{"id":"https://openalex.org/W3108430560","doi":"https://doi.org/10.1145/3421558.3421563","title":"A Survey of Lipreading Methods Based on Deep Learning","display_name":"A Survey of Lipreading Methods Based on Deep Learning","publication_year":2020,"publication_date":"2020-08-05","ids":{"openalex":"https://openalex.org/W3108430560","doi":"https://doi.org/10.1145/3421558.3421563","mag":"3108430560"},"language":"en","primary_location":{"id":"doi:10.1145/3421558.3421563","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3421558.3421563","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 2nd International Conference on Image Processing and Machine Vision","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/A5002380782","display_name":"Mingfeng Hao","orcid":"https://orcid.org/0000-0002-6120-6518"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"MINGFENG HAO","raw_affiliation_strings":["Xinjiang University, China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079890912","display_name":"MUTELEP MAMUT","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"MUTELEP MAMUT","raw_affiliation_strings":["Library of Xinjiang University, China"],"affiliations":[{"raw_affiliation_string":"Library of Xinjiang University, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066506917","display_name":"Kurban Ubul","orcid":"https://orcid.org/0000-0002-7566-6494"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"KURBAN UBUL","raw_affiliation_strings":["Xinjiang University, China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University, China","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5002380782"],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":null,"apc_paid":null,"fwci":0.4546,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.62725477,"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":"31","last_page":"39"},"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":0.9947999715805054,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.984000027179718,"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/computer-science","display_name":"Computer science","score":0.807158887386322},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.72834312915802},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7142579555511475},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6173956990242004},{"id":"https://openalex.org/keywords/movement","display_name":"Movement (music)","score":0.4879698157310486},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.47462785243988037},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.4435352385044098},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44050735235214233},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.41269564628601074},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32819420099258423},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.327075719833374}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.807158887386322},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.72834312915802},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7142579555511475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6173956990242004},{"id":"https://openalex.org/C2780226923","wikidata":"https://www.wikidata.org/wiki/Q929848","display_name":"Movement (music)","level":2,"score":0.4879698157310486},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.47462785243988037},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.4435352385044098},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44050735235214233},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.41269564628601074},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32819420099258423},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.327075719833374},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3421558.3421563","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3421558.3421563","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 2nd International Conference on Image Processing and Machine Vision","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5299999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1526392145","https://openalex.org/W1549662771","https://openalex.org/W1983364832","https://openalex.org/W2015143272","https://openalex.org/W2028778923","https://openalex.org/W2033895145","https://openalex.org/W2046599127","https://openalex.org/W2076462394","https://openalex.org/W2120974626","https://openalex.org/W2121015323","https://openalex.org/W2127141656","https://openalex.org/W2157331557","https://openalex.org/W2163605009","https://openalex.org/W2267805933","https://openalex.org/W2316870419","https://openalex.org/W2406846463","https://openalex.org/W2466347009","https://openalex.org/W2511073133","https://openalex.org/W2578229578","https://openalex.org/W2596627958","https://openalex.org/W2604379605","https://openalex.org/W2604769302","https://openalex.org/W2734984521","https://openalex.org/W2737701198","https://openalex.org/W2741151796","https://openalex.org/W2752186468","https://openalex.org/W2754826374","https://openalex.org/W2761659801","https://openalex.org/W2793493229","https://openalex.org/W2802223794","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2897492880","https://openalex.org/W2901821455","https://openalex.org/W2943455019","https://openalex.org/W2955275164","https://openalex.org/W2957285883","https://openalex.org/W2962915147","https://openalex.org/W2963030892","https://openalex.org/W2963192365","https://openalex.org/W2963370694","https://openalex.org/W2963654155","https://openalex.org/W2963658982","https://openalex.org/W2963744813","https://openalex.org/W2963785710","https://openalex.org/W2972756321","https://openalex.org/W6665984962","https://openalex.org/W6674914833","https://openalex.org/W6686207219","https://openalex.org/W6687483927","https://openalex.org/W6725739302","https://openalex.org/W6734491695","https://openalex.org/W6735927292","https://openalex.org/W6739901393","https://openalex.org/W6765296696"],"related_works":["https://openalex.org/W3203142394","https://openalex.org/W4375867731","https://openalex.org/W4302615923","https://openalex.org/W1974101135","https://openalex.org/W2351061015","https://openalex.org/W2017509870","https://openalex.org/W2184114188","https://openalex.org/W4220731478","https://openalex.org/W2542937328","https://openalex.org/W4251141768"],"abstract_inverted_index":{"Visual":[0],"speech":[1,10,27],"recognition,":[2],"also":[3],"known":[4],"as":[5],"lipreading,":[6],"is":[7,41,82],"to":[8,60,94],"recognize":[9],"content":[11],"by":[12],"decoding":[13],"the":[14,18,23,46,55,96,103,107,112,118,121,126,136,141,144],"visual":[15],"information":[16,105],"of":[17,25,31,49,57,125,143],"speaker's":[19],"lip":[20,97],"movement":[21,98],"on":[22,34,79],"basis":[24],"no":[26],"signal.":[28],"The":[29,89],"effect":[30],"lipreading":[32,61,138],"based":[33,78],"traditional":[35],"manual":[36],"features":[37],"in":[38,52,117,147],"complex":[39],"scenes":[40],"not":[42],"very":[43],"good.":[44],"With":[45],"great":[47],"success":[48],"deep":[50,58,80],"learning":[51,59,81],"image":[53],"classification,":[54],"application":[56],"has":[62],"become":[63],"a":[64],"new":[65],"development":[66],"trend,":[67],"but":[68],"there":[69],"are":[70,91,128],"still":[71],"some":[72],"challenges":[73],"and":[74,87,100,120,130,140],"problems.":[75],"Lipreading":[76],"model":[77,124],"mainly":[83,92],"divided":[84],"into":[85],"front-end":[86,90,119],"back-end.":[88,108],"used":[93,146],"extract":[95],"features,":[99],"then":[101],"decode":[102],"long-term":[104],"through":[106],"In":[109,132],"this":[110],"paper,":[111],"convolution":[113],"neural":[114],"network":[115],"structure":[116],"sequence":[122],"processing":[123],"back-end":[127],"discussed":[129],"analyzed.":[131],"addition,":[133],"it":[134],"introduces":[135],"current":[137],"datasets":[139],"comparison":[142],"methods":[145],"these":[148],"datasets.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}