{"id":"https://openalex.org/W4367665543","doi":"https://doi.org/10.1109/vrw58643.2023.00145","title":"Audio to Deep Visual: Speaking Mouth Generation Based on 3D Sparse Landmarks","display_name":"Audio to Deep Visual: Speaking Mouth Generation Based on 3D Sparse Landmarks","publication_year":2023,"publication_date":"2023-03-01","ids":{"openalex":"https://openalex.org/W4367665543","doi":"https://doi.org/10.1109/vrw58643.2023.00145"},"language":"en","primary_location":{"id":"doi:10.1109/vrw58643.2023.00145","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/vrw58643.2023.00145","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW)","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/A5046565976","display_name":"Hui Fang","orcid":"https://orcid.org/0000-0001-9365-7420"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Fang","raw_affiliation_strings":["School of Optics and Photonics, Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Optics and Photonics, Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080838784","display_name":"Dongdong Weng","orcid":"https://orcid.org/0000-0003-2352-0896"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongdong Weng","raw_affiliation_strings":["School of Optics and Photonics, Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Optics and Photonics, Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014732889","display_name":"Zeyu Tian","orcid":"https://orcid.org/0009-0006-5079-8745"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyu Tian","raw_affiliation_strings":["School of Optics and Photonics, Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Optics and Photonics, Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020224567","display_name":"Zhen Song","orcid":"https://orcid.org/0000-0001-8381-0225"},"institutions":[{"id":"https://openalex.org/I2802776907","display_name":"Central Academy of Drama","ror":"https://ror.org/03hkga097","country_code":"CN","type":"education","lineage":["https://openalex.org/I2802776907"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Song","raw_affiliation_strings":["Advanced Research Center For Digitalization of the Traditional Drama, The Central Academy of Drama"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Research Center For Digitalization of the Traditional Drama, The Central Academy of Drama","institution_ids":["https://openalex.org/I2802776907"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"605","last_page":"606"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.996399998664856,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9871000051498413,"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":0.8235287666320801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5890271663665771},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5010137557983398},{"id":"https://openalex.org/keywords/sync","display_name":"sync","score":0.5004501342773438},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46450942754745483},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.42009836435317993},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4164505898952484}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8235287666320801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5890271663665771},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5010137557983398},{"id":"https://openalex.org/C3913047","wikidata":"https://www.wikidata.org/wiki/Q1956265","display_name":"sync","level":3,"score":0.5004501342773438},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46450942754745483},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.42009836435317993},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4164505898952484},{"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/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vrw58643.2023.00145","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/vrw58643.2023.00145","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2115252128","https://openalex.org/W2769666294","https://openalex.org/W2944294033","https://openalex.org/W2949662773","https://openalex.org/W2980581183","https://openalex.org/W3104792420","https://openalex.org/W3203407300","https://openalex.org/W3209059054","https://openalex.org/W4200174933","https://openalex.org/W4385245566","https://openalex.org/W6677618333","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W2624451073","https://openalex.org/W2104325098","https://openalex.org/W2005984284","https://openalex.org/W2687972263","https://openalex.org/W2981958238","https://openalex.org/W2029249305","https://openalex.org/W2096175171","https://openalex.org/W2030131924","https://openalex.org/W2110645484","https://openalex.org/W2118983851"],"abstract_inverted_index":{"Having":[0],"a":[1,6,26],"system":[2],"to":[3,44,52],"automatically":[4],"generate":[5,31],"talking":[7,33,88],"mouth":[8,34,47,61,96],"in":[9,75],"sync":[10],"with":[11],"input":[12],"speech":[13,16],"would":[14],"enhance":[15],"communication":[17],"and":[18,54,93],"enable":[19],"many":[20],"novel":[21],"applications.":[22],"This":[23],"article":[24],"presents":[25],"new":[27],"model":[28,45],"that":[29,85],"can":[30],"3D":[32,42,95],"landmarks":[35,43,89],"from":[36],"Chinese":[37,77],"speech.":[38],"We":[39],"use":[40],"sparse":[41],"the":[46,73,76,86],"motion,":[48],"which":[49],"are":[50],"easy":[51],"capture":[53,70],"provide":[55],"sufficient":[56],"lip":[57,79],"accuracy.":[58],"The":[59,81],"4D":[60],"motion":[62],"dataset":[63],"was":[64],"collected":[65],"by":[66],"our":[67],"self-developed":[68],"facial":[69],"device,":[71],"filling":[72],"gap":[74],"speech-driven":[78],"dataset.":[80],"exper-imental":[82],"results":[83],"show":[84],"generated":[87],"achieve":[90],"accurate,":[91],"smooth,":[92],"natural":[94],"movements.":[97]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}