{"id":"https://openalex.org/W4399873823","doi":"https://doi.org/10.1145/3661725.3661767","title":"Speaker Adaptation for Lip Reading with Robust Entropy Minimization and Adaptive Pseudo Labels","display_name":"Speaker Adaptation for Lip Reading with Robust Entropy Minimization and Adaptive Pseudo Labels","publication_year":2024,"publication_date":"2024-04-12","ids":{"openalex":"https://openalex.org/W4399873823","doi":"https://doi.org/10.1145/3661725.3661767"},"language":"en","primary_location":{"id":"doi:10.1145/3661725.3661767","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3661725.3661767","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conference on Computing Machine Learning and Data Science","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101480652","display_name":"Hao Shen","orcid":"https://orcid.org/0009-0005-8729-4551"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Shen","raw_affiliation_strings":["State Grid Zhejiang Electric Power Co., Ltd, China"],"raw_orcid":"https://orcid.org/0009-0005-8729-4551","affiliations":[{"raw_affiliation_string":"State Grid Zhejiang Electric Power Co., Ltd, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083246300","display_name":"Weihao Jiang","orcid":"https://orcid.org/0009-0006-8093-4437"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weihao Jiang","raw_affiliation_strings":["Zhejiang University, China"],"raw_orcid":"https://orcid.org/0009-0006-8093-4437","affiliations":[{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055689719","display_name":"Junjie Huang","orcid":"https://orcid.org/0009-0009-2663-0848"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Huang","raw_affiliation_strings":["Zhejiang University, China"],"raw_orcid":"https://orcid.org/0009-0009-2663-0848","affiliations":[{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9937000274658203,"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/T11448","display_name":"Face recognition and analysis","score":0.9919000267982483,"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":0.8262760639190674},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.7098642587661743},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5562983751296997},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.5446639657020569},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5431659817695618},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5390801429748535},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5136331915855408},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.41193628311157227},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35711681842803955},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35511481761932373}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8262760639190674},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.7098642587661743},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5562983751296997},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.5446639657020569},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5431659817695618},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5390801429748535},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5136331915855408},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.41193628311157227},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35711681842803955},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35511481761932373},{"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3661725.3661767","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3661725.3661767","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conference on Computing Machine Learning and Data Science","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W82936479","https://openalex.org/W1989549063","https://openalex.org/W2010362084","https://openalex.org/W2015143272","https://openalex.org/W2046056978","https://openalex.org/W2079623482","https://openalex.org/W2127141656","https://openalex.org/W2160306971","https://openalex.org/W2890952074","https://openalex.org/W2890964092","https://openalex.org/W2914911817","https://openalex.org/W2939164678","https://openalex.org/W2963528589","https://openalex.org/W2963785710","https://openalex.org/W2972473456","https://openalex.org/W2973036346","https://openalex.org/W2981501041","https://openalex.org/W3004032783","https://openalex.org/W3006713268","https://openalex.org/W3015830103","https://openalex.org/W3091641623","https://openalex.org/W3163464943","https://openalex.org/W3167917117","https://openalex.org/W3195455417","https://openalex.org/W4214540501"],"related_works":["https://openalex.org/W4394775207","https://openalex.org/W3035557009","https://openalex.org/W3204418343","https://openalex.org/W2341113105","https://openalex.org/W2955172689","https://openalex.org/W3132602785","https://openalex.org/W3046182208","https://openalex.org/W2343346879","https://openalex.org/W2186589590","https://openalex.org/W4297818280"],"abstract_inverted_index":{"Lip":[0],"reading":[1,26,115],"aims":[2],"at":[3],"recognizing":[4],"what":[5],"a":[6,11,132],"speaker":[7,60,111],"is":[8,45,96],"saying":[9],"in":[10,77,89,104],"silent":[12],"video":[13],"only":[14],"based":[15],"on":[16,47,109],"visual":[17],"information.":[18],"With":[19],"the":[20,43,65,70,73,87,91,117,121,139,146,149,165,168,172,184],"development":[21],"of":[22,72,123,141,148],"deep":[23],"learning,":[24],"lip":[25,114],"has":[27],"attracted":[28],"much":[29],"attention.":[30],"However,":[31,76],"different":[32,35],"people":[33],"have":[34],"facial":[36],"features,":[37],"which":[38,63],"leads":[39],"to":[40,81,137,159],"failure":[41],"when":[42],"model":[44,170],"tested":[46],"unseen":[48],"speakers.":[49],"Most":[50],"existing":[51],"methods":[52,62,95],"deal":[53],"with":[54,57,101],"this":[55,102,105],"problem":[56],"fine-tuning":[58],"or":[59,69,83],"adaptation":[61,112],"require":[64],"source":[66,118,169],"domain":[67],"data":[68,119,125],"labels":[71,122],"target":[74,124],"domain.":[75],"real-world":[78],"applications,":[79],"due":[80],"privacy":[82],"storage":[84],"issues":[85],"and":[86,120,144,171,191],"difficulty":[88],"annotating":[90],"data,":[92],"using":[93],"these":[94],"not":[97],"realistic.":[98],"To":[99],"cope":[100],"problem,":[103],"paper,":[106],"we":[107,153],"focus":[108],"test-time":[110],"for":[113],"where":[116],"are":[126],"unavailable":[127],"during":[128],"adaptation.":[129],"We":[130],"propose":[131,154],"robust":[133],"entropy":[134],"minimization":[135],"strategy":[136,158],"amplify":[138],"optimization":[140],"high-confident":[142],"samples":[143,163],"reduce":[145],"influence":[147],"low-confident":[150],"samples.":[151],"Furthermore,":[152],"an":[155],"adaptive":[156],"pseudo-label":[157],"select":[160],"more":[161],"confident":[162],"between":[164],"outputs":[166],"from":[167],"augmented-averaged":[173],"teacher":[174],"model.":[175],"Extensive":[176],"experiments":[177],"show":[178],"that":[179],"our":[180],"method":[181],"outperforms":[182],"all":[183],"other":[185],"baselines":[186],"consistently,":[187],"demonstrating":[188],"its":[189],"effectiveness":[190],"universality.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}