{"id":"https://openalex.org/W2108967524","doi":"https://doi.org/10.1109/mmsp.2008.4665203","title":"Accurate visual speech synthesis based on diviseme unit selection and concatenation","display_name":"Accurate visual speech synthesis based on diviseme unit selection and concatenation","publication_year":2008,"publication_date":"2008-10-01","ids":{"openalex":"https://openalex.org/W2108967524","doi":"https://doi.org/10.1109/mmsp.2008.4665203","mag":"2108967524"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp.2008.4665203","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2008.4665203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE 10th Workshop on Multimedia Signal Processing","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/A5102021514","display_name":"Dongmei Jiang","orcid":"https://orcid.org/0000-0002-6238-8499"},"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":"Dongmei Jiang","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi'an, China","Joint Res. Group on Audio Visual Signal Process., Northwestern Polytech. Univ., Xian"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Joint Res. Group on Audio Visual Signal Process., Northwestern Polytech. Univ., Xian","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090286698","display_name":"Ilse Ravyse","orcid":null},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]},{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["BE","NL"],"is_corresponding":false,"raw_author_name":"Ilse Ravyse","raw_affiliation_strings":["Department ETRO, Vrije Universiteit Brussel, Brussels, Belgium","Dept. ETRO, Vrije Univ. Brussel, Brussel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department ETRO, Vrije Universiteit Brussel, Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]},{"raw_affiliation_string":"Dept. ETRO, Vrije Univ. Brussel, Brussel","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073820422","display_name":"Hichem Sahli","orcid":"https://orcid.org/0000-0002-1774-2970"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]},{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["BE","NL"],"is_corresponding":false,"raw_author_name":"Hichem Sahli","raw_affiliation_strings":["Department ETRO, Vrije Universiteit Brussel, Brussels, Belgium","Dept. ETRO, Vrije Univ. Brussel, Brussel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department ETRO, Vrije Universiteit Brussel, Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]},{"raw_affiliation_string":"Dept. ETRO, Vrije Univ. Brussel, Brussel","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028235866","display_name":"Yanning Zhang","orcid":"https://orcid.org/0000-0002-2977-8057"},"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":"Yanning Zhang","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi'an, China","Joint Research Group on Audio Visual Signal Processing (AVSP), Northwestern Polytechnical University, School of Computer Science, 127 Youyi Xilu, Xi\u00bfan 710072, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Joint Research Group on Audio Visual Signal Processing (AVSP), Northwestern Polytechnical University, School of Computer Science, 127 Youyi Xilu, Xi\u00bfan 710072, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":null,"first_page":"906","last_page":"909"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.998199999332428,"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"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.998199999332428,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9965000152587891,"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":0.9951000213623047,"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/viseme","display_name":"Viseme","score":0.913698136806488},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.8184296488761902},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8137717247009277},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.7154911756515503},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6878798604011536},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5721789002418518},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5568154454231262},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5524258017539978},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47290050983428955},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.46004536747932434},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.4574422836303711},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41688358783721924},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4132798910140991},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34308701753616333},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3305269479751587},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.16677993535995483},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.10894465446472168},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0954512357711792}],"concepts":[{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.913698136806488},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.8184296488761902},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8137717247009277},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7154911756515503},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6878798604011536},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5721789002418518},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5568154454231262},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5524258017539978},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47290050983428955},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.46004536747932434},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.4574422836303711},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41688358783721924},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4132798910140991},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34308701753616333},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3305269479751587},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.16677993535995483},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.10894465446472168},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0954512357711792},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/mmsp.2008.4665203","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2008.4665203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE 10th Workshop on Multimedia Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:vubissmart:VUBISSMART:2000:48170","is_oa":false,"landing_page_url":"https://biblio.vub.ac.be/vubir/accurate-visual-speech-synthesis-based-on-diviseme-unit-selection-and-concatenation(af8b66ed-da1c-470a-87b2-9ea1f3215460).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306402573","display_name":"VUBIR (Vrije Universiteit Brussel)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I13469542","host_organization_name":"Vrije Universiteit Brussel","host_organization_lineage":["https://openalex.org/I13469542"],"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":"bookitem"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","score":0.6700000166893005,"display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W222076935","https://openalex.org/W1551668628","https://openalex.org/W2075316843","https://openalex.org/W2097398294","https://openalex.org/W2128173845","https://openalex.org/W2136813256","https://openalex.org/W2141657634","https://openalex.org/W2143640516","https://openalex.org/W2155129098","https://openalex.org/W4252332688","https://openalex.org/W6608730375","https://openalex.org/W6681131457"],"related_works":["https://openalex.org/W234770729","https://openalex.org/W2588431733","https://openalex.org/W2391796527","https://openalex.org/W2387179309","https://openalex.org/W2388979876","https://openalex.org/W4245668640","https://openalex.org/W2032960563","https://openalex.org/W2142993035","https://openalex.org/W2401811665","https://openalex.org/W2899044948"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,36,40],"novel":[4],"speech":[5,10,33,117],"driven":[6],"accurate":[7],"realistic":[8,135],"visual":[9,16,32],"synthesis":[11,118],"approach.":[12],"Firstly,":[13],"an":[14],"audio":[15,31],"instance":[17,42],"database":[18],"is":[19,45],"built":[20],"for":[21,53],"different":[22],"viseme":[23,55,95],"context":[24],"combinations,":[25],"i.e.":[26],"diviseme":[27,41,51,100],"units,":[28],"using":[29],"100":[30],"sentences":[34],"of":[35,66,72,85,93,112,153],"female":[37],"speaker.":[38],"Then":[39],"selection":[43],"algorithm":[44],"introduced":[46],"to":[47,76,107],"choose":[48],"the":[49,54,58,63,67,73,77,83,86,98,109,113,148,154],"optimal":[50],"instances":[52,101],"contexts":[56],"in":[57,97,144],"input":[59,87,155],"speech,":[60],"considering":[61],"both":[62],"concatenation":[64],"smoothness":[65],"image":[68,91],"sequences,":[69],"and":[70,105,120,138,151],"matching":[71],"mouth":[74,90,110,126,140],"movements":[75],"acoustic":[78,149],"pronunciation":[79,150],"process,":[80],"as":[81],"well":[82],"intensity":[84,152],"speech.":[88,156],"Finally":[89],"sequences":[92],"corresponding":[94],"segments":[96],"selected":[99],"are":[102,132],"time":[103],"warped":[104],"blended":[106],"construct":[108],"images":[111],"final":[114],"animation.":[115],"Visual":[116],"experiments":[119],"subjective":[121],"evaluation":[122],"results":[123],"show":[124],"that":[125],"animations":[127],"can":[128],"be":[129],"obtained":[130],"which":[131],"not":[133],"only":[134],"with":[136,147],"clear":[137],"smooth":[139],"images,":[141],"but":[142],"also":[143],"good":[145],"accordance":[146]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
