{"id":"https://openalex.org/W2043257208","doi":"https://doi.org/10.1109/icassp.2010.5495071","title":"Speaker independent visual-only language identification","display_name":"Speaker independent visual-only language identification","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2043257208","doi":"https://doi.org/10.1109/icassp.2010.5495071","mag":"2043257208"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495071","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495071","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing Sciences, University of East Anglia, Norwich, UK","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing Sciences, University of East Anglia, Norwich, UK","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":1.2805,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.78787879,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5026","last_page":"5029"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9968000054359436,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9833999872207642,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8196513652801514},{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.8008275628089905},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7908041477203369},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6463242173194885},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6424655318260193},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.5188361406326294},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4805215299129486},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4594936668872833},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.45905956625938416},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43590247631073},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.4101092219352722},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.22362765669822693},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.08235761523246765},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.057025134563446045}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8196513652801514},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.8008275628089905},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7908041477203369},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6463242173194885},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6424655318260193},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.5188361406326294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4805215299129486},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4594936668872833},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.45905956625938416},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43590247631073},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.4101092219352722},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.22362765669822693},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.08235761523246765},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.057025134563446045},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2010.5495071","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495071","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:ueaeprints.uea.ac.uk:26045","is_oa":false,"landing_page_url":"https://ueaeprints.uea.ac.uk/id/eprint/26045/","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":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"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/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W5542484","https://openalex.org/W14569549","https://openalex.org/W139257441","https://openalex.org/W1492424399","https://openalex.org/W1531976713","https://openalex.org/W1578725541","https://openalex.org/W2071096833","https://openalex.org/W2096391593","https://openalex.org/W2163228070","https://openalex.org/W2172287020","https://openalex.org/W6605722544","https://openalex.org/W6631751486","https://openalex.org/W6634609231"],"related_works":["https://openalex.org/W4234190324","https://openalex.org/W157723669","https://openalex.org/W4396668120","https://openalex.org/W2776235554","https://openalex.org/W2126085626","https://openalex.org/W2284708545","https://openalex.org/W36105149","https://openalex.org/W2545131480","https://openalex.org/W1973693762","https://openalex.org/W208363076"],"abstract_inverted_index":{"We":[0],"describe":[1],"experiments":[2],"in":[3,8,36,57,69],"visual-only":[4],"language":[5,21,42,59],"identification":[6],"(VLID),":[7],"which":[9],"only":[10],"lip":[11],"shape,":[12],"appearance":[13],"and":[14],"motion":[15],"are":[16],"used":[17],"to":[18,65],"determine":[19],"the":[20,41,63,111],"of":[22,92,110,113],"a":[23,45],"spoken":[24,43],"utterance.":[25],"In":[26],"previous":[27],"work,":[28],"we":[29,61],"had":[30],"shown":[31],"that":[32,53,75,99],"this":[33],"is":[34],"possible":[35],"speaker-dependent":[37],"mode,":[38],"i.e.":[39],"identifying":[40],"by":[44,49],"multi-lingual":[46],"speaker.":[47],"Here,":[48],"appropriately":[50],"modifying":[51],"techniques":[52],"have":[54],"been":[55],"successful":[56],"audio":[58],"identification,":[60],"extend":[62],"work":[64],"discriminating":[66],"two":[67],"languages":[68],"speaker-independent":[70],"mode.":[71],"Our":[72],"results":[73],"indicate":[74],"even":[76],"with":[77,106],"viseme":[78,95,107],"accuracy":[79,94,102],"as":[80,82],"low":[81],"about":[83],"34%,":[84],"reasonable":[85],"discrimination":[86],"can":[87],"be":[88,104],"obtained.":[89],"A":[90],"simulation":[91],"degraded":[93],"recognition":[96,108],"performance":[97],"indicates":[98],"high":[100],"VLID":[101],"should":[103],"achievable":[105],"errors":[109],"order":[112],"50%.":[114]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}