{"id":"https://openalex.org/W4415707152","doi":"https://doi.org/10.1109/lsp.2025.3627133","title":"Lipvis: A Novel Transient Viseme Extraction Framework for Lip Reading","display_name":"Lipvis: A Novel Transient Viseme Extraction Framework for Lip Reading","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4415707152","doi":"https://doi.org/10.1109/lsp.2025.3627133"},"language":null,"primary_location":{"id":"doi:10.1109/lsp.2025.3627133","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3627133","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","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":null,"display_name":"Hao Yuan","orcid":"https://orcid.org/0009-0005-3038-4679"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["CN","US"],"is_corresponding":true,"raw_author_name":"Hao Yuan","raw_affiliation_strings":["School of Advanced Manufacturing and Robotics, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Advanced Manufacturing and Robotics, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100647278","display_name":"Yakun Zhang","orcid":"https://orcid.org/0000-0001-5829-1371"},"institutions":[{"id":"https://openalex.org/I2802541053","display_name":"Academy of Military Medical Sciences","ror":"https://ror.org/02bv3c993","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802541053"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yakun Zhang","raw_affiliation_strings":["Defense Innovation Institute, Academy of Military Sciences (AMS), Beijing, China"],"affiliations":[{"raw_affiliation_string":"Defense Innovation Institute, Academy of Military Sciences (AMS), Beijing, China","institution_ids":["https://openalex.org/I2802541053"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100432041","display_name":"Xingyu Zhang","orcid":"https://orcid.org/0000-0003-4108-9817"},"institutions":[{"id":"https://openalex.org/I2802541053","display_name":"Academy of Military Medical Sciences","ror":"https://ror.org/02bv3c993","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802541053"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingyu Zhang","raw_affiliation_strings":["Defense Innovation Institute, Academy of Military Sciences (AMS), Beijing, China"],"affiliations":[{"raw_affiliation_string":"Defense Innovation Institute, Academy of Military Sciences (AMS), Beijing, China","institution_ids":["https://openalex.org/I2802541053"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009285282","display_name":"Liang Xie","orcid":"https://orcid.org/0000-0002-8286-6785"},"institutions":[{"id":"https://openalex.org/I2802541053","display_name":"Academy of Military Medical Sciences","ror":"https://ror.org/02bv3c993","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802541053"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Xie","raw_affiliation_strings":["Defense Innovation Institute, Academy of Military Sciences (AMS), Beijing, China"],"affiliations":[{"raw_affiliation_string":"Defense Innovation Institute, Academy of Military Sciences (AMS), Beijing, China","institution_ids":["https://openalex.org/I2802541053"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071229482","display_name":"Erwei Yin","orcid":"https://orcid.org/0000-0002-2147-9888"},"institutions":[{"id":"https://openalex.org/I2802541053","display_name":"Academy of Military Medical Sciences","ror":"https://ror.org/02bv3c993","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802541053"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Erwei Yin","raw_affiliation_strings":["Defense Innovation Institute, Academy of Military Sciences (AMS), Beijing, China"],"affiliations":[{"raw_affiliation_string":"Defense Innovation Institute, Academy of Military Sciences (AMS), Beijing, China","institution_ids":["https://openalex.org/I2802541053"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4210116723"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3914026,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"4334","last_page":"4338"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9686999917030334,"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":0.9686999917030334,"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":0.00839999970048666,"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"}},{"id":"https://openalex.org/T12301","display_name":"Facial Nerve Paralysis Treatment and Research","score":0.002199999988079071,"subfield":{"id":"https://openalex.org/subfields/2728","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.7770000100135803},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.57669997215271},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5139999985694885},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5110999941825867},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5059000253677368},{"id":"https://openalex.org/keywords/transient","display_name":"Transient (computer