{"id":"https://openalex.org/W2073776768","doi":"https://doi.org/10.1109/icassp.2010.5494894","title":"Realistic mouth animation based on an articulatory DBN model with constrained asynchrony","display_name":"Realistic mouth animation based on an articulatory DBN model with constrained asynchrony","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2073776768","doi":"https://doi.org/10.1109/icassp.2010.5494894","mag":"2073776768"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5494894","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5494894","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-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/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":true,"raw_author_name":"Dongmei Jiang","raw_affiliation_strings":["VUB-NPU Joint Research Group on Audio Visual Signal Processing (AVSP), Northwestern Polytechnical University, Xi'an, China","VUB-NPU Joint Research Group on Audio Visual Signal Processing (AVSP), Northwestern Polytechnical University, Xi'an 710072, China"],"affiliations":[{"raw_affiliation_string":"VUB-NPU Joint Research Group on Audio Visual Signal Processing (AVSP), Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"VUB-NPU Joint Research Group on Audio Visual Signal Processing (AVSP), Northwestern Polytechnical University, Xi'an 710072, China","institution_ids":["https://openalex.org/I17145004"]}]},{"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"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Ilse Ravyse","raw_affiliation_strings":["Department ETRO, Vrije Universiteit Brussel, Brussels, Belgium","VUB-NPU Joint Research Group on Audio Visual Signal Processing (AVSP), Vrije Universiteit Brussel, Department ETRO, Pleinlaan 2, 1050 Brussels, Belgium"],"affiliations":[{"raw_affiliation_string":"Department ETRO, Vrije Universiteit Brussel, Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]},{"raw_affiliation_string":"VUB-NPU Joint Research Group on Audio Visual Signal Processing (AVSP), Vrije Universiteit Brussel, Department ETRO, Pleinlaan 2, 1050 Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008154433","display_name":"Peizhen Liu","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":"Peizhen Liu","raw_affiliation_strings":["VUB-NPU Joint Research Group on Audio Visual Signal Processing (AVSP), Northwestern Polytechnical University, Xi'an, China","VUB-NPU Joint Research Group on Audio Visual Signal Processing (AVSP), Northwestern Polytechnical University, Xi'an 710072, China"],"affiliations":[{"raw_affiliation_string":"VUB-NPU Joint Research Group on Audio Visual Signal Processing (AVSP), Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"VUB-NPU Joint Research Group on Audio Visual Signal Processing (AVSP), Northwestern Polytechnical University, Xi'an 710072, China","institution_ids":["https://openalex.org/I17145004"]}]},{"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"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Hichem Sahli","raw_affiliation_strings":["Department ETRO, Vrije Universiteit Brussel, Brussels, Belgium","VUB-NPU Joint Research Group on Audio Visual Signal Processing (AVSP), Vrije Universiteit Brussel, Department ETRO, Pleinlaan 2, 1050 Brussels, Belgium"],"affiliations":[{"raw_affiliation_string":"Department ETRO, Vrije Universiteit Brussel, Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]},{"raw_affiliation_string":"VUB-NPU Joint Research Group on Audio Visual Signal Processing (AVSP), Vrije Universiteit Brussel, Department ETRO, Pleinlaan 2, 1050 Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109089316","display_name":"Werner Verhelst","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"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Werner Verhelst","raw_affiliation_strings":["Department ETRO, Vrije Universiteit Brussel, Brussels, Belgium","VUB-NPU Joint Research Group on Audio Visual Signal Processing (AVSP), Vrije Universiteit Brussel, Department ETRO, Pleinlaan 2, 1050 Brussels, Belgium"],"affiliations":[{"raw_affiliation_string":"Department ETRO, Vrije Universiteit Brussel, Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]},{"raw_affiliation_string":"VUB-NPU Joint Research Group on Audio Visual Signal Processing (AVSP), Vrije Universiteit Brussel, Department ETRO, Pleinlaan 2, 1050 Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102021514"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.682,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.69510591,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"3024","issue":null,"first_page":"2478","last_page":"2481"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9761999845504761,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9236999750137329,"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/upsampling","display_name":"Upsampling","score":0.7895512580871582},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7759736776351929},{"id":"https://openalex.org/keywords/asynchrony","display_name":"Asynchrony (computer