{"id":"https://openalex.org/W2405997896","doi":"https://doi.org/10.21437/icslp.2002-422","title":"Audiovisual speech synthesis. from ground truth to models","display_name":"Audiovisual speech synthesis. from ground truth to models","publication_year":2002,"publication_date":"2002-09-16","ids":{"openalex":"https://openalex.org/W2405997896","doi":"https://doi.org/10.21437/icslp.2002-422","mag":"2405997896"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.2002-422","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","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/A5071432574","display_name":"G\u00e9rard Bailly","orcid":"https://orcid.org/0000-0002-6053-0818"},"institutions":[{"id":"https://openalex.org/I106785703","display_name":"Institut polytechnique de Grenoble","ror":"https://ror.org/05sbt2524","country_code":"FR","type":"education","lineage":["https://openalex.org/I106785703","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"G\u00e9rard Bailly","raw_affiliation_strings":["Grenoble Institute of Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Grenoble Institute of Technology#TAB#","institution_ids":["https://openalex.org/I106785703"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5071432574"],"corresponding_institution_ids":["https://openalex.org/I106785703"],"apc_list":null,"apc_paid":null,"fwci":0.408,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.61031774,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1453","last_page":"1456"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9871000051498413,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9690999984741211,"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":0.7210984230041504},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.6907638311386108},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6829988360404968},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.6541364789009094},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.6075608730316162},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.598212718963623},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5347012281417847},{"id":"https://openalex.org/keywords/common-ground","display_name":"Common ground","score":0.5096101760864258},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5056135654449463},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.46933355927467346},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43922606110572815},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.41442155838012695},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.4114544689655304},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4086707830429077},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37176522612571716},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.17142823338508606},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1632995903491974},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.14260250329971313},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10436782240867615},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08602777123451233},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08443531394004822},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.08384925127029419},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07557165622711182}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7210984230041504},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.6907638311386108},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6829988360404968},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.6541364789009094},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.6075608730316162},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.598212718963623},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5347012281417847},{"id":"https://openalex.org/C2777877512","wikidata":"https://www.wikidata.org/wiki/Q1116097","display_name":"Common ground","level":2,"score":0.5096101760864258},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5056135654449463},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.46933355927467346},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43922606110572815},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.41442155838012695},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.4114544689655304},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4086707830429077},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37176522612571716},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.17142823338508606},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1632995903491974},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.14260250329971313},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10436782240867615},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08602777123451233},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08443531394004822},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.08384925127029419},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07557165622711182},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/icslp.2002-422","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W143827410","https://openalex.org/W183006904","https://openalex.org/W1532571392","https://openalex.org/W1552319954","https://openalex.org/W1554803342","https://openalex.org/W1569425235","https://openalex.org/W1693261796","https://openalex.org/W1978015745","https://openalex.org/W1996363348","https://openalex.org/W2019083158","https://openalex.org/W2047618352","https://openalex.org/W2063401705","https://openalex.org/W2105248785","https://openalex.org/W2112728655","https://openalex.org/W2120654454","https://openalex.org/W2125675458","https://openalex.org/W2128597598","https://openalex.org/W2132172443","https://openalex.org/W2148985157","https://openalex.org/W2153813006","https://openalex.org/W2156671261","https://openalex.org/W2396966646","https://openalex.org/W2404157703","https://openalex.org/W2406132719","https://openalex.org/W2533826620","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W1546315632","https://openalex.org/W1901124962","https://openalex.org/W2486181377","https://openalex.org/W2607325685","https://openalex.org/W8712222","https://openalex.org/W4307535225","https://openalex.org/W2905544777","https://openalex.org/W2108358695","https://openalex.org/W2087756952","https://openalex.org/W3133492806"],"abstract_inverted_index":{"We":[0,17,49],"present":[1],"here":[2],"the":[3,24,37,53,63,67],"main":[4],"approaches":[5],"used":[6],"to":[7,55],"synthesize":[8],"and":[9,36,44,58],"drive":[10],"talking":[11],"faces.":[12],"Illustrative":[13],"systems":[14],"are":[15,30],"described.":[16],"distinguish":[18],"between":[19],"facial":[20,28,68],"synthesis":[21],"itself":[22],"(i.e":[23],"manner":[25],"in":[26],"which":[27],"movements":[29,40],"rendered":[31],"on":[32,52,71],"a":[33,72],"computer":[34],"screen),":[35],"way":[38],"these":[39],"may":[41],"be":[42],"controlled":[43],"predicted":[45],"using":[46],"phonetic":[47],"input.":[48],"then":[50],"focus":[51],"necessity":[54],"capture,":[56],"model":[57],"render":[59],"with":[60],"maximum":[61],"fidelity":[62],"intimate":[64],"coherence":[65],"of":[66],"deformations":[69],"observed":[70],"human":[73],"face.":[74]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
