{"id":"https://openalex.org/W3126757411","doi":"https://doi.org/10.1109/taslp.2021.3057230","title":"Audio-Visual Deep Neural Network for Robust Person Verification","display_name":"Audio-Visual Deep Neural Network for Robust Person Verification","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3126757411","doi":"https://doi.org/10.1109/taslp.2021.3057230","mag":"3126757411"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3057230","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3057230","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","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/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["SpeechLab, Department of Computer Science and Engineering and MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SpeechLab, Department of Computer Science and Engineering and MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101416769","display_name":"Zhengyang Chen","orcid":"https://orcid.org/0000-0003-1293-8146"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengyang Chen","raw_affiliation_strings":["SpeechLab, Department of Computer Science and Engineering and MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SpeechLab, Department of Computer Science and Engineering and MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100328340","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0003-1523-9631"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["SpeechLab, Department of Computer Science and Engineering and MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SpeechLab, Department of Computer Science and Engineering and MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":6.8869,"has_fulltext":false,"cited_by_count":60,"citation_normalized_percentile":{"value":0.97789671,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"29","issue":null,"first_page":"1079","last_page":"1092"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9983000159263611,"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/T11309","display_name":"Music and Audio Processing","score":0.996999979019165,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8110454678535461},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7968167066574097},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6099138259887695},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5680133700370789},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.55219966173172},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49474141001701355},{"id":"https://openalex.org/keywords/biometrics","display_name":"Biometrics","score":0.48031988739967346},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4376232922077179},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43196815252304077},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3908615708351135}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8110454678535461},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7968167066574097},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6099138259887695},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5680133700370789},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.55219966173172},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49474141001701355},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.48031988739967346},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4376232922077179},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43196815252304077},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3908615708351135},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2021.3057230","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3057230","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1899722019","display_name":"\u6df1\u5ea6\u5b66\u4e60\u8bed\u97f3\u8bc6\u522b\u4e2d\u7684\u5feb\u901f\u9ad8\u6548\u81ea\u9002\u5e94\u65b9\u6cd5\u7814\u7a76","funder_award_id":"62071288","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G257170","display_name":null,"funder_award_id":"U1736202","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W579245046","https://openalex.org/W1006777433","https://openalex.org/W1524333225","https://openalex.org/W1782590233","https://openalex.org/W1950843348","https://openalex.org/W1975056068","https://openalex.org/W1982048725","https://openalex.org/W1998808035","https://openalex.org/W2041823554","https://openalex.org/W2046056978","https://openalex.org/W2096733369","https://openalex.org/W2133564696","https://openalex.org/W2138621090","https://openalex.org/W2140609507","https://openalex.org/W2144172034","https://openalex.org/W2145287260","https://openalex.org/W2150769028","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2325939864","https://openalex.org