{"id":"https://openalex.org/W3112783203","doi":"https://doi.org/10.1109/smc42975.2020.9283044","title":"Part-Based Lipreading for Audio-Visual Speech Recognition","display_name":"Part-Based Lipreading for Audio-Visual Speech Recognition","publication_year":2020,"publication_date":"2020-10-11","ids":{"openalex":"https://openalex.org/W3112783203","doi":"https://doi.org/10.1109/smc42975.2020.9283044","mag":"3112783203"},"language":"en","primary_location":{"id":"doi:10.1109/smc42975.2020.9283044","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc42975.2020.9283044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5053671393","display_name":"Ziling Miao","orcid":"https://orcid.org/0000-0003-2414-3674"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ziling Miao","raw_affiliation_strings":["Shenzhen Graduate School, Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Graduate School, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I4210128628"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100410326","display_name":"Hong Liu","orcid":"https://orcid.org/0000-0002-7498-6541"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Liu","raw_affiliation_strings":["Shenzhen Graduate School, Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Graduate School, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I4210128628"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086513946","display_name":"Bing Yang","orcid":"https://orcid.org/0000-0002-8978-2322"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Yang","raw_affiliation_strings":["Shenzhen Graduate School, Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Graduate School, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I4210128628"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053671393"],"corresponding_institution_ids":["https://openalex.org/I4210128628"],"apc_list":null,"apc_paid":null,"fwci":0.6096,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.68441711,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9936000108718872,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9926000237464905,"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/computer-science","display_name":"Computer science","score":0.7669733762741089},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.692955732345581},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5192189812660217},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5038990378379822},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49478524923324585},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.46773773431777954},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4629007577896118},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4568711817264557},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.1262936294078827},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06460380554199219}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7669733762741089},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.692955732345581},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5192189812660217},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5038990378379822},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49478524923324585},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.46773773431777954},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4629007577896118},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4568711817264557},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.1262936294078827},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06460380554199219},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc42975.2020.9283044","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc42975.2020.9283044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1522734439","https://openalex.org/W1526392145","https://openalex.org/W1974387177","https://openalex.org/W2015143272","https://openalex.org/W2096391593","https://openalex.org/W2121486117","https://openalex.org/W2148659689","https://openalex.org/W2194775991","https://openalex.org/W2243738093","https://openalex.org/W2289925289","https://openalex.org/W2404704342","https://openalex.org/W2527681779","https://openalex.org/W2550980560","https://openalex.org/W2551572271","https://openalex.org/W2556171197","https://openalex.org/W2594690981","https://openalex.org/W2952746495","https://openalex.org/W2963295405","https://openalex.org/W2963528589","https://openalex.org/W2963654155","https://openalex.org/W2963842104","https://openalex.org/W2964121744","https://openalex.org/W3105538092","https://openalex.org/W6631190155","https://openalex.org/W6729540071","https://openalex.org/W6729699919","https://openalex.org/W6734491695"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2074916782","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W4245955731","https://openalex.org/W2393726419","https://openalex.org/W2330333072","https://openalex.org/W2380912101"],"abstract_inverted_index":{"Lipreading":[0],"is":[1,80,185],"an":[2,88,177],"important":[3],"component":[4],"of":[5,24,30,96,102,146,162,166],"audio-visual":[6,179],"speech":[7,180],"recognition.":[8],"However,":[9],"lips":[10,112],"are":[11,135],"usually":[12,49,63],"modeled":[13],"as":[14,67,70],"a":[15,51,119,138],"whole":[16,47],"in":[17,107,151,158],"lipreading,":[18],"which":[19,57],"ignores":[20],"that":[21,59],"each":[22,39],"part":[23,40,145],"lip":[25,48,90],"focuses":[26],"on":[27,45,104,123,137,170,174,192],"different":[28,55],"characteristics":[29],"mouth":[31],"and":[32,92,114,126,144,172,187],"the":[33,46,60,85,93,99,105,155,159],"overall":[34,89],"model":[35,91],"can":[36],"not":[37],"fit":[38],"perfectly.":[41],"Besides,":[42],"features":[43,125],"based":[44],"vary":[50],"lot":[52],"according":[53],"to":[54,65,82,153],"speakers,":[56],"leads":[58],"training":[61,108],"databases":[62],"need":[64],"contain":[66],"much":[68],"speakers":[69,106],"possible.":[71],"In":[72],"this":[73],"paper,":[74],"A":[75],"part-based":[76],"lipreading":[77],"(PBL)":[78],"method":[79],"proposed":[81],"deal":[83],"with":[84],"mismatch":[86],"between":[87],"separate":[94],"parts":[95],"lips,":[97],"also":[98],"excessive":[100],"dependence":[101],"models":[103,111],"set.":[109],"PBL":[110,167,184],"partly":[113],"predicts":[115],"jointly.":[116],"It":[117],"employs":[118],"uniform":[120],"partition":[121],"strategy":[122],"convolutional":[124],"generates":[127],"several":[128],"part-level":[129],"sub-results":[130],"for":[131],"final":[132],"prediction.":[133],"Experiments":[134],"performed":[136],"large":[139],"publicly":[140],"available":[141],"dataset":[142],"(LRW)":[143],"it":[147],"(p-LRW,":[148],"65":[149],"words),":[150],"order":[152],"simulate":[154],"progressive":[156],"instructions":[157],"working":[160],"scene":[161],"robots.":[163],"Word":[164],"accuracy":[165,191],"reaches":[168],"82.8%":[169],"LRW":[171],"88.9%":[173],"p-LRW.":[175],"Finally,":[176],"end-to-end":[178],"recognition":[181],"system":[182],"using":[183],"established":[186],"achieves":[188],"98.3%":[189],"word":[190],"LRW.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}