{"id":"https://openalex.org/W4412939594","doi":"https://doi.org/10.1109/tcss.2025.3586845","title":"CFLip: Generalizing Lipreading to Unseen Speakers by Learning Common Features","display_name":"CFLip: Generalizing Lipreading to Unseen Speakers by Learning Common Features","publication_year":2025,"publication_date":"2025-08-04","ids":{"openalex":"https://openalex.org/W4412939594","doi":"https://doi.org/10.1109/tcss.2025.3586845"},"language":"en","primary_location":{"id":"doi:10.1109/tcss.2025.3586845","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcss.2025.3586845","pdf_url":null,"source":{"id":"https://openalex.org/S2490693980","display_name":"IEEE Transactions on Computational Social Systems","issn_l":"2329-924X","issn":["2329-924X","2373-7476"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computational Social Systems","raw_type":"journal-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/A5101856018","display_name":"Li Yu","orcid":"https://orcid.org/0000-0002-4654-2089"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yu Li","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-4654-2089","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081427161","display_name":"Feng Xue","orcid":"https://orcid.org/0000-0003-4962-9734"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Xue","raw_affiliation_strings":["Key Laboratory of Knowledge Engineering with Big Data of Ministry of Education, the Intelligent Interconnected Systems Laboratory of Anhui Province, and the School of Software, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-4962-9734","affiliations":[{"raw_affiliation_string":"Key Laboratory of Knowledge Engineering with Big Data of Ministry of Education, the Intelligent Interconnected Systems Laboratory of Anhui Province, and the School of Software, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059530979","display_name":"Dan Guo","orcid":"https://orcid.org/0000-0003-2594-254X"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Guo","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-2594-254X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076104260","display_name":"Shengeng Tang","orcid":"https://orcid.org/0000-0001-6313-2543"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengeng Tang","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-6313-2543","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102359660","display_name":"Peng Li","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Li","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0000-4398-5362","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100728145","display_name":"Shujie Li","orcid":"https://orcid.org/0000-0002-6525-2706"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shujie Li","raw_affiliation_strings":["School of Software, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-6525-2706","affiliations":[{"raw_affiliation_string":"School of Software, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051332325","display_name":"Richang Hong","orcid":"https://orcid.org/0000-0001-5461-3986"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Richang Hong","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-5461-3986","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101856018"],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":2.1733,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89727614,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"13","issue":"1","first_page":"180","last_page":"195"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9941999912261963,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9941999912261963,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9929999709129333,"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/T12031","display_name":"Speech and dialogue systems","score":0.9811000227928162,"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":0.5090674757957458},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4960819184780121},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35682544112205505},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3353491425514221},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.32805582880973816},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2777636647224426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5090674757957458},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4960819184780121},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35682544112205505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3353491425514221},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.32805582880973816},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2777636647224426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcss.2025.3586845","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcss.2025.3586845","pdf_url":null,"source":{"id":"https://openalex.org/S2490693980","display_name":"IEEE Transactions on Computational Social Systems","issn_l":"2329-924X","issn":["2329-924X","2373-7476"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computational