{"id":"https://openalex.org/W4401991227","doi":"https://doi.org/10.1109/icmew63481.2024.10645400","title":"Enhancing Lip Reading with Multi-Scale Video and Multi-Encoder","display_name":"Enhancing Lip Reading with Multi-Scale Video and Multi-Encoder","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4401991227","doi":"https://doi.org/10.1109/icmew63481.2024.10645400"},"language":"en","primary_location":{"id":"doi:10.1109/icmew63481.2024.10645400","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew63481.2024.10645400","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","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/A5101149305","display_name":"He Wang","orcid":"https://orcid.org/0000-0002-7852-8492"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Wang","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101783173","display_name":"Pengcheng Guo","orcid":"https://orcid.org/0009-0001-2388-5935"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Guo","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047201304","display_name":"Xucheng Wan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123571","display_name":"Huawei Technologies (France)","ror":"https://ror.org/02rbzf697","country_code":"FR","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210123571"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Xucheng Wan","raw_affiliation_strings":["IT Innovation and Research Center, Huawei Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IT Innovation and Research Center, Huawei Technologies","institution_ids":["https://openalex.org/I4210123571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084727631","display_name":"Huan Zhou","orcid":"https://orcid.org/0000-0003-2319-4103"},"institutions":[{"id":"https://openalex.org/I4210123571","display_name":"Huawei Technologies (France)","ror":"https://ror.org/02rbzf697","country_code":"FR","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210123571"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Huan Zhou","raw_affiliation_strings":["IT Innovation and Research Center, Huawei Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IT Innovation and Research Center, Huawei Technologies","institution_ids":["https://openalex.org/I4210123571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6686,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.84911061,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"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":0.9810000061988831,"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":0.9810000061988831,"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":0.9014999866485596,"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":0.7598652839660645},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.6461613178253174},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6252680420875549},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5769745111465454},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4581564664840698},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4575442969799042},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4441166818141937},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4000915586948395},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07316046953201294},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.0688580572605133}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7598652839660645},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.6461613178253174},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6252680420875549},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5769745111465454},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4581564664840698},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4575442969799042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4441166818141937},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4000915586948395},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07316046953201294},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0688580572605133},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/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/icmew63481.2024.10645400","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew63481.2024.10645400","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8100000023841858,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1904457459","https://openalex.org/W2194775991","https://openalex.org/W2526425061","https://openalex.org/W2533523411","https://openalex.org/W2795935804","https://openalex.org/W3093145643","https://openalex.org/W3097777922","https://openalex.org/W3128564814","https://openalex.org/W3162293946","https://openalex.org/W3203942572","https://openalex.org/W4224933780","https://openalex.org/W4297841387","https://openalex.org/W4297841719","https://openalex.org/W4360995947","https://openalex.org/W4372317224","https://openalex.org/W4372346152","https://openalex.org/W4375869161","https://openalex.org/W4390961124","https://openalex.org/W4392902829","https://openalex.org/W4392903825","https://openalex.org/W4392908934","https://openalex.org/W6728841359","https://openalex.org/W6839026989","https://openalex.org/W6845482479","https://openalex.org/W6860836352"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2082438799","https://openalex.org/W1966986837","https://openalex.org/W2360138227","https://openalex.org/W2142795561","https://openalex.org/W4365808155","https://openalex.org/W1838455177","https://openalex.org/W1489909378"],"abstract_inverted_index":{"Automatic":[0],"lip-reading":[1,20,43],"(ALR)":[2],"aims":[3],"to":[4,28,41,78,90,166],"automatically":[5],"tran-scribe":[6],"spoken":[7],"content":[8],"from":[9],"a":[10,24,33,55,157],"speaker's":[11,68],"silent":[12],"lip":[13,58,80],"motion":[14,59],"captured":[15],"in":[16,88,148,160],"video.":[17],"Current":[18],"mainstream":[19,92],"approaches":[21],"only":[22],"use":[23],"single":[25,34],"visual":[26,75,106],"encoder":[27],"model":[29],"input":[30],"videos":[31],"of":[32,66,115],"scale.":[35],"In":[36,108],"this":[37],"paper,":[38],"we":[39,52,96,111],"propose":[40,71],"enhance":[42],"by":[44,131],"incorporating":[45],"multi-scale":[46,57],"video":[47,117],"data":[48,118],"and":[49,70,94,103,120,126],"multi-encoder.":[50],"Specifically,":[51],"first":[53],"introduce":[54],"novel":[56],"extraction":[60],"algorithm":[61],"based":[62],"on":[63,122,170],"the":[64,67,86,91,99,109,113,128,149,167,171],"size":[65],"face":[69],"an":[72],"Enhanced":[73],"ResNet3D":[74],"front-end":[76],"(VFE)":[77],"extract":[79],"features":[81],"at":[82],"different":[83,116],"scales.":[84],"For":[85],"multi-encoder,":[87],"addition":[89],"Transformer":[93],"Conformer,":[95],"also":[97],"incorporate":[98],"recently":[100],"proposed":[101,144],"Branch-former":[102],"E-Branchformer":[104],"as":[105],"encoders.":[107],"experiments,":[110],"explore":[112],"influence":[114],"scales":[119],"encoders":[121],"ALR":[123,133],"system":[124],"performance":[125],"fuse":[127],"texts":[129],"transcribed":[130],"all":[132],"systems":[134],"using":[135],"recognizer":[136],"output":[137],"voting":[138],"error":[139,162],"reduction":[140,159],"(ROVER).":[141],"Finally,":[142],"our":[143],"approach":[145],"placed":[146],"second":[147],"ICME":[150],"2024":[151],"ChatCLR":[152],"Challenge":[153],"Task":[154],"2,":[155],"with":[156],"21.52%":[158],"character":[161],"rate":[163],"(CER)":[164],"compared":[165],"official":[168],"baseline":[169],"evaluation":[172],"set.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}