{"id":"https://openalex.org/W2147016966","doi":"https://doi.org/10.1109/icassp.2012.6288364","title":"Hybrid phoneme based clustering approach for audio driven facial animation","display_name":"Hybrid phoneme based clustering approach for audio driven facial animation","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2147016966","doi":"https://doi.org/10.1109/icassp.2012.6288364","mag":"2147016966"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288364","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288364","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 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/A5068617749","display_name":"Benjamin Havell","orcid":null},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Benjamin Havell","raw_affiliation_strings":["School of Computer Science and Informatics, School of Engineering, Cardiff University, UK","School of Computer Science and Informatics, Cardiff University, UK#TAB#"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Informatics, School of Engineering, Cardiff University, UK","institution_ids":["https://openalex.org/I79510175"]},{"raw_affiliation_string":"School of Computer Science and Informatics, Cardiff University, UK#TAB#","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068129380","display_name":"Paul L. Rosin","orcid":"https://orcid.org/0000-0002-4965-3884"},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Paul L. Rosin","raw_affiliation_strings":["School of Computer Science and Informatics, Cardiff University, UK","School of Computer Science and Informatics, Cardiff University, UK#TAB#"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Informatics, Cardiff University, UK","institution_ids":["https://openalex.org/I79510175"]},{"raw_affiliation_string":"School of Computer Science and Informatics, Cardiff University, UK#TAB#","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004587843","display_name":"Saeid Sanei","orcid":"https://orcid.org/0000-0002-1446-5744"},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Saeid Sanei","raw_affiliation_strings":["School of Engineering, Cardiff University, UK","[School of Engineering, Cardiff University, UK]"],"affiliations":[{"raw_affiliation_string":"School of Engineering, Cardiff University, UK","institution_ids":["https://openalex.org/I79510175"]},{"raw_affiliation_string":"[School of Engineering, Cardiff University, UK]","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047142160","display_name":"Andrew J. Aubrey","orcid":null},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew Aubrey","raw_affiliation_strings":["School of Computer Science and Informatics, Cardiff University, UK","School of Computer Science and Informatics, Cardiff University, UK#TAB#"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Informatics, Cardiff University, UK","institution_ids":["https://openalex.org/I79510175"]},{"raw_affiliation_string":"School of Computer Science and Informatics, Cardiff University, UK#TAB#","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031677311","display_name":"David Marshall","orcid":"https://orcid.org/0000-0003-2789-1395"},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"David Marshall","raw_affiliation_strings":["School of Computer Science and Informatics, Cardiff University, UK","School of Computer Science and Informatics, Cardiff University, UK#TAB#"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Informatics, Cardiff University, UK","institution_ids":["https://openalex.org/I79510175"]},{"raw_affiliation_string":"School of Computer Science and Informatics, Cardiff University, UK#TAB#","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010194843","display_name":"Yulia Hicks","orcid":"https://orcid.org/0000-0002-7179-4587"},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yulia Hicks","raw_affiliation_strings":["School of Engineering, Cardiff University, UK","[School of Engineering, Cardiff University, UK]"],"affiliations":[{"raw_affiliation_string":"School of Engineering, Cardiff University, UK","institution_ids":["https://openalex.org/I79510175"]},{"raw_affiliation_string":"[School of Engineering, Cardiff University, UK]","institution_ids":["https://openalex.org/I79510175"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5068617749"],"corresponding_institution_ids":["https://openalex.org/I79510175"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.17648461,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"2261","last_page":"2264"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9991999864578247,"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/T10057","display_name":"Face and Expression Recognition","score":0.9739999771118164,"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":0.8348774313926697},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7754708528518677},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7150489091873169},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6345015168190002},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.6212023496627808},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5809511542320251},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.573824405670166},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5469451546669006},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4552622437477112},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4177539050579071},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.38593795895576477},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.24927911162376404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8348774313926697},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7754708528518677},