{"id":"https://openalex.org/W3207232031","doi":"https://doi.org/10.1145/3462244.3479952","title":"Speech Guided Disentangled Visual Representation Learning for Lip Reading","display_name":"Speech Guided Disentangled Visual Representation Learning for Lip Reading","publication_year":2021,"publication_date":"2021-10-15","ids":{"openalex":"https://openalex.org/W3207232031","doi":"https://doi.org/10.1145/3462244.3479952","mag":"3207232031"},"language":"en","primary_location":{"id":"doi:10.1145/3462244.3479952","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3462244.3479952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimodal Interaction","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/A5113892134","display_name":"Ya Zhao","orcid":null},"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":"Ya Zhao","raw_affiliation_strings":["Zhejiang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071422456","display_name":"Cheng Ma","orcid":"https://orcid.org/0000-0002-8148-374X"},"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":"Cheng Ma","raw_affiliation_strings":["Zhejiang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043914348","display_name":"Zunlei Feng","orcid":"https://orcid.org/0000-0001-8640-8434"},"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":"Zunlei Feng","raw_affiliation_strings":["Zhejiang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026532752","display_name":"Mingli Song","orcid":"https://orcid.org/0000-0003-2621-6048"},"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":"Mingli Song","raw_affiliation_strings":["Zhejiang University, China"],"raw_orcid":null,"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":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.1812,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.37936749,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"687","last_page":"691"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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/T11309","display_name":"Music and Audio Processing","score":0.9800999760627747,"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":0.7301230430603027},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.5660237073898315},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5600693821907043},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45901620388031006},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38627612590789795},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3660234808921814},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16517633199691772}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7301230430603027},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.5660237073898315},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5600693821907043},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45901620388031006},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38627612590789795},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3660234808921814},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16517633199691772},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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:10.1145/3462244.3479952","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3462244.3479952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimodal Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8399999737739563}],"awards":[{"id":"https://openalex.org/G5901820694","display_name":null,"funder_award_id":"U20B2066, 61976186","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1526392145","https://openalex.org/W1965365831","https://openalex.org/W1994618660","https://openalex.org/W2018703285","https://openalex.org/W2104095591","https://openalex.org/W2551572271","https://openalex.org/W2594690981","https://openalex.org/W2753738274","https://openalex.org/W2801365175","https://openalex.org/W2803398058","https://openalex.org/W2804205394","https://openalex.org/W2808631503","https://openalex.org/W2808706139","https://openalex.org/W2883725317","https://openalex.org/W2897492880","https://openalex.org/W2911495555","https://openalex.org/W2912083425","https://openalex.org/W2916104401","https://openalex.org/W2952746495","https://openalex.org/W2963258075","https://openalex.org/W2963290645","https://openalex.org/W2963528589","https://openalex.org/W2965424936","https://openalex.org/W2981501041","https://openalex.org/W2996970093","https://openalex.org/W2999528291","https://openalex.org/W3015734344","https://openalex.org/W4297736840","https://openalex.org/W6751836845"],"related_works":["https://openalex.org/W2082438799","https://openalex.org/W1966986837","https://openalex.org/W2360138227","https://openalex.org/W4365808155","https://openalex.org/W1838455177","https://openalex.org/W1489909378","https://openalex.org/W2392697679","https://openalex.org/W2385990477","https://openalex.org/W2331964906","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Lip":[0],"reading":[1,92,159,167],"has":[2],"achieved":[3,105],"unparalleled":[4],"development":[5],"in":[6,36,64],"recent":[7],"years.":[8],"However,":[9],"existing":[10],"methods":[11],"have":[12,169],"two":[13],"main":[14],"problems:":[15],"1)":[16],"there":[17],"is":[18,81,104,128,150],"no":[19],"explicit":[20],"mechanism":[21],"to":[22,32,55,62,82,134],"ensure":[23],"that":[24,145],"the":[25,109,125,131,142,157,171,174],"extracted":[26],"visual":[27,74,88],"features":[28,89,127,149],"are":[29,53,60],"only":[30],"related":[31,87,114,119],"lip":[33,85,91,112,147,158,166],"movements,":[34],"resulting":[35],"degraded":[37],"performance":[38],"when":[39],"video":[40,143],"contains":[41],"large":[42],"variations,":[43],"such":[44],"as":[45,130,152],"speakers\u2019":[46],"poses;":[47],"2)":[48],"quantities":[49,98],"of":[50,97,99,173],"labeled":[51],"data":[52],"required":[54],"achieve":[56],"good":[57],"results,":[58],"which":[59],"difficult":[61],"obtain":[63],"low-resource":[65],"languages.":[66],"In":[67],"this":[68,139],"paper,":[69],"we":[70],"propose":[71],"a":[72,153],"new":[73],"representation":[75],"learning":[76],"method,":[77],"SVLR,":[78],"whose":[79],"purpose":[80],"extract":[83],"disentangled,":[84],"movements":[86,113,148],"for":[90,156],"task,":[93],"by":[94,106],"making":[95],"use":[96],"unlabeled":[100],"audio-visual":[101],"data.":[102],"This":[103],"explicitly":[107],"disentangling":[108],"feature":[110,154],"into":[111],"part":[115],"and":[116],"speaker":[117],"identity":[118],"part.":[120],"Then":[121],"predicting":[122],"speech":[123],"from":[124],"disentangled":[126],"used":[129,151],"training":[132],"objective":[133],"optimize":[135],"model":[136],"parameters.":[137],"After":[138],"cross-modal":[140],"training,":[141],"encoder":[144],"extracts":[146],"extractor":[155],"task.":[160],"Various":[161],"experiments":[162],"on":[163],"several":[164],"word-level":[165],"benchmarks":[168],"proved":[170],"effectiveness":[172],"proposed":[175],"method.":[176]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}