{"id":"https://openalex.org/W2020596545","doi":"https://doi.org/10.1109/icassp.2013.6638089","title":"Designing relevant features for visual speech recognition","display_name":"Designing relevant features for visual speech recognition","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2020596545","doi":"https://doi.org/10.1109/icassp.2013.6638089","mag":"2020596545"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6638089","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638089","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5013808024","display_name":"Eric Benhaim","orcid":null},"institutions":[{"id":"https://openalex.org/I4210146074","display_name":"Analyse, G\u00e9om\u00e9trie et Mod\u00e9lisation","ror":"https://ror.org/03qgt2624","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210141950","https://openalex.org/I4210142324","https://openalex.org/I4210146074"]},{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210105651","display_name":"Laboratoire Traitement du Signal et de l'Image","ror":"https://ror.org/01f1amm71","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I154526488","https://openalex.org/I4210105651","https://openalex.org/I4210105774","https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Eric Benhaim","raw_affiliation_strings":["TELECOM ParisTech, Paris, \u00c3\u017dle-de-France, FR","Image, Mod\u00e9lisation, Analyse, GEom\u00e9trie, Synth\u00e8se","D\u00e9partement Traitement du Signal et des Images"],"affiliations":[{"raw_affiliation_string":"TELECOM ParisTech, Paris, \u00c3\u017dle-de-France, FR","institution_ids":["https://openalex.org/I12356871"]},{"raw_affiliation_string":"Image, Mod\u00e9lisation, Analyse, GEom\u00e9trie, Synth\u00e8se","institution_ids":["https://openalex.org/I4210146074"]},{"raw_affiliation_string":"D\u00e9partement Traitement du Signal et des Images","institution_ids":["https://openalex.org/I4210105651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029896607","display_name":"Hichem Sahbi","orcid":"https://orcid.org/0000-0001-6813-9146"},"institutions":[{"id":"https://openalex.org/I4210105651","display_name":"Laboratoire Traitement du Signal et de l'Image","ror":"https://ror.org/01f1amm71","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I154526488","https://openalex.org/I4210105651","https://openalex.org/I4210105774","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I4210146074","display_name":"Analyse, G\u00e9om\u00e9trie et Mod\u00e9lisation","ror":"https://ror.org/03qgt2624","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210141950","https://openalex.org/I4210142324","https://openalex.org/I4210146074"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Hichem Sahbi","raw_affiliation_strings":["CNRS-LTCI, Telecom Paris Tech, Paris, France","D\u00e9partement Traitement du Signal et des Images","Image, Mod\u00e9lisation, Analyse, GEom\u00e9trie, Synth\u00e8se"],"affiliations":[{"raw_affiliation_string":"CNRS-LTCI, Telecom Paris Tech, Paris, France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I1294671590","https://openalex.org/I12356871"]},{"raw_affiliation_string":"D\u00e9partement Traitement du Signal et des Images","institution_ids":["https://openalex.org/I4210105651"]},{"raw_affiliation_string":"Image, Mod\u00e9lisation, Analyse, GEom\u00e9trie, Synth\u00e8se","institution_ids":["https://openalex.org/I4210146074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056593902","display_name":"Guillaume Vitte","orcid":null},"institutions":[{"id":"https://openalex.org/I4210132757","display_name":"Parrot (France)","ror":"https://ror.org/03wadyw29","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210132757"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Guillaume Vitte","raw_affiliation_strings":["Parrot S.A, Paris, France","Parrot S.A., Paris, France"],"affiliations":[{"raw_affiliation_string":"Parrot S.A, Paris, France","institution_ids":["https://openalex.org/I4210132757"]},{"raw_affiliation_string":"Parrot S.A., Paris, France","institution_ids":["https://openalex.org/I4210132757"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5013808024"],"corresponding_institution_ids":["https://openalex.org/I12356871","https://openalex.org/I4210105651","https://openalex.org/I4210146074"],"apc_list":null,"apc_paid":null,"fwci":1.2768,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.79419,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"56","issue":null,"first_page":"2420","last_page":"2424"},"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9961000084877014,"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/T11448","display_name":"Face recognition and analysis","score":0.9958000183105469,"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":0.8352991938591003},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6380273103713989},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5882143378257751},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5539999604225159},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5470044612884521},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5226414203643799},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.498781681060791},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.48784804344177246},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.48241767287254333},{"id":"https://openalex.org/keywords/string-kernel","display_name":"String