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7150489091873169},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6345015168190002},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.6212023496627808},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5809511542320251},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.573824405670166},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5469451546669006},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4552622437477112},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4177539050579071},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.38593795895576477},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.24927911162376404},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp.2012.6288364","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288364","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.309.1351","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.309.1351","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://users.cs.cf.ac.uk/Paul.Rosin/resources/papers/phoneme-ICASSP.pdf","raw_type":"text"},{"id":"pmh:oai:alma.44SUR_INST:11140112230002346","is_oa":false,"landing_page_url":"https://openresearch.surrey.ac.uk/esploro/outputs/journalArticle/Hybrid-phoneme-based-clustering-approach-for/99516819502346","pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:epubs.surrey.ac.uk:742474","is_oa":false,"landing_page_url":"http://epubs.surrey.ac.uk/742474/1/4.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400680","display_name":"Surrey Research Insight Open Access (The University of Surrey)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28290843","host_organization_name":"University of Surrey","host_organization_lineage":["https://openalex.org/I28290843"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:https://orca.cardiff.ac.uk:38779","is_oa":false,"landing_page_url":"https://orca.cardiff.ac.uk/id/eprint/38779/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401195","display_name":"ORCA Online Research @Cardiff (Cardiff University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79510175","host_organization_name":"Cardiff University","host_organization_lineage":["https://openalex.org/I79510175"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1533179050","https://openalex.org/W1539720309","https://openalex.org/W1552213476","https://openalex.org/W1608356169","https://openalex.org/W1618101233","https://openalex.org/W2026185542","https://openalex.org/W2029835507","https://openalex.org/W2115652602","https://openalex.org/W2125231580","https://openalex.org/W2125838338","https://openalex.org/W2135624911","https://openalex.org/W2143132120","https://openalex.org/W2152826865","https://openalex.org/W2172803778","https://openalex.org/W2293491238","https://openalex.org/W2294798173","https://openalex.org/W2295661697","https://openalex.org/W2949823946","https://openalex.org/W4300944962","https://openalex.org/W6632327317","https://openalex.org/W6636203038","https://openalex.org/W6680241228","https://openalex.org/W6681253763","https://openalex.org/W6682634897","https://openalex.org/W6763876014"],"related_works":["https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2160650576","https://openalex.org/W1544039745","https://openalex.org/W2121378366","https://openalex.org/W2053298083","https://openalex.org/W615219140","https://openalex.org/W2999276620","https://openalex.org/W4232411666","https://openalex.org/W1978243811"],"abstract_inverted_index":{"We":[0,95,130],"consider":[1],"the":[2,50,55,68,74,77,82,89,92,107,110,168],"problem":[3],"of":[4,70,76,79,91,100,109,141,181],"producing":[5,175],"accurate":[6,158],"facial":[7,41,196],"animation":[8,197],"corresponding":[9],"to":[10,27,38,48,105,125,134],"a":[11,29,98,115,138,148,164,176],"given":[12],"input":[13,56],"speech":[14],"signal.":[15],"A":[16],"popular":[17],"technique":[18,72],"previously":[19],"used":[20],"for":[21,194],"Audio":[22],"Driven":[23],"Facial":[24],"Animation":[25],"is":[26,171,187],"build":[28],"joint":[30],"audio-visual":[31],"model":[32,126,177],"using":[33,120,137],"Active":[34],"Appearance":[35],"Models":[36,46,123],"(AAMs)":[37],"represent":[39],"possible":[40],"variations":[42],"and":[43,73,113,151,200],"Hidden":[44],"Markov":[45],"(HMMs)":[47],"select":[49],"correct":[51],"appearance":[52],"based":[53,118],"on":[54,119],"audio.":[57],"However":[58],"there":[59],"are":[60],"several":[61,135],"questions":[62],"that":[63,153],"remained":[64],"unanswered.":[65],"In":[66,160],"particular":[67],"choice":[69,75],"clustering":[71,101],"number":[78],"clusters":[80],"in":[81,103],"HMM":[83,111],"may":[84],"have":[85,96],"significant":[86],"influence":[87],"over":[88],"quality":[90,108],"produced":[93],"videos.":[94],"investigated":[97],"range":[99],"techniques":[102],"order":[104],"improve":[106],"produced,":[112],"proposed":[114],"new":[116],"structure":[117],"Gaussian":[121],"Mixture":[122],"(GMMs)":[124],"each":[127],"phoneme":[128],"separately.":[129],"compared":[131],"our":[132,154,192],"approach":[133,155,166,193],"alternatives":[136],"public":[139],"dataset":[140],"300":[142],"phonetically":[143,172],"labeled":[144,173],"sentences":[145],"spoken":[146],"by":[147],"single":[149],"person":[150],"found":[152],"produces":[156],"more":[157],"animation.":[159],"addition,":[161],"we":[162],"use":[163],"hybrid":[165],"where":[167],"training":[169],"data":[170,186],"thus":[174,190],"with":[178],"better":[179],"separation":[180],"phonemes,":[182],"but":[183],"test":[184],"audio":[185],"not":[188],"labeled,":[189],"making":[191],"generating":[195],"less":[198],"laborious":[199],"fully":[201],"automatic.":[202]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
