{"id":"https://openalex.org/W2398406965","doi":"https://doi.org/10.1109/icassp.2016.7472172","title":"Improved speaker independent lip reading using speaker adaptive training and deep neural networks","display_name":"Improved speaker independent lip reading using speaker adaptive training and deep neural networks","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2398406965","doi":"https://doi.org/10.1109/icassp.2016.7472172","mag":"2398406965"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472172","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/A5037461866","display_name":"Ibrahim Almajai","orcid":null},"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":"Ibrahim Almajai","raw_affiliation_strings":["School of Computing Sciences, University of East Anglia, Norwich"],"affiliations":[{"raw_affiliation_string":"School of Computing Sciences, University of East Anglia, Norwich","institution_ids":["https://openalex.org/I1118541"]}]},{"author_position":"middle","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 Cox","raw_affiliation_strings":["School of Computing Sciences, University of East Anglia, Norwich"],"affiliations":[{"raw_affiliation_string":"School of Computing Sciences, University of East Anglia, Norwich","institution_ids":["https://openalex.org/I1118541"]}]},{"author_position":"middle","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"],"affiliations":[{"raw_affiliation_string":"School of Computing Sciences, University of East Anglia, Norwich","institution_ids":["https://openalex.org/I1118541"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108688251","display_name":"Yuxuan Lan","orcid":null},"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":"Yuxuan Lan","raw_affiliation_strings":["School of Computing Sciences, University of East Anglia, Norwich"],"affiliations":[{"raw_affiliation_string":"School of Computing Sciences, University of East Anglia, Norwich","institution_ids":["https://openalex.org/I1118541"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5037461866"],"corresponding_institution_ids":["https://openalex.org/I1118541"],"apc_list":null,"apc_paid":null,"fwci":7.8176,"has_fulltext":false,"cited_by_count":70,"citation_normalized_percentile":{"value":0.97963558,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2722","last_page":"2726"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.998199999332428,"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"}},{"id":"https://openalex.org/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8198750615119934},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7897440195083618},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6399936079978943},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5838733911514282},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5810170769691467},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5550715923309326},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49110865592956543},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.46859875321388245},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4645625650882721},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.45591554045677185},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45467597246170044},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44673559069633484},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.41882967948913574},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.4102790355682373},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3236401677131653},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32175755500793457},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08955883979797363}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8198750615119934},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7897440195083618},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6399936079978943},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5838733911514282},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5810170769691467},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5550715923309326},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49110865592956543},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.46859875321388245},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4645625650882721},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.45591554045677185},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45467597246170044},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44673559069633484},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.41882967948913574},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.4102790355682373},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3236401677131653},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32175755500793457},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08955883979797363},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2016.7472172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472172","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:ueaeprints.uea.ac.uk:63479","is_oa":false,"landing_page_url":null,"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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"NonPeerReviewed"}],"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":34,"referenced_works":["https://openalex.org/W82494927","https://openalex.org/W142803501","https://openalex.org/W1503933356","https://openalex.org/W1524333225","https://openalex.org/W1531976713","https://openalex.org/W1981970480","https://openalex.org/W1982656606","https://openalex.org/W1992790156","https://openalex.org/W2022799064","https://openalex.org/W2071096833","https://openalex.org/W2076462394","https://openalex.org/W2078711706","https://openalex.org/W2081258893","https://openalex.org/W2096263221","https://openalex.org/W2096391593","https://openalex.org/W2113814270","https://openalex.org/W2122272452","https://openalex.org/W2124629003","https://openalex.org/W2140826107","https://openalex.org/W2160815625","https://openalex.org/W2184188583","https://openalex.org/W2295119550","https://openalex.org/W2399507222","https://openalex.org/W2539331707","https://openalex.org/W2579335913","https://openalex.org/W4285719527","https://openalex.org/W6603350892","https://openalex.org/W6605737493","https://openalex.org/W6631362777","https://openalex.org/W6631751486","https://openalex.org/W6648479894","https://openalex.org/W6686207219","https://openalex.org/W6712426025","https://openalex.org/W6732514500"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2915347927"],"abstract_inverted_index":{"Recent":[0],"improvements":[1],"in":[2,45,72,81],"tracking":[3],"and":[4,49],"feature":[5],"extraction":[6],"mean":[7],"that":[8,69,85,98,117],"speaker-dependent":[9],"lip-reading":[10,89],"of":[11,27,41,52,56,109],"continuous":[12],"speech":[13,73,130],"using":[14],"a":[15,36,67],"medium":[16],"size":[17],"vocabulary":[18],"(around":[19],"1000":[20],"words)":[21],"is":[22,70,119],"realistic.":[23],"However,":[24],"the":[25,42,50,106],"recognition":[26,74],"previously":[28,78],"unseen":[29],"speakers":[30,48],"has":[31,76],"been":[32,79],"found":[33],"to":[34,63,122,125],"be":[35,91,101],"very":[37,61,92],"challenging":[38],"task,":[39],"because":[40],"large":[43],"variation":[44],"lip-shapes":[46],"across":[47],"lack":[51],"large,":[53],"tracked":[54],"databases":[55],"visual":[57,129],"features,":[58],"which":[59],"are":[60],"expensive":[62],"produce.":[64],"By":[65],"adapting":[66],"technique":[68],"established":[71],"but":[75],"not":[77],"used":[80],"lip-reading,":[82],"we":[83,96],"show":[84,97],"error-rates":[86,99],"for":[87,127],"speaker-independent":[88],"can":[90,100],"significantly":[93],"reduced.":[94],"Furthermore,":[95],"even":[102],"further":[103],"reduced":[104],"by":[105],"additional":[107],"use":[108],"Deep":[110],"Neural":[111],"Networks":[112],"(DNN).":[113],"We":[114],"also":[115],"find":[116],"there":[118],"no":[120],"need":[121],"map":[123],"phonemes":[124],"visemes":[126],"context-dependent":[128],"transcription.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}