{"id":"https://openalex.org/W3195455417","doi":"https://doi.org/10.1109/icip42928.2021.9506396","title":"Speaker-Independent Lipreading By Disentangled Representation Learning","display_name":"Speaker-Independent Lipreading By Disentangled Representation Learning","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W3195455417","doi":"https://doi.org/10.1109/icip42928.2021.9506396","mag":"3195455417"},"language":"en","primary_location":{"id":"doi:10.1109/icip42928.2021.9506396","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip42928.2021.9506396","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Image Processing (ICIP)","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/A5100363180","display_name":"Qun Zhang","orcid":"https://orcid.org/0000-0002-2773-3437"},"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":"Qun Zhang","raw_affiliation_strings":["Shanghai Jiaotong University,School of Electronic Information and Electrical Engineering,Shanghai,China,200240"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiaotong University,School of Electronic Information and Electrical Engineering,Shanghai,China,200240","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":["Shanghai Jiaotong University,School of Electronic Information and Electrical Engineering,Shanghai,China,200240"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiaotong University,School of Electronic Information and Electrical Engineering,Shanghai,China,200240","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087546979","display_name":"Gongliang Chen","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":"Gongliang Chen","raw_affiliation_strings":["Shanghai Jiaotong University,School of Electronic Information and Electrical Engineering,Shanghai,China,200240"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiaotong University,School of Electronic Information and Electrical Engineering,Shanghai,China,200240","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2493","last_page":"2497"},"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":0.9973000288009644,"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":0.9932000041007996,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8177981376647949},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7041847705841064},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6183263659477234},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5831270813941956},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5816221833229065},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5809425711631775},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.5680208206176758},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5449962615966797},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.48565423488616943},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4668470323085785},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4377765655517578},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4359019994735718},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34341228008270264},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08116969466209412}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8177981376647949},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7041847705841064},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6183263659477234},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5831270813941956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5816221833229065},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5809425711631775},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5680208206176758},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5449962615966797},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.48565423488616943},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4668470323085785},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4377765655517578},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4359019994735718},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34341228008270264},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08116969466209412},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/icip42928.2021.9506396","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip42928.2021.9506396","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"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":25,"referenced_works":["https://openalex.org/W2015143272","https://openalex.org/W2076462394","https://openalex.org/W2404704342","https://openalex.org/W2551572271","https://openalex.org/W2766042539","https://openalex.org/W2808707363","https://openalex.org/W2886945201","https://openalex.org/W2890952074","https://openalex.org/W2962681491","https://openalex.org/W2963356069","https://openalex.org/W2963936489","https://openalex.org/W2981501041","https://openalex.org/W2993240882","https://openalex.org/W3035040255","https://openalex.org/W3035757124","https://openalex.org/W3089868584","https://openalex.org/W3091641623","https://openalex.org/W4298112588","https://openalex.org/W4385245566","https://openalex.org/W6732872814","https://openalex.org/W6734491695","https://openalex.org/W6739901393","https://openalex.org/W6742376216","https://openalex.org/W6752365561","https://openalex.org/W6754392867"],"related_works":["https://openalex.org/W4375867731","https://openalex.org/W2905271011","https://openalex.org/W3048601286","https://openalex.org/W3164948662","https://openalex.org/W4289536128","https://openalex.org/W2965925734","https://openalex.org/W1560125148","https://openalex.org/W3153597579","https://openalex.org/W1872833176","https://openalex.org/W4309346246"],"abstract_inverted_index":{"With":[0],"the":[1,4,23,41,49,53,79,83,87,94,100,116,123,129,135,153,156,160],"development":[2],"of":[3,155],"deep":[5,12,58],"learning":[6],"technology,":[7],"automatic":[8],"lipreading":[9,30],"based":[10],"on":[11,146],"neural":[13,59],"network":[14,60,111,158],"can":[15,142],"achieve":[16],"reliable":[17],"results":[18],"for":[19,31,139],"speakers":[20,141],"appeared":[21],"in":[22,52,71,99,110,159],"training":[24,42],"dataset.":[25],"However,":[26],"speaker-independent":[27,54,161],"lipreading,":[28],"i.e.":[29],"unseen":[32,140],"speakers,":[33],"is":[34,69,75,108],"still":[35],"a":[36,56,103],"challenging":[37],"task,":[38],"especially":[39],"when":[40],"samples":[43],"are":[44,119],"quite":[45],"limited.":[46],"To":[47,91],"improve":[48],"recognition":[50,137],"performance":[51,138],"scenario,":[55],"new":[57],"structure,":[61],"named":[62],"Disentangled":[63],"Visual":[64],"Speech":[65],"Recognition":[66],"Network":[67],"(DVSR-Net),":[68],"proposed":[70,157],"this":[72,114],"paper.":[73],"DVSR-Net":[74],"designed":[76,109],"to":[77,122,128],"disentangle":[78],"identity-related":[80],"features":[81,85,118],"and":[82,126,133],"content-related":[84],"from":[86],"lip":[88],"image":[89],"sequence.":[90],"further":[92],"eliminate":[93],"identity":[95],"information":[96,125],"that":[97],"remained":[98],"content":[101,104,124],"features,":[102],"feature":[105],"refinement":[106],"stage":[107],"optimization.":[112],"By":[113],"way,":[115],"extracted":[117],"closely":[120],"related":[121],"irrelevant":[127],"various":[130],"talking":[131],"style":[132],"thus":[134],"speech":[136],"be":[143],"improved.":[144],"Experiments":[145],"two":[147],"widely":[148],"used":[149],"datasets":[150],"have":[151],"demonstrated":[152],"effectiveness":[154],"scenario.":[162]},"counts_by_year":[{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}