{"id":"https://openalex.org/W2094800907","doi":"https://doi.org/10.1109/tasl.2012.2191956","title":"Language Identification Using Visual Features","display_name":"Language Identification Using Visual Features","publication_year":2012,"publication_date":"2012-04-11","ids":{"openalex":"https://openalex.org/W2094800907","doi":"https://doi.org/10.1109/tasl.2012.2191956","mag":"2094800907"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2012.2191956","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2191956","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002367391","display_name":"Jacob Newman","orcid":"https://orcid.org/0000-0002-9149-6181"},"institutions":[{"id":"https://openalex.org/I1118541","display_name":"University of East Anglia","ror":"https://ror.org/026k5mg93","country_code":"GB","type":"education","lineage":["https://openalex.org/I1118541"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jacob L. Newman","raw_affiliation_strings":["School of Computing Sciences, University of East Anglia, Norwich, UK","School of Computer Science, University of East Anglia, Norwich, UK#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing Sciences, University of East Anglia, Norwich, UK","institution_ids":["https://openalex.org/I1118541"]},{"raw_affiliation_string":"School of Computer Science, University of East Anglia, Norwich, UK#TAB#","institution_ids":["https://openalex.org/I1118541"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101798651","display_name":"Stephen Cox","orcid":"https://orcid.org/0000-0002-4443-1000"},"institutions":[{"id":"https://openalex.org/I1118541","display_name":"University of East Anglia","ror":"https://ror.org/026k5mg93","country_code":"GB","type":"education","lineage":["https://openalex.org/I1118541"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stephen J. Cox","raw_affiliation_strings":["School of Computing Sciences, University of East Anglia, Norwich, UK","School of Computer Science, University of East Anglia, Norwich, UK#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing Sciences, University of East Anglia, Norwich, UK","institution_ids":["https://openalex.org/I1118541"]},{"raw_affiliation_string":"School of Computer Science, University of East Anglia, Norwich, UK#TAB#","institution_ids":["https://openalex.org/I1118541"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1118541"],"apc_list":null,"apc_paid":null,"fwci":1.7058,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.87670172,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"20","issue":"7","first_page":"1936","last_page":"1947"},"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/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"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":0.9958000183105469,"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":0.8299355506896973},{"id":"https://openalex.org/keywords/phonotactics","display_name":"Phonotactics","score":0.6940501928329468},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.661197304725647},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5900130271911621},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.47800102829933167},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4584678113460541},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.4566437900066376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4564511775970459},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.455596923828125},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4416114091873169},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.42196255922317505},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.41921624541282654},{"id":"https://openalex.org/keywords/phonology","display_name":"Phonology","score":0.31104376912117004},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.28274691104888916},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1777697503566742},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.08988025784492493}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8299355506896973},{"id":"https://openalex.org/C4768521","wikidata":"https://www.wikidata.org/wiki/Q512366","display_name":"Phonotactics","level":3,"score":0.6940501928329468},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.661197304725647},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5900130271911621},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.47800102829933167},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4584678113460541},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.4566437900066376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4564511775970459},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.455596923828125},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4416114091873169},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.42196255922317505},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.41921624541282654},{"id":"https://openalex.org/C148934300","wikidata":"https://www.wikidata.org/wiki/Q40998","display_name":"Phonology","level":2,"score":0.31104376912117004},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28274691104888916},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1777697503566742},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.08988025784492493},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tasl.2012.2191956","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2191956","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:ueaeprints.uea.ac.uk:42159","is_oa":false,"landing_page_url":"https://ueaeprints.uea.ac.uk/id/eprint/42159/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400384","display_name":"UEA