Social Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G3948531644","display_name":null,"funder_award_id":"U24A20332","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5571440487","display_name":null,"funder_award_id":"62272143","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W1919971835","https://openalex.org/W1994616650","https://openalex.org/W2015143272","https://openalex.org/W2033895145","https://openalex.org/W2086541583","https://openalex.org/W2127141656","https://openalex.org/W2157331557","https://openalex.org/W2160815625","https://openalex.org/W2255466643","https://openalex.org/W2551572271","https://openalex.org/W2604379605","https://openalex.org/W2618530766","https://openalex.org/W2890952074","https://openalex.org/W2898859620","https://openalex.org/W2905426022","https://openalex.org/W2906502833","https://openalex.org/W2962778134","https://openalex.org/W2963030892","https://openalex.org/W2963076818","https://openalex.org/W2963173190","https://openalex.org/W2972775954","https://openalex.org/W2996970093","https://openalex.org/W2999528291","https://openalex.org/W3001079424","https://openalex.org/W3006974783","https://openalex.org/W3007589762","https://openalex.org/W3015830103","https://openalex.org/W3016011581","https://openalex.org/W3035042697","https://openalex.org/W3036415234","https://openalex.org/W3080253586","https://openalex.org/W3131096279","https://openalex.org/W3162707322","https://openalex.org/W3167917117","https://openalex.org/W3204447181","https://openalex.org/W3206248339","https://openalex.org/W4210623456","https://openalex.org/W4220663529","https://openalex.org/W4221141813","https://openalex.org/W4224319127","https://openalex.org/W4295308310","https://openalex.org/W4302029223","https://openalex.org/W4304014341","https://openalex.org/W4312638101","https://openalex.org/W4312975593","https://openalex.org/W4319862233","https://openalex.org/W4361214501","https://openalex.org/W4378976162","https://openalex.org/W4379116955","https://openalex.org/W4385482982","https://openalex.org/W4385815549","https://openalex.org/W4386065999","https://openalex.org/W4389161308","https://openalex.org/W4391187671","https://openalex.org/W4392903857","https://openalex.org/W4396712810","https://openalex.org/W4396886564","https://openalex.org/W4397026515","https://openalex.org/W4399452222","https://openalex.org/W4399555970","https://openalex.org/W4400071971","https://openalex.org/W4402353462","https://openalex.org/W4403635980","https://openalex.org/W4403722234","https://openalex.org/W4404238471","https://openalex.org/W4405386671"],"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/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Lipreading":[0],"refers":[1],"to":[2,22,54,102,113,120,139,155,183,217],"translating":[3],"the":[4,40,49,55,62,65,69,75,80,97,104,189,192,198,211],"lip":[5,41],"movements":[6,42],"observed":[7],"in":[8,48,64,79,170],"a":[9,12,19,128,180],"video":[10,146,176],"of":[11,32,43,61,71,82,117,194],"speaker":[13],"into":[14],"corresponding":[15],"textual":[16],"outputs,":[17],"providing":[18],"visual":[20,57,77],"alternative":[21],"auditory":[23],"communication":[24],"for":[25],"individuals":[26],"who":[27],"are":[28,89],"deaf":[29],"or":[30],"hard":[31],"hearing.":[33],"Existing":[34],"lipreading":[35,72,118,130],"methods":[36],"typically":[37],"independently":[38],"learn":[39,103,184],"each":[44],"speaker.":[45],"This":[46],"results":[47],"model":[50,119],"being":[51],"highly":[52],"sensitive":[53],"individual":[56],"features":[58,93,107,143,193],"(lip":[59],"color/shape)":[60],"speakers":[63,165,196],"training":[66],"set,":[67],"hindering":[68],"generalization":[70,116],"models.":[73],"Despite":[74],"obvious":[76],"variations":[78],"lips":[81],"different":[83,109,164,195],"speakers,":[84,110],"we":[85,126,149,178],"claim":[86],"that":[87,159,210],"there":[88],"still":[90],"inherent":[91],"common":[92,105,141],"when":[94],"they":[95],"pronounce":[96],"same":[98,199],"phoneme.":[99],"We":[100],"attempt":[101],"pronunciation":[106,142],"across":[108],"so":[111],"as":[112],"achieve":[114],"better":[115],"unseen":[121,218],"speakers.":[122,219],"In":[123],"this":[124],"article,":[125],"propose":[127],"sentence-level":[129],"framework":[131],"based":[132],"on":[133,206],"Learning":[134],"Common":[135],"Features":[136],"(CFLip),":[137],"designed":[138,179],"extract":[140],"from":[144],"<real-pseudo>":[145,175],"pairs.":[147],"Specifically,":[148],"first":[150],"employ":[151],"data":[152],"augmentation":[153],"strategy":[154],"generate":[156],"pseudo":[157],"videos":[158],"share":[160],"labels":[161],"but":[162],"with":[163],"by":[166,187],"replacing":[167],"frame":[168],"segments":[169],"real":[171],"videos.":[172],"With":[173],"these":[174],"pairs,":[177],"dual-stream":[181],"network":[182],"commonality":[185],"feature":[186],"minimized":[188],"distance":[190],"between":[191],"pronouncing":[197],"words":[200],"via":[201],"Generalization":[202],"Loss.":[203],"Extensive":[204],"experiments":[205],"benchmark":[207],"datasets":[208],"demonstrate":[209],"proposed":[212],"CFLip":[213],"can":[214],"effectively":[215],"generalize":[216]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}