{"id":"https://openalex.org/W2365880764","doi":"https://doi.org/10.1109/icassp.2016.7472029","title":"Decoding visemes: Improving machine lip-reading","display_name":"Decoding visemes: Improving machine lip-reading","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2365880764","doi":"https://doi.org/10.1109/icassp.2016.7472029","mag":"2365880764"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/A5031962033","display_name":"Helen L. Bear","orcid":"https://orcid.org/0000-0002-6051-536X"},"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":true,"raw_author_name":"Helen L. Bear","raw_affiliation_strings":["School of Computing Sciences, University of East Anglia, Norwich, United Kingdom"],"affiliations":[{"raw_affiliation_string":"School of Computing Sciences, University of East Anglia, Norwich, United Kingdom","institution_ids":["https://openalex.org/I1118541"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035826908","display_name":"Richard Harvey","orcid":"https://orcid.org/0000-0001-9925-8316"},"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":"Richard Harvey","raw_affiliation_strings":["School of Computing Sciences, University of East Anglia, Norwich, United Kingdom"],"affiliations":[{"raw_affiliation_string":"School of Computing Sciences, University of East Anglia, Norwich, United Kingdom","institution_ids":["https://openalex.org/I1118541"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031962033"],"corresponding_institution_ids":["https://openalex.org/I1118541"],"apc_list":null,"apc_paid":null,"fwci":5.8752,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.96799156,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2009","last_page":"2013"},"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":0.9902999997138977,"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":0.9890999794006348,"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/viseme","display_name":"Viseme","score":0.9692144393920898},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7928366661071777},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7161786556243896},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.6740913391113281},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6480324864387512},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.479672908782959},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39143821597099304},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36016350984573364},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2359461784362793},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09776473045349121},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08468341827392578},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.07274079322814941}],"concepts":[{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.9692144393920898},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7928366661071777},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7161786556243896},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.6740913391113281},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6480324864387512},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.479672908782959},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39143821597099304},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36016350984573364},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2359461784362793},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09776473045349121},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08468341827392578},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.07274079322814941},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2016.7472029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:roar.uel.ac.uk:5703","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400937","display_name":"ROAR (University of East London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I157227730","host_organization_name":"University of East London","host_organization_lineage":["https://openalex.org/I157227730"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Book Section"},{"id":"pmh:oai:repository.uel.ac.uk:850yz","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ICASSP.2016.7472029","pdf_url":null,"source":{"id":"https://openalex.org/S4306401301","display_name":"UEL Research Repository (University of East London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I157227730","host_organization_name":"University of East London","host_organization_lineage":["https://openalex.org/I157227730"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8500000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W82494927","https://openalex.org/W242871668","https://openalex.org/W943204654","https://openalex.org/W1976927254","https://openalex.org/W2071096833","https://openalex.org/W2078711706","https://openalex.org/W2078902741","https://openalex.org/W2082308025","https://openalex.org/W2101013379","https://openalex.org/W2109004156","https://openalex.org/W2113814270","https://openalex.org/W2140826107","https://openalex.org/W2142490914","https://openalex.org/W2151323546","https://openalex.org/W2152826865","https://openalex.org/W2155765376","https://openalex.org/W2168744723","https://openalex.org/W2306241824","https://openalex.org/W2397233148","https://openalex.org/W2963024054","https://openalex.org/W6603350892","https://openalex.org/W6675427651","https://openalex.org/W6681494444","https://openalex.org/W6712469390"],"related_works":["https://openalex.org/W1974357398","https://openalex.org/W2796042130","https://openalex.org/W2142490914","https://openalex.org/W4253235840","https://openalex.org/W2116497041","https://openalex.org/W2591964346","https://openalex.org/W131634123","https://openalex.org/W2757496505","https://openalex.org/W1560013842","https://openalex.org/W1530111162"],"abstract_inverted_index":{"To":[0],"undertake":[1],"machine":[2],"lip-reading,":[3],"we":[4,46,70],"try":[5],"to":[6],"recognise":[7],"speech":[8],"from":[9],"a":[10,48],"visual":[11],"signal.":[12],"Current":[13],"work":[14,45],"often":[15],"uses":[16,57],"viseme":[17,41],"classification":[18,72],"supported":[19],"by":[20],"language":[21],"models":[22],"with":[23],"varying":[24],"degrees":[25],"of":[26,52],"success.":[27],"A":[28],"few":[29],"recent":[30],"works":[31],"suggest":[32],"phoneme":[33,54],"classification,":[34],"in":[35,61],"the":[36,62],"right":[37],"circumstances,":[38],"can":[39],"outperform":[40],"classification.":[42],"In":[43],"this":[44],"present":[47],"novel":[49],"two-pass":[50],"method":[51],"training":[53,68],"classifiers":[55],"which":[56,74],"previously":[58],"trained":[59],"visemes":[60],"first":[63],"pass.":[64],"With":[65],"our":[66],"new":[67],"algorithm,":[69],"show":[71],"performance":[73],"significantly":[75],"improves":[76],"on":[77],"previous":[78],"lip-reading":[79],"results.":[80]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}