{"id":"https://openalex.org/W2115119650","doi":"https://doi.org/10.1109/tasl.2008.2008740","title":"Face Active Appearance Modeling and Speech Acoustic Information to Recover Articulation","display_name":"Face Active Appearance Modeling and Speech Acoustic Information to Recover Articulation","publication_year":2009,"publication_date":"2009-02-13","ids":{"openalex":"https://openalex.org/W2115119650","doi":"https://doi.org/10.1109/tasl.2008.2008740","mag":"2115119650"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2008.2008740","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2008.2008740","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://doi.org/10.1109/TASL.2008.2008740","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003869083","display_name":"Athanasios Katsamanis","orcid":"https://orcid.org/0000-0002-2642-2354"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]},{"id":"https://openalex.org/I200777214","display_name":"National and Kapodistrian University of Athens","ror":"https://ror.org/04gnjpq42","country_code":"GR","type":"education","lineage":["https://openalex.org/I200777214"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"A. Katsamanis","raw_affiliation_strings":["School of Electrical and Computer Engineering, National and Technical University of Athens, Athens, Greece","Sch. of Electr. & Comput. Eng. Nat., Tech. Univ. of Athens, Athens"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, National and Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]},{"raw_affiliation_string":"Sch. of Electr. & Comput. Eng. Nat., Tech. Univ. of Athens, Athens","institution_ids":["https://openalex.org/I200777214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034294456","display_name":"George Papandreou","orcid":"https://orcid.org/0000-0002-1468-2976"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]},{"id":"https://openalex.org/I200777214","display_name":"National and Kapodistrian University of Athens","ror":"https://ror.org/04gnjpq42","country_code":"GR","type":"education","lineage":["https://openalex.org/I200777214"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"G. Papandreou","raw_affiliation_strings":["School of Electrical and Computer Engineering, National and Technical University of Athens, Athens, Greece","Sch. of Electr. & Comput. Eng. Nat., Tech. Univ. of Athens, Athens"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, National and Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]},{"raw_affiliation_string":"Sch. of Electr. & Comput. Eng. Nat., Tech. Univ. of Athens, Athens","institution_ids":["https://openalex.org/I200777214"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079243420","display_name":"Petros Maragos","orcid":"https://orcid.org/0000-0003-0534-2707"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]},{"id":"https://openalex.org/I200777214","display_name":"National and Kapodistrian University of Athens","ror":"https://ror.org/04gnjpq42","country_code":"GR","type":"education","lineage":["https://openalex.org/I200777214"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"P. Maragos","raw_affiliation_strings":["School of Electrical and Computer Engineering, National and Technical University of Athens, Athens, Greece","Sch. of Electr. & Comput. Eng. Nat., Tech. Univ. of Athens, Athens"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, National and Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]},{"raw_affiliation_string":"Sch. of Electr. & Comput. Eng. Nat., Tech. Univ. of Athens, Athens","institution_ids":["https://openalex.org/I200777214"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.4032,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.97847147,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"17","issue":"3","first_page":"411","last_page":"422"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9861999750137329,"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/computer-science","display_name":"Computer science","score":0.8035564422607422},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7232405543327332},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5730931162834167},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.5511632561683655},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.4446728825569153},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4404889941215515},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.43313246965408325},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3683309257030487},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.35457122325897217}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8035564422607422},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7232405543327332},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5730931162834167},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.5511632561683655},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.4446728825569153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4404889941215515},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.43313246965408325},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3683309257030487},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.35457122325897217}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tasl.2008.2008740","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2008.2008740","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.414.7006","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.414.7006","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cvsp.cs.ntua.gr/publications/jpubl+bchap/KatsamanisPapandreouMaragos_AudiovisualSpeechInversion_ieee-j-aslp09.pdf","raw_type":"text"},{"id":"pmh:oai:dspace.lib.ntua.gr:123456789/19605","is_oa":true,"landing_page_url":"http://doi.org/10.1109/TASL.2008.2008740","pdf_url":null,"source":{"id":"https://openalex.org/S4377196837","display_name":"DSpace - NTUA (National Technical University of Athens)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I174458059","host_organization_name":"National Technical University of