programming)","score":0.5058000087738037},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.3944999873638153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7964000105857849},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.7770000100135803},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.57669997215271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5716999769210815},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5396000146865845},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5139999985694885},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5110999941825867},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5059000253677368},{"id":"https://openalex.org/C2780799671","wikidata":"https://www.wikidata.org/wiki/Q17087362","display_name":"Transient (computer programming)","level":2,"score":0.5058000087738037},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.3944999873638153},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.33309999108314514},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C90734943","wikidata":"https://www.wikidata.org/wiki/Q17008777","display_name":"Conceptualization","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2700999975204468},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25600001215934753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2025.3627133","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3627133","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5931773243","display_name":null,"funder_award_id":"62332019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6231997530","display_name":null,"funder_award_id":"20240484513","funder_id":"https://openalex.org/F4320334978","funder_display_name":"Beijing Nova Program"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1578725541","https://openalex.org/W2015143272","https://openalex.org/W2121486117","https://openalex.org/W2136155248","https://openalex.org/W2136813256","https://openalex.org/W2365880764","https://openalex.org/W2551572271","https://openalex.org/W2594690981","https://openalex.org/W2741151796","https://openalex.org/W2890952074","https://openalex.org/W2897846591","https://openalex.org/W2905426022","https://openalex.org/W2963030892","https://openalex.org/W2996970093","https://openalex.org/W2999528291","https://openalex.org/W3080253586","https://openalex.org/W3155765542","https://openalex.org/W3206248339","https://openalex.org/W4307286264","https://openalex.org/W4308238102","https://openalex.org/W4379116955","https://openalex.org/W4385571549","https://openalex.org/W4386158915","https://openalex.org/W4386160029","https://openalex.org/W4402112118","https://openalex.org/W4407097719"],"related_works":[],"abstract_inverted_index":{"The":[0],"accurate":[1],"extraction":[2,37,55,71],"of":[3,35,65,72,114,126,137],"visemes\u2014the":[4],"minimal":[5],"distinguishable":[6],"units":[7],"in":[8,61],"lip":[9,58,90,108],"reading\u2014lacks":[10],"a":[11,80,121,132,165],"systematic":[12],"solution.":[13],"Existing":[14],"methods":[15],"primarily":[16],"rely":[17],"on":[18,97,129,140],"audio":[19],"alignment":[20],"and":[21,29,100,131,144],"phoneme":[22],"mapping,":[23],"which":[24],"suffers":[25],"from":[26],"inconsistent":[27],"categorization":[28],"temporal":[30,77],"information":[31],"loss.":[32],"Suitable":[33],"evaluation":[34],"the":[36,45,52,62,112,146],"quality":[38],"also":[39],"remain":[40],"scarce.":[41],"This":[42],"work":[43],"bridges":[44],"research":[46],"gap":[47],"by":[48],"establishing":[49,164],"Lipvis":[50,68],"as":[51],"first":[53],"viseme":[54,117],"framework":[56],"for":[57,167],"reading,":[59,91],"grounded":[60],"novel":[63],"conceptualization":[64],"transient":[66,73,116],"visemes.":[67],"enables":[69],"audio-independent":[70],"visemes":[74,84],"with":[75],"preserved":[76],"dynamics":[78],"via":[79],"multi-stage":[81],"pipeline.":[82],"These":[83,153],"are":[85],"subsequently":[86],"annotated":[87],"to":[88,159],"assist":[89],"validating":[92],"their":[93],"incremental":[94],"utility.":[95],"Experiments":[96],"both":[98],"Chinese":[99],"English":[101],"datasets":[102],"demonstrate":[103,156],"that":[104],"our":[105],"method":[106],"enhances":[107],"reading":[109],"performance":[110,148],"through":[111],"incorporation":[113],"fine-grained":[115],"knowledge.":[118],"It":[119],"achieves":[120],"word":[122],"error":[123,134],"rate":[124,135],"(WER)":[125],"1.02":[127],"%":[128,139],"GRID":[130],"character":[133],"(CER)":[136],"20.93":[138],"CMLR,":[141],"outperforming":[142],"baselines":[143],"marking":[145],"best-known":[147],"under":[149],"identical":[150],"experimental":[151],"conditions.":[152],"compelling":[154],"results":[155],"Lipvis's":[157],"capability":[158],"extract":[160],"high-quality,":[161],"task-relevant":[162],"visemes,":[163],"foundation":[166],"advancing":[168],"viseme-based":[169],"lipreading":[170],"research.":[171]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-30T00:00:00"}