{"id":"https://openalex.org/W3091641623","doi":"https://doi.org/10.1109/icip40778.2020.9190780","title":"Speaker-Independent Lipreading With Limited Data","display_name":"Speaker-Independent Lipreading With Limited Data","publication_year":2020,"publication_date":"2020-09-30","ids":{"openalex":"https://openalex.org/W3091641623","doi":"https://doi.org/10.1109/icip40778.2020.9190780","mag":"3091641623"},"language":"en","primary_location":{"id":"doi:10.1109/icip40778.2020.9190780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip40778.2020.9190780","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 Image Processing (ICIP)","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/A5059557772","display_name":"Chenzhao Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chenzhao Yang","raw_affiliation_strings":["School of Electronic Information and Electrical Engineering, Shanghai Jiaotong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiaotong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101717685","display_name":"Shilin Wang","orcid":"https://orcid.org/0000-0002-8214-6809"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shilin Wang","raw_affiliation_strings":["School of Electronic Information and Electrical Engineering, Shanghai Jiaotong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiaotong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054452505","display_name":"Xingxuan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingxuan Zhang","raw_affiliation_strings":["School of Electronic Information and Electrical Engineering, Shanghai Jiaotong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiaotong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112108272","display_name":"Yun Zhu","orcid":"https://orcid.org/0009-0008-4616-3039"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Zhu","raw_affiliation_strings":["School of Electronic Information and Electrical Engineering, Shanghai Jiaotong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiaotong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5059557772"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":1.5153,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.83350889,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2181","last_page":"2185"},"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":0.9922999739646912,"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":0.9793000221252441,"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":0.8316053748130798},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7236294150352478},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6312404870986938},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5836687684059143},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5321943759918213},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5072019100189209},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.471469908952713},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.45572370290756226},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4405694007873535},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.41536518931388855},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34275585412979126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8316053748130798},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7236294150352478},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6312404870986938},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5836687684059143},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5321943759918213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5072019100189209},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.471469908952713},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.45572370290756226},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4405694007873535},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.41536518931388855},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34275585412979126},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip40778.2020.9190780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip40778.2020.9190780","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 Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1531976713","https://openalex.org/W2015143272","https://openalex.org/W2015394094","https://openalex.org/W2046599127","https://openalex.org/W2087681821","https://openalex.org/W2096391593","https://openalex.org/W2099940393","https://openalex.org/W2106137268","https://openalex.org/W2127141656","https://openalex.org/W2130112859","https://openalex.org/W2142075667","https://openalex.org/W2267805933","https://openalex.org/W2551572271","https://openalex.org/W2578229578","https://openalex.org/W2594690981","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2952746495","https://openalex.org/W2963403868","https://openalex.org/W2981501041","https://openalex.org/W4298112588","https://openalex.org/W4385245566","https://openalex.org/W6631751486","https://openalex.org/W6732872814","https://openalex.org/W6734491695","https://openalex.org/W6739901393","https://openalex.org/W6754392867","https://openalex.org/W6754420807"],"related_works":["https://openalex.org/W2953716828","https://openalex.org/W2904857019","https://openalex.org/W2944728705","https://openalex.org/W3011538607","https://openalex.org/W2904022177","https://openalex.org/W2591697403","https://openalex.org/W4321441197","https://openalex.org/W2359348847","https://openalex.org/W4294432981","https://openalex.org/W4321276295"],"abstract_inverted_index":{"Recent":[0],"researches":[1],"have":[2,141],"demonstrated":[3,142],"that":[4],"with":[5,152],"a":[6,20,34,65],"huge":[7],"annotated":[8],"training":[9,28,154],"dataset,":[10],"some":[11],"sophisticated":[12],"automatic":[13],"lipreading":[14,41,59],"methods":[15],"perform":[16],"even":[17],"better":[18],"than":[19],"professional":[21],"human":[22],"lip":[23,104],"reader.":[24],"However,":[25],"when":[26],"the":[27,53,58,62,85,93,108,119,138,143,146],"set":[29],"is":[30,71,79,100,130],"limited,":[31],"i.e.":[32,84],"containing":[33],"few":[35],"number":[36],"of":[37,81,121,145],"speakers,":[38],"most":[39],"existing":[40],"approaches":[42],"cannot":[43],"provide":[44],"accurate":[45],"recognition":[46,151],"results":[47,136],"for":[48,132],"unseen":[49],"speakers":[50],"due":[51],"to":[52,102,113],"inter-speaker":[54],"variability.":[55],"To":[56],"improve":[57],"performance":[60],"in":[61,73],"speaker-independent":[63,150],"scenario,":[64],"new":[66],"deep":[67],"neural":[68],"network":[69,78,133,148],"(DNN)":[70],"proposed":[72,77,147],"this":[74],"paper.":[75],"The":[76,98,110],"composed":[80],"two":[82],"parts,":[83],"Transformer-based":[86],"Visual":[87],"Speech":[88],"Recognition":[89],"Network":[90],"(TVSR-Net)":[91],"and":[92,106],"Speaker":[94],"Confusion":[95],"Block":[96],"(SC-Block).":[97],"TVSR-Net":[99],"designed":[101,131],"extract":[103],"features":[105],"recognize":[107],"speech.":[109],"SC-Block":[111],"aims":[112],"achieve":[114],"speaker":[115],"normalization":[116],"by":[117],"eliminating":[118],"influence":[120],"various":[122],"talking":[123],"styles/habits.":[124],"A":[125],"Multi-Task":[126],"Learning":[127],"(MTL)":[128],"scheme":[129],"optimization.":[134],"Experiment":[135],"on":[137,149],"GRID":[139],"dataset":[140],"effectiveness":[144],"limited":[153],"data.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}