"face,":[57],"which":[58],"represented":[60],"by":[61],"shapes,":[68],"consistent":[70],"input":[73],"speech.":[74,159],"order":[76],"enhance":[78],"robustness":[80],"different":[85],"sound":[86],"signals,":[87],"adapt":[89],"trained":[91],"recognition":[93],"extract":[96],"feature,":[98],"velocity":[101],"loss":[102],"term":[103],"adopted":[105],"reduce":[107],"jitter":[109],"generated":[111],"facial":[112],"animation.":[113],"We":[114],"recorded":[115],"series":[117],"videos":[119],"Chinese":[122],"adult":[123],"speaking":[124],"Mandarin":[125],"created":[127],"new":[129],"speech-animation":[130],"dataset":[131],"compensate":[133],"lack":[135],"such":[137],"public":[138],"data.":[139],"Qualitative":[140],"quantitative":[142],"evaluations":[143],"indicate":[144],"that":[145],"our":[146],"able":[149],"smooth":[152],"movements":[156]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}