kernel","score":0.4394875168800354},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4257884919643402},{"id":"https://openalex.org/keywords/kernel-method","display_name":"Kernel method","score":0.4072413146495819},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39903682470321655},{"id":"https://openalex.org/keywords/radial-basis-function-kernel","display_name":"Radial basis function kernel","score":0.24620577692985535},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.15873822569847107}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8352991938591003},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6380273103713989},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5882143378257751},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5539999604225159},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5470044612884521},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5226414203643799},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.498781681060791},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.48784804344177246},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.48241767287254333},{"id":"https://openalex.org/C55851704","wikidata":"https://www.wikidata.org/wiki/Q7623983","display_name":"String kernel","level":5,"score":0.4394875168800354},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4257884919643402},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.4072413146495819},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39903682470321655},{"id":"https://openalex.org/C75866337","wikidata":"https://www.wikidata.org/wiki/Q7280263","display_name":"Radial basis function kernel","level":4,"score":0.24620577692985535},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.15873822569847107},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2013.6638089","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638089","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W142803501","https://openalex.org/W177229737","https://openalex.org/W1595717062","https://openalex.org/W1908325895","https://openalex.org/W1908566903","https://openalex.org/W1976524151","https://openalex.org/W2015394094","https://openalex.org/W2082308025","https://openalex.org/W2098923380","https://openalex.org/W2106503792","https://openalex.org/W2113814270","https://openalex.org/W2116217121","https://openalex.org/W2124225821","https://openalex.org/W2124397839","https://openalex.org/W2136155248","https://openalex.org/W2142075667","https://openalex.org/W2152826865","https://openalex.org/W2158702718","https://openalex.org/W2161969291","https://openalex.org/W2170960297","https://openalex.org/W2612434330","https://openalex.org/W3097096317","https://openalex.org/W3143803406","https://openalex.org/W4285719527","https://openalex.org/W6605737493","https://openalex.org/W6635755983","https://openalex.org/W6639968709","https://openalex.org/W6639996154","https://openalex.org/W6678167290"],"related_works":["https://openalex.org/W1558903433","https://openalex.org/W4291669689","https://openalex.org/W2079825755","https://openalex.org/W2066281563","https://openalex.org/W2157788863","https://openalex.org/W2095626363","https://openalex.org/W2089892314","https://openalex.org/W1983263273","https://openalex.org/W4386075310","https://openalex.org/W2295320501"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,30,49],"analysis":[2],"is":[3,17],"currently":[4],"evolving":[5],"towards":[6],"hybrid":[7],"systems":[8,32],"that":[9,78,104,122],"combine":[10],"both":[11],"visual":[12,48,88,106],"and":[13,25,56,93,110],"acoustic":[14],"information.":[15],"This":[16],"due":[18],"to":[19],"limitations":[20],"of":[21,63,70,87],"existing":[22],"acoustic-based":[23],"approaches":[24],"the":[26,68,80,85,123],"need":[27],"for":[28],"robust":[29],"recognition":[31,50],"working":[33],"under":[34],"extremely":[35],"challenging":[36],"conditions":[37],"including":[38],"noisy":[39],"environments.":[40],"We":[41],"introduce":[42],"in":[43,90],"this":[44,64],"paper":[45],"a":[46,71,95,117],"novel":[47],"approach,":[51],"based":[52,74,99],"on":[53,75,100,116],"string":[54,76],"kernels":[55],"support":[57],"vector":[58],"machines.":[59],"The":[60],"main":[61],"contributions":[62],"work":[65],"include":[66],"(i)":[67],"design":[69],"similarity":[72],"function,":[73],"kernels,":[77],"models":[79],"dynamics":[81],"as":[82,84],"well":[83],"appearance":[86],"features":[89],"talking":[91],"faces":[92],"(ii)":[94],"kernel":[96,102],"combination":[97],"procedure":[98],"multiple":[101],"learning,":[103],"makes":[105],"feature":[107],"selection":[108],"effective":[109],"also":[111],"more":[112],"tractable.":[113],"Experiments":[114],"conducted,":[115],"standard":[118],"digit":[119],"database,":[120],"show":[121],"proposed":[124],"algorithm":[125],"outperforms":[126],"current":[127],"state-of-the-art":[128],"methods.":[129]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}