{"id":"https://openalex.org/W4210588066","doi":"https://doi.org/10.1109/asru51503.2021.9688240","title":"DeepLip: A Benchmark for Deep Learning-Based Audio-Visual Lip Biometrics","display_name":"DeepLip: A Benchmark for Deep Learning-Based Audio-Visual Lip Biometrics","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4210588066","doi":"https://doi.org/10.1109/asru51503.2021.9688240"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688240","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688240","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5100457438","display_name":"Meng Liu","orcid":"https://orcid.org/0000-0002-1582-5764"},"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":true,"raw_author_name":"Meng Liu","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University,China","College of Intelligence and Computing, Tianjin University, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University,China","institution_ids":["https://openalex.org/I162868743"]},{"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/A5101745213","display_name":"Longbiao Wang","orcid":"https://orcid.org/0000-0002-8094-6861"},"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":"Longbiao Wang","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University,China","College of Intelligence and Computing, Tianjin University, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University,China","institution_ids":["https://openalex.org/I162868743"]},{"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/A5004287909","display_name":"Kong Aik Lee","orcid":"https://orcid.org/0000-0001-9133-3000"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kong Aik Lee","raw_affiliation_strings":["Institute for Infocomm Research, A&#x002A;STAR,Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, A&#x002A;STAR,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041985945","display_name":"Hanyi Zhang","orcid":"https://orcid.org/0000-0003-0109-6481"},"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":"Hanyi Zhang","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University,China","College of Intelligence and Computing, Tianjin University, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University,China","institution_ids":["https://openalex.org/I162868743"]},{"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/A5100654128","display_name":"Chang Zeng","orcid":"https://orcid.org/0000-0002-4882-1823"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chang Zeng","raw_affiliation_strings":["National Institute of Informatics,Tokyo,Japan","National Institute of Informatics, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Tokyo,Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017251198","display_name":"Jianwu Dang","orcid":"https://orcid.org/0000-0002-9237-4821"},"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":"Jianwu Dang","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University,China","College of Intelligence and Computing, Tianjin University, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100457438"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":0.3441,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.59435863,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"37","issue":null,"first_page":"122","last_page":"129"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T11309","display_name":"Music and Audio Processing","score":0.9959999918937683,"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":0.9861999750137329,"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/computer-science","display_name":"Computer science","score":0.742687463760376},{"id":"https://openalex.org/keywords/biometrics","display_name":"Biometrics","score":0.7170201539993286},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6510409712791443},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6217842698097229},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5552552938461304},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5532110929489136},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5257963538169861},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45381611585617065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.742687463760376},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.7170201539993286},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6510409712791443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6217842698097229},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5552552938461304},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5532110929489136},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5257963538169861},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45381611585617065},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9688240","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688240","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7599999904632568}],"awards":[{"id":"https://openalex.org/G5633359880","display_name":null,"funder_award_id":"61771333","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8651560819","display_name":null,"funder_award_id":"2018YFB1305200","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1664547674","https://openalex.org/W1915742967","https://openalex.org/W1974783905","https://openalex.org/W2015143272","https://openalex.org/W2029199293","https://openalex.org/W2053365209","https://openalex.org/W2099731107","https://openalex.org/W2143231843","https://openalex.org/W2168285300","https://openalex.org/W2398406965","https://openalex.org/W2748488820","https://openalex.org/W2808631503","https://openalex.org/W2810311710","https://openalex.org/W2891205112","https://openalex.org/W2897492880","https://openalex.org/W2911233953","https://openalex.org/W2932691488","https://openalex.org/W2938358845","https://openalex.org/W2963356069","https://openalex.org/W2963658982","https://openalex.org/W2972986505","https://openalex.org/W2977115923","https://openalex.org/W2985076077","https://openalex.org/W3001079424","https://openalex.org/W3016011581","https://openalex.org/W3024869864","https://openalex.org/W3026006730","https://openalex.org/W3095191006","https://openalex.org/W3097741049","https://openalex.org/W3113824005","https://openalex.org/W3126757411","https://openalex.org/W3136499730","https://openalex.org/W3162707322","https://openalex.org/W3163527109","https://openalex.org/W4288091954","https://openalex.org/W4289665794","https://openalex.org/W4298112588","https://openalex.org/W6732872814","https://openalex.org/W6734491695","https://openalex.org/W6742376216","https://openalex.org/W6754420807","https://openalex.org/W6769178842","https://openalex.org/W6781925879","https://openalex.org/W6785102699"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2076845124","https://openalex.org/W2183964146","https://openalex.org/W4321353415","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3193565141","https://openalex.org/W3133861977","https://openalex.org/W3167935049","https://openalex.org/W3029198973"],"abstract_inverted_index":{"Audio-visual":[0],"lip":[1],"biometrics":[2,8],"(AV-LB)":[3],"has":[4,44,101],"been":[5,45],"an":[6,176],"emerging":[7],"technology":[9],"that":[10,154],"straddles":[11],"auditory":[12],"and":[13,48,55,142,146,164,182],"visual":[14],"speech":[15,56],"processing.":[16],"Previous":[17],"works":[18],"mainly":[19],"focused":[20],"on":[21,75,88,184],"the":[22,35,60,81,89,93,99,157,185],"front-end":[23],"lip-based":[24],"feature":[25],"engineering":[26],"combined":[27],"with":[28,139,171,175],"a":[29,63,70,112,124,147],"shallow":[30],"statistical":[31],"back-end":[32],"model.":[33],"Over":[34],"past":[36],"decade,":[37],"convolutional":[38,140],"neural":[39],"network":[40],"(CNN,":[41],"or":[42],"ConvNet)":[43],"widely":[46],"used":[47],"achieved":[49],"good":[50],"performance":[51],"in":[52,72,161],"computer":[53],"vision":[54],"processing":[57],"tasks.":[58,77],"However,":[59],"lack":[61],"of":[62,95,104,180],"sizeable":[64],"public":[65,117],"AV-LB":[66,76,127],"database":[67,114],"led":[68],"to":[69,80,102],"stagnation":[71],"deep-learning":[73],"exploration":[74],"In":[78],"addition":[79],"dual":[82],"audio-visual":[83],"streams,":[84],"one":[85],"essential":[86],"requirement":[87],"video":[90,141],"stream":[91],"is":[92],"region":[94],"interest":[96],"(ROI)":[97],"around":[98],"lips":[100],"be":[103],"sufficient":[105],"resolution.":[106],"To":[107],"this":[108,120],"end,":[109],"we":[110,122],"compile":[111],"moderate-size":[113],"using":[115],"existing":[116],"databases.":[118],"Using":[119],"database,":[121],"present":[123],"deep":[125],"learning-based":[126],"benchmark,":[128],"dubbed":[129],"DeepLip":[130,155],"<sup":[131,134],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[132,135],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[133,136],"https://github.com/DanielMengLiu/DeepLip,":[137],"realized":[138],"audio":[143],"unimodal":[144,173],"modules,":[145],"multimodal":[148],"fusion":[149],"module.":[150],"Our":[151],"experiments":[152],"show":[153],"outperforms":[156],"traditional":[158],"lip-biometrics":[159],"system":[160],"context":[162],"modeling":[163],"achieves":[165],"over":[166],"50%":[167],"relative":[168],"improvements":[169],"compared":[170],"its":[172],"system,":[174],"equal":[177],"error":[178],"rate":[179],"0.75%":[181],"1.11%":[183],"test":[186],"datasets,":[187],"respectively.":[188]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}