{"id":"https://openalex.org/W4413010306","doi":"https://doi.org/10.1109/fg61629.2025.11099112","title":"Lip Enhancement and Multi-View Simulation for Robust Visual Speech Recognition in MAVSR 2025","display_name":"Lip Enhancement and Multi-View Simulation for Robust Visual Speech Recognition in MAVSR 2025","publication_year":2025,"publication_date":"2025-05-26","ids":{"openalex":"https://openalex.org/W4413010306","doi":"https://doi.org/10.1109/fg61629.2025.11099112"},"language":"en","primary_location":{"id":"doi:10.1109/fg61629.2025.11099112","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg61629.2025.11099112","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 19th International Conference on Automatic Face and Gesture Recognition (FG)","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/A5052100570","display_name":"Fei Su","orcid":"https://orcid.org/0000-0002-3529-9845"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fei Su","raw_affiliation_strings":["Wuhan University,School of Computer Science,Wuhan,China,430072"],"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Computer Science,Wuhan,China,430072","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113355139","display_name":"Cancan Li","orcid":"https://orcid.org/0009-0002-2537-6293"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cancan Li","raw_affiliation_strings":["Wuhan University,School of Computer Science,Wuhan,China,430072"],"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Computer Science,Wuhan,China,430072","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100446344","display_name":"Juan Liu","orcid":"https://orcid.org/0000-0003-4963-6694"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juan Liu","raw_affiliation_strings":["Wuhan University,School of Artificial Intelligence,Wuhan,China,430072"],"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Artificial Intelligence,Wuhan,China,430072","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5052100570"],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28756415,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9944000244140625,"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":0.9944000244140625,"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":0.724302351474762},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6902065873146057},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5463748574256897},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3597177267074585},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.07565021514892578}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.724302351474762},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6902065873146057},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5463748574256897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3597177267074585},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.07565021514892578}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fg61629.2025.11099112","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg61629.2025.11099112","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 19th International Conference on Automatic Face and Gesture Recognition (FG)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1526392145","https://openalex.org/W1935685005","https://openalex.org/W2060510034","https://openalex.org/W2157190406","https://openalex.org/W2237250383","https://openalex.org/W2301937176","https://openalex.org/W2395106899","https://openalex.org/W2511073133","https://openalex.org/W2549228277","https://openalex.org/W2551572271","https://openalex.org/W2559085405","https://openalex.org/W2594690981","https://openalex.org/W2769666294","https://openalex.org/W2806833697","https://openalex.org/W2890952074","https://openalex.org/W2897492880","https://openalex.org/W2963528589","https://openalex.org/W2972756321","https://openalex.org/W3006974783","https://openalex.org/W3015689952","https://openalex.org/W3015830103","https://openalex.org/W3097777922","https://openalex.org/W3109585842","https://openalex.org/W3162293946","https://openalex.org/W3167917117","https://openalex.org/W3203407300","https://openalex.org/W3206835951","https://openalex.org/W4224940398","https://openalex.org/W4287887284","https://openalex.org/W4307286264","https://openalex.org/W4312578889","https://openalex.org/W4317039283","https://openalex.org/W4382202533","https://openalex.org/W4385767994","https://openalex.org/W4392904696","https://openalex.org/W4402775747","https://openalex.org/W6754420807","https://openalex.org/W6767264202","https://openalex.org/W6850737308","https://openalex.org/W6873764603"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,54],"present":[4],"our":[5],"work":[6],"for":[7],"Visual":[8],"Speech":[9,16],"Recognition":[10,17],"(VSR)":[11],"in":[12,135,145],"the":[13,82,99,102,113,126,131,146],"Mandarin":[14],"Audio-Visual":[15],"(MAVSR)":[18],"Challenge":[19],"2025,":[20],"with":[21],"a":[22,41,57],"particular":[23],"focus":[24],"on":[25,46,125],"improving":[26],"lipreading":[27],"under":[28,68,105],"challenging":[29],"visual":[30,50,58,66,107],"conditions.":[31,108],"The":[32,148],"proposed":[33,114],"system":[34,104,134],"leverages":[35],"cross-modal":[36],"knowledge":[37],"transfer":[38],"and":[39,49,76,92,138],"employs":[40],"progressive":[42],"training":[43],"strategy":[44],"based":[45],"large-scale":[47],"speech":[48,51],"datasets.":[52],"Furthermore,":[53],"introduce":[55],"LIPER,":[56],"enhancement":[59],"module":[60],"designed":[61],"to":[62,130],"generate":[63],"improved":[64],"lip-region":[65],"data":[67],"conditions":[69],"such":[70],"as":[71],"low":[72],"resolution,":[73],"poor":[74],"illumination,":[75],"color":[77],"distortion.":[78],"LIPER":[79],"further":[80],"facilitates":[81],"synthesis":[83],"of":[84,101,123],"multi-view":[85],"lip":[86,89],"movements":[87],"through":[88],"pose":[90],"estimation":[91],"3D":[93],"reconstruction.":[94],"These":[95],"enhancements":[96],"significantly":[97],"improve":[98],"robustness":[100],"VSR":[103],"low-quality":[106],"Experimental":[109],"results":[110],"show":[111],"that":[112],"approach":[115],"achieves":[116,139],"relative":[117],"character":[118],"error":[119],"rate":[120],"(CER)":[121],"reductions":[122],"16.1%":[124],"MOV20-Test":[127],"set,":[128],"compared":[129],"official":[132],"baseline":[133],"track":[136],"1,":[137],"second":[140],"place":[141],"among":[142],"submitted":[143],"systems":[144],"challenge.":[147],"code":[149],"is":[150],"available":[151],"at":[152],"https://github.com/yaku122/RVSR.":[153]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}