Digital Repository (University of East Anglia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1118541","host_organization_name":"University of East Anglia","host_organization_lineage":["https://openalex.org/I1118541"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G3064872541","display_name":null,"funder_award_id":"EP/E028047/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320326","display_name":"University of Reading","ror":"https://ror.org/05v62cm79"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W5542484","https://openalex.org/W82494927","https://openalex.org/W160552598","https://openalex.org/W1531976713","https://openalex.org/W1565194362","https://openalex.org/W1577371984","https://openalex.org/W1578725541","https://openalex.org/W1588084597","https://openalex.org/W1908325895","https://openalex.org/W1971273973","https://openalex.org/W1983072039","https://openalex.org/W2015143272","https://openalex.org/W2018506469","https://openalex.org/W2021279213","https://openalex.org/W2042025748","https://openalex.org/W2043257208","https://openalex.org/W2044194330","https://openalex.org/W2047432705","https://openalex.org/W2048196756","https://openalex.org/W2071096833","https://openalex.org/W2082308025","https://openalex.org/W2094342469","https://openalex.org/W2094800907","https://openalex.org/W2096391593","https://openalex.org/W2106284094","https://openalex.org/W2112348857","https://openalex.org/W2113814270","https://openalex.org/W2125168896","https://openalex.org/W2127015832","https://openalex.org/W2129571380","https://openalex.org/W2146194791","https://openalex.org/W2147986626","https://openalex.org/W2152826865","https://openalex.org/W2157190406","https://openalex.org/W2164770604","https://openalex.org/W2170533888","https://openalex.org/W2171012658","https://openalex.org/W2172287020","https://openalex.org/W3149793578","https://openalex.org/W4298266977","https://openalex.org/W4321429290","https://openalex.org/W6603350892","https://openalex.org/W6606522495","https://openalex.org/W6631751486","https://openalex.org/W6634609231","https://openalex.org/W6639968709","https://openalex.org/W6684959007"],"related_works":["https://openalex.org/W2006971780","https://openalex.org/W2347141333","https://openalex.org/W2294084151","https://openalex.org/W2134815611","https://openalex.org/W2403450742","https://openalex.org/W2102951823","https://openalex.org/W3153972594","https://openalex.org/W178568469","https://openalex.org/W2123872165","https://openalex.org/W4386302218"],"abstract_inverted_index":{"Automatic":[0],"visual":[1,14,82,141,155,187],"language":[2,25,38,83,95],"identification":[3,39,84],"(VLID)":[4],"is":[5,41,50,60,66,106,135],"the":[6,13,19,24,29,70,124,151,160],"technology":[7],"of":[8,18,31,73,148,154,162,169,186],"using":[9,182],"information":[10],"derived":[11],"from":[12],"appearance":[15],"and":[16,97,120,176,181],"movement":[17],"speech":[20,156],"articulators":[21],"to":[22,99,126,131,138],"identify":[23],"being":[26],"spoken,":[27],"without":[28],"use":[30],"any":[32],"audio":[33,48,58,90,145],"information.":[34],"This":[35,76],"technique":[36,125],"for":[37,81],"(LID)":[40],"useful":[42],"in":[43,45,63,69,108,172],"situations":[44],"which":[46,93],"conventional":[47],"processing":[49],"ineffective":[51],"(very":[52],"noisy":[53],"environments),":[54],"or":[55,144],"impossible":[56],"(no":[57],"signal":[59],"available).":[61],"Research":[62],"this":[64],"field":[65,72],"also":[67],"beneficial":[68],"related":[71],"automatic":[74],"lip-reading.":[75],"paper":[77],"introduces":[78],"several":[79],"methods":[80],"(VLID).":[85],"They":[86],"are":[87],"based":[88],"upon":[89],"LID":[91],"techniques,":[92],"exploit":[94],"phonology":[96],"phonotactics":[98],"discriminate":[100],"languages.":[101],"We":[102],"show":[103],"that":[104,133],"VLID":[105],"possible":[107],"a":[109],"speaker-dependent":[110],"mode":[111],"by":[112,117],"discriminating":[113,173],"different":[114],"languages":[115],"spoken":[116],"an":[118,167],"individual,":[119],"we":[121,164],"then":[122],"extend":[123],"speaker-independent":[127],"operation,":[128],"taking":[129],"pains":[130],"ensure":[132],"discrimination":[134],"not":[136],"due":[137],"artifacts,":[139],"either":[140],"(e.g.,":[142,146],"skin-tone)":[143],"rate":[147],"speaking).":[149],"Although":[150],"low":[152],"accuracy":[153],"recognition":[157],"currently":[158],"limits":[159],"performance":[161],"VLID,":[163],"can":[165],"obtain":[166],"error-rate":[168],"<;":[170],"10%":[171],"between":[174],"Arabic":[175],"English":[177],"on":[178],"19":[179],"speakers":[180],"about":[183],"30":[184],"s":[185],"speech.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
