{"id":"https://openalex.org/W3157951503","doi":"https://doi.org/10.1109/icpr48806.2021.9413218","title":"Three-Dimensional Lip Motion Network for Text-Independent Speaker Recognition","display_name":"Three-Dimensional Lip Motion Network for Text-Independent Speaker Recognition","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3157951503","doi":"https://doi.org/10.1109/icpr48806.2021.9413218","mag":"3157951503"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9413218","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9413218","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","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/A5102003658","display_name":"Jianrong Wang","orcid":"https://orcid.org/0000-0002-8980-1634"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianrong Wang","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101847139","display_name":"Tong Wu","orcid":"https://orcid.org/0000-0001-5557-0623"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Wu","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078297565","display_name":"Shanyu Wang","orcid":"https://orcid.org/0000-0002-9366-1144"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanyu Wang","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027142928","display_name":"Mei Yu","orcid":"https://orcid.org/0000-0002-5169-4829"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mei Yu","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101779069","display_name":"Qiang Fang","orcid":"https://orcid.org/0000-0002-6548-980X"},"institutions":[{"id":"https://openalex.org/I114218197","display_name":"Chinese Academy of Social Sciences","ror":"https://ror.org/05bxbmy32","country_code":"CN","type":"facility","lineage":["https://openalex.org/I114218197"]},{"id":"https://openalex.org/I4210121707","display_name":"Institute of Linguistics","ror":"https://ror.org/02mrea437","country_code":"CN","type":"facility","lineage":["https://openalex.org/I114218197","https://openalex.org/I4210121707"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Fang","raw_affiliation_strings":["Institute of Linguistics, Chinese Academy of Social Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Linguistics, Chinese Academy of Social Sciences, China","institution_ids":["https://openalex.org/I114218197","https://openalex.org/I4210121707"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100620206","display_name":"Ju Zhang","orcid":"https://orcid.org/0000-0002-0378-6497"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ju Zhang","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100418818","display_name":"Li Liu","orcid":"https://orcid.org/0000-0002-4497-0135"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Liu","raw_affiliation_strings":["Shenzhen Research Institute of Big Data, The chinese university of hong kong shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, The chinese university of hong kong shenzhen, China","institution_ids":["https://openalex.org/I4210099586","https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3380","last_page":"3387"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.996999979019165,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9840999841690063,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7910522222518921},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5940426588058472},{"id":"https://openalex.org/keywords/biometrics","display_name":"Biometrics","score":0.5762080550193787},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5656921863555908},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5634835362434387},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5320903658866882},{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.5199588537216187},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5081806182861328},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5058786273002625},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47092074155807495},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45907139778137207},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3538223206996918}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7910522222518921},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5940426588058472},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.5762080550193787},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5656921863555908},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5634835362434387},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5320903658866882},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.5199588537216187},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5081806182861328},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5058786273002625},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47092074155807495},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45907139778137207},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3538223206996918},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr48806.2021.9413218","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9413218","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1570254061","https://openalex.org/W1575423098","https://openalex.org/W1686810756","https://openalex.org/W1994481804","https://openalex.org/W1996575884","https://openalex.org/W2037002527","https://openalex.org/W2053365209","https://openalex.org/W2064675550","https://openalex.org/W2093942149","https://openalex.org/W2100899763","https://openalex.org/W2112026651","https://openalex.org/W2131670212","https://openalex.org/W2161361444","https://openalex.org/W2194775991","https://openalex.org/W2307299445","https://openalex.org/W2508015696","https://openalex.org/W2509549781","https://openalex.org/W2517322077","https://openalex.org/W2594830998","https://openalex.org/W2608169513","https://openalex.org/W2734704977","https://openalex.org/W2743103362","https://openalex.org/W2760932242","https://openalex.org/W2778635523","https://openalex.org/W2783706016","https://openalex.org/W2796191958","https://openalex.org/W2810912318","https://openalex.org/W2888888638","https://openalex.org/W2891874376","https://openalex.org/W2911260807","https://openalex.org/W2914969757","https://openalex.org/W2946602381","https://openalex.org/W2975779505","https://openalex.org/W2979898924","https://openalex.org/W2984189102","https://openalex.org/W6634505398","https://openalex.org/W6637373629","https://openalex.org/W6675020145","https://openalex.org/W6680111399","https://openalex.org/W6734968509"],"related_works":["https://openalex.org/W2056853153","https://openalex.org/W2057559274","https://openalex.org/W2026924879","https://openalex.org/W2005087563","https://openalex.org/W2378111931","https://openalex.org/W2052388267","https://openalex.org/W2950647290","https://openalex.org/W1968481813","https://openalex.org/W2620829895","https://openalex.org/W2356918560"],"abstract_inverted_index":{"Lip":[0],"motion":[1,61,70,102],"reflects":[2],"behavior":[3],"characteristics":[4],"of":[5,16,25,100,185],"speakers,":[6],"and":[7,79,110,129,142,167,169],"thus":[8],"can":[9],"be":[10],"used":[11,27],"as":[12,177,179],"a":[13,36,56,117],"new":[14,83],"kind":[15],"biometrics":[17],"in":[18,35,51,75,93],"speaker":[19,34],"recognition.":[20],"In":[21],"the":[22,66,77,135,161,171,180],"literature,":[23],"lots":[24],"works":[26],"two-dimensional":[28],"(2D)":[29],"lip":[30,41,60,69,95,101,175],"images":[31],"to":[32,72,90,105,115,133,160],"recognize":[33,73],"text-dependent":[37,80],"context.":[38],"However,":[39],"2D":[40,174],"easily":[42],"suffers":[43],"from":[44],"various":[45],"face":[46,130],"orientations.":[47],"To":[48],"this":[49,52,151,186],"end,":[50],"work,":[53],"we":[54,122],"present":[55,123],"novel":[57],"end-to-end":[58],"3D":[59,68,181],"Network":[62],"(3LMNet)":[63],"by":[64],"utilizing":[65],"sentence-level":[67],"(S3DLM)":[71],"speakers":[74,141],"both":[76],"text-independent":[78],"contexts.":[81],"A":[82],"regional":[84],"feedback":[85],"module":[86],"(RFM)":[87],"is":[88,103,158,188],"proposed":[89,156],"obtain":[91],"attentions":[92],"different":[94],"regions.":[96],"Besides,":[97],"prior":[98],"knowledge":[99],"investigated":[104],"complement":[106],"RFM,":[107],"where":[108],"landmark-level":[109],"frame-level":[111],"features":[112],"are":[113],"merged":[114],"form":[116],"better":[118],"feature":[119],"representation.":[120],"Moreover,":[121],"two":[124],"methods,":[125],"i.e.,":[126,164],"coordinate":[127],"transformation":[128],"posture":[131],"correction":[132],"pre-process":[134],"LSD-AV":[136],"dataset,":[137],"which":[138],"contains":[139],"68":[140],"146":[143],"sentences":[144],"per":[145],"speaker.":[146],"The":[147,183],"evaluation":[148],"results":[149],"on":[150],"dataset":[152],"demonstrate":[153],"that":[154],"our":[155],"3LMNet":[157],"superior":[159],"baseline":[162],"models,":[163],"LSTM,":[165],"VGG-16":[166],"ResNet-34,":[168],"outperforms":[170],"state-of-the-art":[172],"using":[173],"image":[176],"well":[178],"face.":[182],"code":[184],"work":[187],"released":[189],"at":[190],"https://github.com/wutong18/Three-Dimensional-Lip-Motion-Network-for-Text-Independent-Speaker-Recognition.":[191]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