Athens","host_organization_lineage":["https://openalex.org/I174458059"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Audio, Speech and Language Processing","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:dspace.lib.ntua.gr:123456789/19605","is_oa":true,"landing_page_url":"http://doi.org/10.1109/TASL.2008.2008740","pdf_url":null,"source":{"id":"https://openalex.org/S4377196837","display_name":"DSpace - NTUA (National Technical University of Athens)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I174458059","host_organization_name":"National Technical University of Athens","host_organization_lineage":["https://openalex.org/I174458059"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Audio, Speech and Language Processing","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4300000071525574,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320332","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90"},{"id":"https://openalex.org/F4320330142","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W70924070","https://openalex.org/W75017197","https://openalex.org/W157899740","https://openalex.org/W1494195105","https://openalex.org/W1506806321","https://openalex.org/W1510680587","https://openalex.org/W1519698338","https://openalex.org/W1560013842","https://openalex.org/W1566824264","https://openalex.org/W1576996184","https://openalex.org/W1608978487","https://openalex.org/W1663973292","https://openalex.org/W1982854652","https://openalex.org/W1990394889","https://openalex.org/W2015394094","https://openalex.org/W2023689787","https://openalex.org/W2034829178","https://openalex.org/W2038381734","https://openalex.org/W2042608483","https://openalex.org/W2047618352","https://openalex.org/W2052382192","https://openalex.org/W2069618035","https://openalex.org/W2083792893","https://openalex.org/W2095731437","https://openalex.org/W2096391593","https://openalex.org/W2114336453","https://openalex.org/W2117631864","https://openalex.org/W2120535071","https://openalex.org/W2121486117","https://openalex.org/W2127211243","https://openalex.org/W2128173845","https://openalex.org/W2130618758","https://openalex.org/W2140199909","https://openalex.org/W2140427427","https://openalex.org/W2143451044","https://openalex.org/W2143493821","https://openalex.org/W2149329249","https://openalex.org/W2150709375","https://openalex.org/W2152826865","https://openalex.org/W2155765376","https://openalex.org/W2164598857","https://openalex.org/W2603829373","https://openalex.org/W4212863985","https://openalex.org/W4239472098","https://openalex.org/W6606471501","https://openalex.org/W6634084634","https://openalex.org/W6634430985","https://openalex.org/W6674534281","https://openalex.org/W6677895275","https://openalex.org/W6679553610","https://openalex.org/W6736176328"],"related_works":["https://openalex.org/W3162157266","https://openalex.org/W2162084437","https://openalex.org/W2102353451","https://openalex.org/W2082000062","https://openalex.org/W4234201046","https://openalex.org/W2058733683","https://openalex.org/W2150243332","https://openalex.org/W2804836678","https://openalex.org/W953964455","https://openalex.org/W2010642486"],"abstract_inverted_index":{"We":[0,182],"are":[1,26],"interested":[2],"in":[3,147,177,200,212],"recovering":[4],"aspects":[5],"of":[6,45,168,175],"vocal":[7],"tract's":[8],"geometry":[9],"and":[10,117,133,139,188,195,209],"dynamics":[11],"from":[12,60],"speech,":[13],"a":[14,81,213],"problem":[15],"referred":[16],"to":[17,165,224],"as":[18,153],"speech":[19,23,32,179],"inversion.":[20],"Traditional":[21],"audio-only":[22,47],"inversion":[24,48,53],"techniques":[25],"inherently":[27],"ill-posed":[28],"since":[29],"the":[30,43,46,61,102,115,144,169,178,186],"same":[31],"acoustics":[33],"can":[34],"be":[35],"produced":[36],"by":[37,70,80,172],"multiple":[38],"articulatory":[39,87],"configurations.":[40],"To":[41],"alleviate":[42],"ill-posedness":[44],"process,":[49],"we":[50,106,127],"propose":[51],"an":[52,71],"scheme":[54,219],"which":[55,85,111,191],"also":[56],"exploits":[57],"visual":[58,118,140,210],"information":[59],"speaker's":[62],"face.":[63],"The":[64,202],"complex":[65],"audiovisual-to-articulatory":[66],"mapping":[67,93],"is":[68,78,94],"approximated":[69],"adaptive":[72],"piecewise":[73],"linear":[74,92],"model.":[75],"Model":[76],"switching":[77],"governed":[79],"Markovian":[82],"discrete":[83],"process":[84],"captures":[86],"dynamic":[88],"information.":[89],"Each":[90],"constituent":[91],"effectively":[95],"estimated":[96],"via":[97],"canonical":[98],"correlation":[99],"analysis.":[100],"In":[101],"described":[103],"multimodal":[104],"context,":[105],"investigate":[107],"alternative":[108],"fusion":[109],"schemes":[110],"allow":[112],"interaction":[113],"between":[114],"audio":[116,150,208,226],"modalities":[119,211],"at":[120],"various":[121],"synchronization":[122],"levels.":[123],"For":[124],"facial":[125],"analysis,":[126],"employ":[128],"active":[129],"appearance":[130],"models":[131],"(AAMs)":[132],"demonstrate":[134],"fully":[135],"automatic":[136],"face":[137],"tracking":[138],"feature":[141],"extraction.":[142],"Using":[143],"AAM":[145],"features":[146,151],"conjunction":[148],"with":[149],"such":[152],"Mel":[154],"frequency":[155],"cepstral":[156],"coefficients":[157],"(MFCCs)":[158],"or":[159,227],"line":[160],"spectral":[161],"frequencies":[162],"(LSFs)":[163],"leads":[164],"effective":[166],"estimation":[167],"trajectories":[170],"followed":[171],"certain":[173],"points":[174],"interest":[176],"production":[180],"system.":[181],"report":[183],"experiments":[184],"on":[185],"QSMT":[187],"MOCHA":[189],"databases":[190],"contain":[192],"audio,":[193],"video,":[194],"electromagnetic":[196],"articulography":[197],"data":[198],"recorded":[199],"parallel.":[201],"results":[203],"show":[204],"that":[205],"exploiting":[206],"both":[207],"multistream":[214],"hidden":[215],"Markov":[216],"model":[217],"based":[218],"clearly":[220],"improves":[221],"performance":[222],"relative":[223],"either":[225],"visual-only":[228],"estimation.":[229]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}