programming)","score":0.7102887034416199},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6478756666183472},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.562355101108551},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5408523678779602},{"id":"https://openalex.org/keywords/dynamic-bayesian-network","display_name":"Dynamic Bayesian network","score":0.4954155683517456},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4727127254009247},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44869306683540344},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.4403689205646515},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3888430595397949},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.2500641345977783},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14857348799705505},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13692396879196167},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.09389001131057739},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.08821812272071838}],"concepts":[{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.7895512580871582},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7759736776351929},{"id":"https://openalex.org/C2779019669","wikidata":"https://www.wikidata.org/wiki/Q25203946","display_name":"Asynchrony (computer programming)","level":3,"score":0.7102887034416199},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6478756666183472},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.562355101108551},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5408523678779602},{"id":"https://openalex.org/C82142266","wikidata":"https://www.wikidata.org/wiki/Q3456604","display_name":"Dynamic Bayesian network","level":3,"score":0.4954155683517456},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4727127254009247},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44869306683540344},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4403689205646515},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3888430595397949},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2500641345977783},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14857348799705505},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13692396879196167},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.09389001131057739},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.08821812272071838},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2010.5494894","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5494894","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1551668628","https://openalex.org/W1867429401","https://openalex.org/W1973686310","https://openalex.org/W2105055531","https://openalex.org/W2114336453","https://openalex.org/W2122678358","https://openalex.org/W2128173845","https://openalex.org/W2148226542","https://openalex.org/W6639126518","https://openalex.org/W6675803844","https://openalex.org/W6678062257"],"related_works":["https://openalex.org/W2062399876","https://openalex.org/W2534656837","https://openalex.org/W2607795551","https://openalex.org/W3155117723","https://openalex.org/W1991429770","https://openalex.org/W2017210410","https://openalex.org/W1993009522","https://openalex.org/W1995792634","https://openalex.org/W2135672910","https://openalex.org/W2378274372"],"abstract_inverted_index":{"In":[0,68],"this":[1],"paper,":[2],"we":[3],"propose":[4],"an":[5,18,60],"approach":[6],"to":[7,11,33,53,138],"convert":[8],"acoustic":[9],"speech":[10],"video":[12],"realistic":[13,128],"mouth":[14,83,94,129],"animation":[15,95],"based":[16],"on":[17],"articulatory":[19,150],"dynamic":[20],"Bayesian":[21],"network":[22],"model":[23,152],"with":[24],"constrained":[25],"asynchrony":[26,154],"(AF_AVDBN).":[27],"Conditional":[28],"probability":[29],"distributions":[30],"are":[31,86,109],"defined":[32],"control":[34],"the":[35,38,55,64,69,72,81,93,98,118,132,139,142],"asynchronies":[36],"between":[37],"articulators":[39],"such":[40],"as":[41,88],"lips,":[42],"tongue":[43],"and":[44,63,105,113,127,131,149],"glottis/velum.":[45],"An":[46],"EM-based":[47],"conversion":[48],"algorithm":[49],"is":[50,121,134],"also":[51],"presented":[52],"learn":[54],"optimal":[56],"visual":[57,89,100],"features":[58,79],"given":[59],"auditory":[61],"input":[62],"trained":[65],"AF_AVDBN":[66,73],"parameters.":[67],"training":[70],"of":[71,80,123,141],"models,":[74],"downsampled":[75],"YUV":[76],"spatial":[77,103],"frequency":[78],"interpolated":[82],"image":[84],"sequences":[85],"extracted":[87],"features.":[90],"For":[91],"reproducing":[92],"sequence,":[96],"from":[97],"learned":[99],"features,":[101],"a":[102,106],"upsampling":[104],"temporal":[107],"downsampling":[108],"applied.":[110],"Both":[111],"qualitative":[112],"quantitative":[114],"results":[115],"show":[116],"that":[117],"proposed":[119],"method":[120],"capable":[122],"producing":[124],"more":[125],"natural":[126],"animations,":[130],"accuracy":[133],"further":[135],"improved":[136],"compared":[137],"state":[140],"art":[143],"multi-stream":[144],"Hidden":[145],"Markov":[146],"Model":[147],"(MSHMM)":[148],"DBN":[151],"without":[153],"constraint":[155],"(AF_DBN).":[156]},"counts_by_year":[{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}