{"id":"https://openalex.org/W2902299888","doi":"https://doi.org/10.1109/icassp.2019.8683477","title":"Noise-tolerant Audio-visual Online Person Verification Using an Attention-based Neural Network Fusion","display_name":"Noise-tolerant Audio-visual Online Person Verification Using an Attention-based Neural Network Fusion","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2902299888","doi":"https://doi.org/10.1109/icassp.2019.8683477","mag":"2902299888"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5020263683","display_name":"Suwon Shon","orcid":null},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suwon Shon","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4405258931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078114111","display_name":"Tae-Hyun Oh","orcid":"https://orcid.org/0000-0003-0468-1571"},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tae-Hyun Oh","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4405258931"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Glass","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4405258931"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4405258931"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3995","last_page":"3999"},"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":0.9998000264167786,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9994999766349792,"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":0.7966974973678589},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.688291072845459},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6476541757583618},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5890138149261475},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5430303812026978},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.5056204795837402},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5023326873779297},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4376758635044098},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4121643304824829},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3940645456314087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7966974973678589},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.688291072845459},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6476541757583618},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5890138149261475},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5430303812026978},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5056204795837402},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5023326873779297},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4376758635044098},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4121643304824829},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3940645456314087},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W77253143","https://openalex.org/W1834627138","https://openalex.org/W2019370496","https://openalex.org/W2038262612","https://openalex.org/W2090575847","https://openalex.org/W2096733369","https://openalex.org/W2120945552","https://openalex.org/W2133564696","https://openalex.org/W2138377320","https://openalex.org/W2142393318","https://openalex.org/W2145962650","https://openalex.org/W2154383330","https://openalex.org/W2311038409","https://openalex.org/W2549238875","https://openalex.org/W2557135105","https://openalex.org/W2726515241","https://openalex.org/W2799429369","https://openalex.org/W2808631503","https://openalex.org/W2890704021","https://openalex.org/W2897663715","https://openalex.org/W2962918445","https://openalex.org/W2963342110","https://openalex.org/W2963654155","https://openalex.org/W2963680395","https://openalex.org/W2963887950","https://openalex.org/W2964308564","https://openalex.org/W3099202502","https://openalex.org/W3099206234","https://openalex.org/W3105024549","https://openalex.org/W6603203679","https://openalex.org/W6679434410","https://openalex.org/W6682845781","https://openalex.org/W6729999607","https://openalex.org/W6749336676","https://openalex.org/W6750148349","https://openalex.org/W6751966083","https://openalex.org/W6754615656","https://openalex.org/W6785273600"],"related_works":["https://openalex.org/W2329500892","https://openalex.org/W28991112","https://openalex.org/W2370726991","https://openalex.org/W2385859805","https://openalex.org/W2369710579","https://openalex.org/W2530972254","https://openalex.org/W2545348020","https://openalex.org/W4327728159","https://openalex.org/W2912751582","https://openalex.org/W2130893381"],"abstract_inverted_index":{"In":[0,88],"this":[1,74],"paper,":[2],"we":[3,28,92],"present":[4],"a":[5,56,66],"multi-modal":[6,101],"online":[7],"person":[8,43],"verification":[9],"system":[10],"using":[11],"both":[12],"speech":[13,60],"and":[14,26,61],"visual":[15],"signals.":[16],"Inspired":[17],"by":[18],"neuroscientific":[19],"findings":[20],"on":[21,113],"the":[22,40,76,89],"association":[23,38],"of":[24,42,73,107],"voice":[25],"face,":[27],"propose":[29],"an":[30],"attention-based":[31],"end-to-end":[32],"neural":[33],"network":[34,51,77],"that":[35,64,94],"learns":[36,52],"multi-sensory":[37],"for":[39,104],"task":[41],"verification.":[44],"The":[45],"attention":[46],"mechanism":[47],"in":[48],"our":[49,95,116],"proposed":[50],"to":[53,80],"conditionally":[54],"select":[55],"salient":[57],"modality":[58],"between":[59,68],"facial":[62],"representations":[63],"provides":[65],"balance":[67],"complementary":[69],"inputs.":[70],"By":[71],"virtue":[72],"capability,":[75],"is":[78],"robust":[79],"missing":[81,111],"or":[82,110],"corrupted":[83],"data":[84,112],"from":[85],"either":[86,114],"modality.":[87],"VoxCeleb2":[90],"dataset,":[91],"show":[93],"method":[96,117],"performs":[97],"favorably":[98],"against":[99],"competing":[100],"methods.":[102,123],"Even":[103],"extreme":[105],"cases":[106],"large":[108],"corruption":[109],"modality,":[115],"demonstrates":[118],"robustness":[119],"over":[120],"other":[121],"unimodal":[122]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}