{"id":"https://openalex.org/W4375869361","doi":"https://doi.org/10.1109/icassp49357.2023.10096012","title":"On the Role of LIP Articulation in Visual Speech Perception","display_name":"On the Role of LIP Articulation in Visual Speech Perception","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869361","doi":"https://doi.org/10.1109/icassp49357.2023.10096012"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5090927958","display_name":"Zakaria Aldeneh","orcid":"https://orcid.org/0000-0003-4599-2448"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Zakaria Aldeneh","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000858764","display_name":"Masha Fedzechkina","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Masha Fedzechkina","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059839283","display_name":"Skyler Seto","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Skyler Seto","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045884826","display_name":"Katherine Metcalf","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Katherine Metcalf","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018074056","display_name":"Miguel Sarabia","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Miguel Sarabia","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071541814","display_name":"Nicholas Apostoloff","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nicholas Apostoloff","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112911728","display_name":"Barry-John Theobald","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Barry-John Theobald","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5090927958"],"corresponding_institution_ids":["https://openalex.org/I4210107260"],"apc_list":null,"apc_paid":null,"fwci":0.4075,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54316119,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9923999905586243,"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/T11309","display_name":"Music and Audio Processing","score":0.9882000088691711,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.7346751689910889},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.6931734085083008},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6742220520973206},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6275547742843628},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.5971894860267639},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5654515027999878},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4910316467285156},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.42463356256484985},{"id":"https://openalex.org/keywords/manner-of-articulation","display_name":"Manner of articulation","score":0.4152153730392456},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3644052743911743},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.3506506681442261},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3349834084510803},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3296816349029541}],"concepts":[{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.7346751689910889},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.6931734085083008},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6742220520973206},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6275547742843628},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.5971894860267639},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5654515027999878},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4910316467285156},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.42463356256484985},{"id":"https://openalex.org/C66029223","wikidata":"https://www.wikidata.org/wiki/Q210847","display_name":"Manner of articulation","level":2,"score":0.4152153730392456},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3644052743911743},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3506506681442261},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3349834084510803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3296816349029541},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":24,"referenced_works":["https://openalex.org/W2005030514","https://openalex.org/W2015143272","https://openalex.org/W2115252128","https://openalex.org/W2737658251","https://openalex.org/W2738406145","https://openalex.org/W2795230330","https://openalex.org/W2884460600","https://openalex.org/W2889214350","https://openalex.org/W2914217321","https://openalex.org/W2979894294","https://openalex.org/W2980562267","https://openalex.org/W2990452356","https://openalex.org/W3019952993","https://openalex.org/W3081492798","https://openalex.org/W3094612121","https://openalex.org/W3101631197","https://openalex.org/W3109114891","https://openalex.org/W3172598908","https://openalex.org/W3174763799","https://openalex.org/W3180770160","https://openalex.org/W3207281888","https://openalex.org/W4301962329","https://openalex.org/W6677618333","https://openalex.org/W6791043231"],"related_works":["https://openalex.org/W2063833029","https://openalex.org/W2022221551","https://openalex.org/W1037709911","https://openalex.org/W1552694876","https://openalex.org/W2063579271","https://openalex.org/W2891508361","https://openalex.org/W2351908579","https://openalex.org/W2748448327","https://openalex.org/W2066914524","https://openalex.org/W1544536563"],"abstract_inverted_index":{"Generating":[0],"realistic":[1],"lip":[2,32,88,102,122,155,161],"motion":[3,33,89,103,156,162],"from":[4,34],"audio":[5],"to":[6,25,79],"simulate":[7],"speech":[8,35],"production":[9],"is":[10],"critical":[11],"for":[12,30],"driving":[13],"natural":[14],"character":[15],"animation.":[16],"Previous":[17],"research":[18],"has":[19],"shown":[20],"that":[21,49,151,164],"traditional":[22],"metrics":[23,48],"used":[24],"optimize":[26],"and":[27,73,99,134,163,171],"assess":[28],"models":[29],"generating":[31],"are":[36,126,143],"not":[37],"a":[38,75],"good":[39],"indicator":[40],"of":[41,44,61,71,77,87,107,113,138],"subjective":[42,52],"opinion":[43,53],"animation":[45],"quality.":[46,62,108],"Devising":[47],"align":[50],"with":[51,128,145],"first":[54],"requires":[55],"understanding":[56],"what":[57],"impacts":[58,84],"human":[59,85,105,117],"perception":[60,86,106,118],"In":[63],"this":[64,165],"work,":[65],"we":[66,93],"focus":[67],"on":[68,116],"the":[69,111,136],"degree":[70],"articulation":[72,82,114],"run":[74],"series":[76],"experiments":[78],"study":[80,94],"how":[81,95],"strength":[83,115],"accompanying":[90],"speech.":[91],"Specifically,":[92],"increasing":[96],"under-articulated":[97,160],"(dampened)":[98],"over-articulated":[100,154],"(exaggerated)":[101],"affects":[104],"We":[109],"examine":[110],"impact":[112],"when":[119],"considering":[120],"only":[121],"motion,":[123],"where":[124,141],"viewers":[125,142,152],"presented":[127,144],"talking":[129],"faces":[130],"represented":[131],"by":[132],"landmarks,":[133],"in":[135],"context":[137],"embodied":[139],"characters,":[140],"photo-realistic":[146],"videos.":[147],"Our":[148],"results":[149],"show":[150],"prefer":[153],"consistently":[157],"more":[158],"than":[159],"preference":[166],"generalizes":[167],"across":[168],"different":[169],"speakers":[170],"embodiments.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
