{"id":"https://openalex.org/W2401811665","doi":"https://doi.org/10.21437/interspeech.2011-569","title":"Automatic viseme clustering for audiovisual speech synthesis","display_name":"Automatic viseme clustering for audiovisual speech synthesis","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W2401811665","doi":"https://doi.org/10.21437/interspeech.2011-569","mag":"2401811665"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-569","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-569","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","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/A5058232885","display_name":"Wesley Mattheyses","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wesley Mattheyses","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041045271","display_name":"Lukas Latacz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lukas Latacz","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5109089316","display_name":"Werner Verhelst","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Werner Verhelst","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5058232885"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6236,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.71313342,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2173","last_page":"2176"},"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":0.9948999881744385,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9842000007629395,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.9932694435119629},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7453591227531433},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7262197136878967},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.658995509147644},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5565697550773621},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.49882936477661133},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4252052307128906},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36924779415130615},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.20168280601501465},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07653388381004333}],"concepts":[{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.9932694435119629},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7453591227531433},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7262197136878967},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.658995509147644},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5565697550773621},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.49882936477661133},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4252052307128906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36924779415130615},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.20168280601501465},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07653388381004333},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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:10.21437/interspeech.2011-569","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-569","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"},{"id":"pmh:oai:vubissmart:VUBISSMART:2000:69689","is_oa":false,"landing_page_url":"https://biblio.vub.ac.be/vubir/automatic-viseme-clustering-for-audiovisual-speech-synthesis(0581a652-b547-418f-b321-f6c20bfb42b9).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":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1262337263","https://openalex.org/W1552213476","https://openalex.org/W1565009026","https://openalex.org/W1769974409","https://openalex.org/W2036948202","https://openalex.org/W2083792893","https://openalex.org/W2099257899","https://openalex.org/W2171012658","https://openalex.org/W2401229964"],"related_works":["https://openalex.org/W1974357398","https://openalex.org/W2053099149","https://openalex.org/W4253235840","https://openalex.org/W1559261064","https://openalex.org/W2124254345","https://openalex.org/W2116497041","https://openalex.org/W2591964346","https://openalex.org/W2105537028","https://openalex.org/W131634123","https://openalex.org/W1910748333"],"abstract_inverted_index":{"A":[0,46],"common":[1],"approach":[2,75],"in":[3,29,64,140],"visual":[4,120],"speech":[5,24,121],"synthesis":[6,25,44,79,127,130],"is":[7,52,56,110,132],"the":[8,33,59,83,98,119,128,135,141],"use":[9],"of":[10,15,113,118,137],"visemes":[11,90],"as":[12],"atomic":[13],"units":[14],"speech.":[16,143],"In":[17,81,123],"this":[18],"paper,":[19],"phonemebased":[20],"and":[21,38,54,68],"viseme-based":[22,101,126],"audiovisual":[23,41,138],"techniques":[26],"are":[27,91],"compared":[28,57],"order":[30],"to":[31,58,77],"explore":[32],"balancing":[34],"between":[35],"data":[36],"availability":[37],"an":[39],"improved":[40],"coherence":[42,139],"for":[43,48],"optimization.":[45],"technique":[47],"automatic":[49],"viseme":[50,61],"clustering":[51],"described":[53,63],"it":[55],"standardized":[60],"set":[62],"MPEG-4.":[65],"Both":[66],"objective":[67],"subjective":[69],"testing":[70],"indicated":[71],"that":[72,105],"a":[73,106],"phoneme-based":[74],"leads":[76],"better":[78],"results.":[80],"addition,":[82,124],"test":[84],"results":[85],"improve":[86],"when":[87],"more":[88],"different":[89],"defined.":[92],"This":[93],"raises":[94],"some":[95],"questions":[96],"on":[97],"widely":[99],"applied":[100],"approach.":[102],"It":[103],"appears":[104],"many-to-one":[107],"phoneme-to-viseme":[108],"mapping":[109],"not":[111],"capable":[112],"describing":[114],"all":[115],"subtle":[116],"details":[117],"information.":[122],"with":[125],"perceived":[129],"quality":[131],"affected":[133],"by":[134],"loss":[136],"synthetic":[142]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
