{"id":"https://openalex.org/W2096263221","doi":"https://doi.org/10.1109/icassp.2012.6288999","title":"Insights into machine lip reading","display_name":"Insights into machine lip reading","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2096263221","doi":"https://doi.org/10.1109/icassp.2012.6288999","mag":"2096263221"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 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/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, 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":"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, 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/A5112911728","display_name":"Barry-John Theobald","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":"Barry-John Theobald","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":1.7058,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.87683076,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4825","last_page":"4828"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9994000196456909,"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/T10057","display_name":"Face and Expression Recognition","score":0.9304999709129333,"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":0.7705070972442627},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.6641203165054321},{"id":"https://openalex.org/keywords/bittorrent-tracker","display_name":"BitTorrent tracker","score":0.6144455075263977},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5385000109672546},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.529349148273468},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5177292227745056},{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.5045372247695923},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3506714999675751},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33294808864593506},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3217300772666931},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.26357975602149963},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.14799559116363525},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.08637690544128418}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7705070972442627},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.6641203165054321},{"id":"https://openalex.org/C57501372","wikidata":"https://www.wikidata.org/wiki/Q2021268","display_name":"BitTorrent tracker","level":3,"score":0.6144455075263977},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5385000109672546},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.529349148273468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5177292227745056},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.5045372247695923},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3506714999675751},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33294808864593506},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3217300772666931},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.26357975602149963},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.14799559116363525},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.08637690544128418},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2012.6288999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5799999833106995}],"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/F4320320312","display_name":"Home Office","ror":"https://ror.org/00y81cg83"},{"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":12,"referenced_works":["https://openalex.org/W82494927","https://openalex.org/W142803501","https://openalex.org/W943204654","https://openalex.org/W1531976713","https://openalex.org/W1908325895","https://openalex.org/W2071096833","https://openalex.org/W2096391593","https://openalex.org/W2152826865","https://openalex.org/W4285719527","https://openalex.org/W6603350892","https://openalex.org/W6605737493","https://openalex.org/W6639968709"],"related_works":["https://openalex.org/W2796042130","https://openalex.org/W2142490914","https://openalex.org/W4253235840","https://openalex.org/W2488941600","https://openalex.org/W2116497041","https://openalex.org/W2591964346","https://openalex.org/W131634123","https://openalex.org/W2757496505","https://openalex.org/W1560013842","https://openalex.org/W2092351437"],"abstract_inverted_index":{"Computer":[0],"lip-reading":[1],"is":[2,12,17,21,33,102,115],"one":[3],"of":[4,35,38,57,98],"the":[5,13,26,36],"great":[6],"signal":[7,14],"processing":[8],"challenges.":[9],"Not":[10],"only":[11,47],"noisy,":[15],"it":[16,20],"variable.":[18],"However":[19],"almost":[22],"unknown":[23],"to":[24,104],"compare":[25],"performance":[27],"with":[28],"human":[29,39,58,87,107,111],"lip-readers.":[30,88,108],"Partly":[31],"this":[32],"because":[34,43],"paucity":[37],"lip-readers":[40,112],"and":[41,53,82,86],"partly":[42],"most":[44],"automatic":[45,75,90],"systems":[46],"handle":[48],"data":[49],"that":[50,69],"are":[51],"trivial":[52],"therefore":[54],"not":[55],"representative":[56],"speech.":[59],"Here":[60],"we":[61,92],"generate":[62],"a":[63,95],"multiview":[64],"dataset":[65],"using":[66],"connected":[67],"words":[68],"can":[70],"be":[71],"analysed":[72],"by":[73],"an":[74],"system,":[76],"based":[77],"on":[78],"linear":[79],"predictive":[80],"trackers":[81],"active":[83],"appearance":[84],"models,":[85],"The":[89],"system":[91,114],"devise":[93],"has":[94],"viseme":[96],"accuracy":[97],"\u2248":[99],"46%":[100],"which":[101],"comparable":[103],"poor":[105],"professional":[106],"However,":[109],"unlike":[110],"our":[113],"good":[116],"at":[117],"guessing":[118],"its":[119],"fallibility.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