/W2341528187","https://openalex.org/W2593116425","https://openalex.org/W2618530766","https://openalex.org/W2726515241","https://openalex.org/W2747238065","https://openalex.org/W2748488820","https://openalex.org/W2752782242","https://openalex.org/W2799429369","https://openalex.org/W2808631503","https://openalex.org/W2890952074","https://openalex.org/W2890964092","https://openalex.org/W2897663715","https://openalex.org/W2902299888","https://openalex.org/W2944613371","https://openalex.org/W2951529591","https://openalex.org/W2954996726","https://openalex.org/W2956925952","https://openalex.org/W2962918445","https://openalex.org/W2963383024","https://openalex.org/W2963420686","https://openalex.org/W2963528589","https://openalex.org/W2963654155","https://openalex.org/W2963887950","https://openalex.org/W2964171275","https://openalex.org/W2964308564","https://openalex.org/W2969985801","https://openalex.org/W3010925296","https://openalex.org/W3015445830","https://openalex.org/W3023258787","https://openalex.org/W3025804484","https://openalex.org/W3026006730","https://openalex.org/W3049278490","https://openalex.org/W3096936581","https://openalex.org/W3097450720","https://openalex.org/W3099206234","https://openalex.org/W3101998545","https://openalex.org/W3184648662","https://openalex.org/W4288091954","https://openalex.org/W4289665794","https://openalex.org/W6616781057","https://openalex.org/W6631362777","https://openalex.org/W6638046521","https://openalex.org/W6649863312","https://openalex.org/W6679434410","https://openalex.org/W6680902425","https://openalex.org/W6681239517","https://openalex.org/W6688816777","https://openalex.org/W6700903540","https://openalex.org/W6733328719","https://openalex.org/W6769178842","https://openalex.org/W6776889011"],"related_works":["https://openalex.org/W2076845124","https://openalex.org/W2183964146","https://openalex.org/W2379932303","https://openalex.org/W2095239294","https://openalex.org/W3147744369","https://openalex.org/W2062586268","https://openalex.org/W2019582947","https://openalex.org/W3212688212","https://openalex.org/W2381300099","https://openalex.org/W3134175397"],"abstract_inverted_index":{"Voice":[0],"and":[1,16,40,77,124,143,164,171,178,224,238],"face":[2,17],"are":[3,157],"two":[4,32],"most":[5],"popular":[6],"biometrics":[7],"for":[8,55,111,122,136,203],"person":[9,42,56,204],"verification,":[10,57],"usually":[11],"used":[12],"in":[13,92],"speaker":[14],"verification":[15,18,43],"tasks.":[19],"It":[20],"has":[21],"already":[22],"been":[23],"observed":[24],"that":[25,228],"simply":[26],"combining":[27],"the":[28,51,89,141,154,160,167,172,182,194,208,211,220,229,235],"information":[29],"from":[30],"these":[31],"modalities":[33,99],"can":[34,100,150,232],"lead":[35],"to":[36,48,191],"a":[37,214],"more":[38],"powerful":[39],"robust":[41],"system.":[44],"In":[45],"this":[46,201,244],"article,":[47],"fully":[49],"explore":[50],"multi-modal":[52,117,146],"learning":[53,83],"strategies":[54,110],"we":[58,105],"proposed":[59,106,113,121,155,212,230],"three":[60,183],"types":[61],"of":[62,187,210],"audio-visual":[63],"deep":[64],"neural":[65],"network":[66],"(AVN),":[67],"including":[68],"feature":[69,142],"level":[70,74,79,145],"AVN":[71,75,84],"(AVN-F),":[72],"embedding":[73,78,144],"(AVN-E),":[76],"combination":[80],"with":[81,103,129],"joint":[82],"(AVN-J).":[85],"To":[86,206],"further":[87],"enhance":[88],"system":[90,174,198,231,236],"robustness":[91,209,237],"real":[93],"noisy":[94,215,245],"conditions":[95],"where":[96],"not":[97],"both":[98,140],"be":[101,151],"accessed":[102],"high-quality,":[104],"several":[107],"data":[108,118,127,147],"augmentation":[109,119,128,148],"each":[112],"AVN:":[114],"A":[115],"feature-level":[116],"is":[120,134,190,222],"AVN-F":[123],"an":[125],"embedding-level":[126],"novel":[130],"noise":[131],"distribution":[132],"matching":[133],"designed":[135],"AVN-E.":[137],"For":[138],"AVN-J,":[139],"methods":[149],"applied.":[152],"All":[153],"models":[156],"trained":[158],"on":[159,166,181,200,219],"VoxCeleb2":[161],"dev":[162],"dataset":[163],"evaluated":[165],"standard":[168],"VoxCeleb1":[169,221],"dataset,":[170],"best":[173,195],"achieves":[175],"0.558,":[176],"0.441%":[177],"0.793%":[179],"EER":[180],"official":[184],"trial":[185],"lists":[186],"VoxCeleb1,":[188],"which":[189],"our":[192],"knowledge":[193],"published":[196],"single":[197],"results":[199,226],"corpus":[202],"verification.":[205],"validate":[207],"approaches,":[213],"evaluation":[216],"set":[217],"based":[218],"constructed,":[223],"experimental":[225],"show":[227,240],"significantly":[233],"boost":[234],"still":[239],"promising":[241],"performance":[242],"under":[243],"scenario.":[246]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}