{"id":"https://openalex.org/W4408346039","doi":"https://doi.org/10.1109/icassp49660.2025.10889163","title":"LipGen: Viseme-Guided Lip Video Generation for Enhancing Visual Speech Recognition","display_name":"LipGen: Viseme-Guided Lip Video Generation for Enhancing Visual Speech Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408346039","doi":"https://doi.org/10.1109/icassp49660.2025.10889163"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889163","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889163","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5114618273","display_name":"Bowen Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bowen Hao","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044235518","display_name":"Dongliang Zhou","orcid":"https://orcid.org/0009-0006-8609-4555"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongliang Zhou","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100428852","display_name":"Xiaojie Li","orcid":"https://orcid.org/0000-0002-6666-9888"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojie Li","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100432030","display_name":"Xingyu Zhang","orcid":"https://orcid.org/0000-0001-6053-0191"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingyu Zhang","raw_affiliation_strings":["National Institute of Defense Technology Innovation,Academy of Military Sciences,Beijing,China"],"affiliations":[{"raw_affiliation_string":"National Institute of Defense Technology Innovation,Academy of Military Sciences,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101460488","display_name":"Liang Xie","orcid":"https://orcid.org/0000-0003-1718-7556"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang Xie","raw_affiliation_strings":["National Institute of Defense Technology Innovation,Academy of Military Sciences,Beijing,China"],"affiliations":[{"raw_affiliation_string":"National Institute of Defense Technology Innovation,Academy of Military Sciences,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100654190","display_name":"Jianlong Wu","orcid":"https://orcid.org/0000-0003-0247-5221"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianlong Wu","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071229482","display_name":"Erwei Yin","orcid":"https://orcid.org/0000-0002-2147-9888"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erwei Yin","raw_affiliation_strings":["National Institute of Defense Technology Innovation,Academy of Military Sciences,Beijing,China"],"affiliations":[{"raw_affiliation_string":"National Institute of Defense Technology Innovation,Academy of Military Sciences,Beijing,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5114618273"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":11.019,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.98590304,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"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":0.9872000217437744,"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":0.9872000217437744,"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":0.9595000147819519,"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/viseme","display_name":"Viseme","score":0.9295966625213623},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7261453866958618},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5624363422393799},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38247793912887573},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.21541941165924072},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.13618004322052002}],"concepts":[{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.9295966625213623},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7261453866958618},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5624363422393799},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38247793912887573},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.21541941165924072},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.13618004322052002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889163","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889163","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W153185079","https://openalex.org/W2028778923","https://openalex.org/W2029199293","https://openalex.org/W2120974626","https://openalex.org/W2194775991","https://openalex.org/W2325939864","https://openalex.org/W2594690981","https://openalex.org/W2735529525","https://openalex.org/W2962770929","https://openalex.org/W2963528589","https://openalex.org/W2963654155","https://openalex.org/W3015689952","https://openalex.org/W3016011581","https://openalex.org/W3034552680","https://openalex.org/W3119418740","https://openalex.org/W3162707322","https://openalex.org/W3163064317","https://openalex.org/W3192931333","https://openalex.org/W4225299282","https://openalex.org/W4285120484","https://openalex.org/W4295906307","https://openalex.org/W4321009928","https://openalex.org/W4372346152","https://openalex.org/W4392902916","https://openalex.org/W4392903590","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6785851975","https://openalex.org/W6850737308","https://openalex.org/W6862939797","https://openalex.org/W7011482893"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W1974357398","https://openalex.org/W2116497041","https://openalex.org/W2591964346","https://openalex.org/W131634123","https://openalex.org/W2757496505","https://openalex.org/W1560013842","https://openalex.org/W1530111162"],"abstract_inverted_index":{"Visual":[0],"speech":[1],"recognition":[2],"(VSR),":[3],"commonly":[4],"known":[5],"as":[6],"lip":[7,36,53,147],"reading,":[8],"has":[9],"garnered":[10],"significant":[11],"attention":[12,110],"due":[13],"to":[14,64,82,141],"its":[15],"wide-ranging":[16],"practical":[17],"applications.":[18],"The":[19],"advent":[20],"of":[21,35,96,118,129],"deep":[22],"learning":[23],"techniques":[24],"and":[25,154],"advancements":[26],"in":[27,52,58,67,149],"hardware":[28],"capabilities":[29],"have":[30],"significantly":[31],"enhanced":[32],"the":[33,94,115,122,126,142,146,150],"performance":[34,139],"reading":[37,148],"models.":[38],"Despite":[39],"these":[40],"advancements,":[41],"existing":[42],"datasets":[43],"predominantly":[44],"feature":[45],"stable":[46],"video":[47],"recordings":[48],"with":[49],"limited":[50],"variability":[51],"movements.":[54],"This":[55,112],"limitation":[56],"results":[57],"models":[59],"that":[60,105],"are":[61],"highly":[62],"sensitive":[63],"variations":[65],"encountered":[66],"real-world":[68],"scenarios.":[69],"To":[70],"address":[71],"this":[72],"issue,":[73],"we":[74,100],"propose":[75],"a":[76],"novel":[77],"framework,":[78],"LipGen,":[79],"which":[80],"aims":[81],"improve":[83],"model":[84],"robustness":[85],"by":[86],"leveraging":[87],"speech-driven":[88],"synthetic":[89],"visual":[90],"data,":[91],"thereby":[92,131],"mitigating":[93],"constraints":[95],"current":[97,143],"datasets.":[98],"Additionally,":[99],"introduce":[101],"an":[102],"auxiliary":[103],"task":[104],"incorporates":[106],"viseme":[107],"classification":[108],"alongside":[109],"mechanisms.":[111],"approach":[113],"facilitates":[114],"efficient":[116],"integration":[117],"temporal":[119],"information,":[120],"directing":[121],"model\u2019s":[123],"focus":[124],"toward":[125],"relevant":[127],"segments":[128],"speech,":[130],"enhancing":[132],"discriminative":[133],"capabilities.":[134],"Our":[135],"method":[136],"demonstrates":[137],"superior":[138],"compared":[140],"state-of-the-art":[144],"on":[145],"wild":[151],"(LRW)":[152],"dataset":[153],"exhibits":[155],"even":[156],"more":[157],"pronounced":[158],"advantages":[159],"under":[160],"challenging":[161],"conditions.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}