{"id":"https://openalex.org/W2197258718","doi":"https://doi.org/10.1109/btas.2015.7358754","title":"A deep neural network for audio-visual person recognition","display_name":"A deep neural network for audio-visual person recognition","publication_year":2015,"publication_date":"2015-09-01","ids":{"openalex":"https://openalex.org/W2197258718","doi":"https://doi.org/10.1109/btas.2015.7358754","mag":"2197258718"},"language":"en","primary_location":{"id":"doi:10.1109/btas.2015.7358754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/btas.2015.7358754","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems (BTAS)","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/A5108744696","display_name":"Mohammad Rafiqul Alam","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mohammad Rafiqul Alam","raw_affiliation_strings":["School of Computer Science and Software Engineering"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Software Engineering","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009750573","display_name":"Mohammed Bennamoun","orcid":"https://orcid.org/0000-0002-6603-3257"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammed Bennamoun","raw_affiliation_strings":["School of Computer Science and Software Engineering"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Software Engineering","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017213156","display_name":"Roberto Togneri","orcid":"https://orcid.org/0000-0002-3778-4633"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Roberto Togneri","raw_affiliation_strings":["School of Electrical, The University of Western Australia, Crawley, WA, Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical, The University of Western Australia, Crawley, WA, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002219416","display_name":"Ferdous Sohel","orcid":"https://orcid.org/0000-0003-1557-4907"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ferdous Sohel","raw_affiliation_strings":["School of Computer Science and Software Engineering"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Software Engineering","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5108744696"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7482,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.79812461,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"313","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","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"}},"topics":[{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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/T10860","display_name":"Speech and Audio Processing","score":0.9979000091552734,"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/softmax-function","display_name":"Softmax function","score":0.8694643974304199},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8221595287322998},{"id":"https://openalex.org/keywords/boltzmann-machine","display_name":"Boltzmann machine","score":0.6844518780708313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6487506628036499},{"id":"https://openalex.org/keywords/deep-belief-network","display_name":"Deep belief network","score":0.6320069432258606},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5822345018386841},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.5797238945960999},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5702357292175293},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5696992874145508},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5488787293434143},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.482966810464859},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.44249534606933594},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4379359483718872},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.41514822840690613},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.40190327167510986},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32788896560668945}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.8694643974304199},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8221595287322998},{"id":"https://openalex.org/C192576344","wikidata":"https://www.wikidata.org/wiki/Q194706","display_name":"Boltzmann machine","level":3,"score":0.6844518780708313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6487506628036499},{"id":"https://openalex.org/C97385483","wikidata":"https://www.wikidata.org/wiki/Q16954980","display_name":"Deep belief network","level":3,"score":0.6320069432258606},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5822345018386841},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.5797238945960999},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5702357292175293},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5696992874145508},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5488787293434143},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.482966810464859},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.44249534606933594},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4379359483718872},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.41514822840690613},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.40190327167510986},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32788896560668945},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/btas.2015.7358754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/btas.2015.7358754","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems (BTAS)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/d10bc81c-82bf-45cc-b3c9-6b45a1457a73","is_oa":false,"landing_page_url":"https://research-repository.uwa.edu.au/en/publications/d10bc81c-82bf-45cc-b3c9-6b45a1457a73","pdf_url":null,"source":{"id":"https://openalex.org/S4306402523","display_name":"UWA Profiles and Research Repository (University of Western Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Alam , M R , Bennamoun , M , Togneri , R & Sohel , F 2015 , A deep neural network for audio-visual person recognition . in Biometrics Theory, Applications and Systems (BTAS), 2015 IEEE 7th International Conference . vol. N/A , IEEE, Institute of Electrical and Electronics Engineers , USA , pp. 1-6 , Biometrics Theory, Applications and Systems (BTAS) 2015 , Virginia , United States , 8/09/15 . https://doi.org/10.1109/BTAS.2015.7358754","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:researchrepository.murdoch.edu.au:28448","is_oa":false,"landing_page_url":"http://researchrepository.murdoch.edu.au/id/eprint/28448/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400274","display_name":"Murdoch Research Repository (Murdoch University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I176790772","host_organization_name":"Murdoch University","host_organization_lineage":["https://openalex.org/I176790772"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"  Alam, M., Bennamoun, M., Togneri, R. and Sohel, F. <http://researchrepository.murdoch.edu.au/view/author/Sohel, Ferdous.html>   (2015)  A deep neural network for audio-visual person recognition.   In: IEEE Seventh International Conference on Biometrics: Theory, Applications and Systems (BTAS 2015), 8 - 11 September 2015, Buffalo, NY   ","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W49975404","https://openalex.org/W189596042","https://openalex.org/W1482998036","https://openalex.org/W1836015656","https://openalex.org/W1984263024","https://openalex.org/W1985360119","https://openalex.org/W2038447668","https://openalex.org/W2071709160","https://openalex.org/W2093547879","https://openalex.org/W2100495367","https://openalex.org/W2115204524","https://openalex.org/W2122702209","https://openalex.org/W2131081720","https://openalex.org/W2160815625","https://openalex.org/W2164587673","https://openalex.org/W2167136086","https://openalex.org/W2171312459","https://openalex.org/W2184188583","https://openalex.org/W2200708944","https://openalex.org/W2344822617","https://openalex.org/W2399828378","https://openalex.org/W2403389749","https://openalex.org/W6602031664","https://openalex.org/W6606244218","https://openalex.org/W6607775107","https://openalex.org/W6638820060","https://openalex.org/W6646180427","https://openalex.org/W6686207219","https://openalex.org/W6687884132","https://openalex.org/W6704529918","https://openalex.org/W6712943345","https://openalex.org/W6713186265"],"related_works":["https://openalex.org/W2785870119","https://openalex.org/W2064630666","https://openalex.org/W2774266279","https://openalex.org/W2287713958","https://openalex.org/W2737967172","https://openalex.org/W3005904504","https://openalex.org/W2184456254","https://openalex.org/W2133034788","https://openalex.org/W1257380361","https://openalex.org/W1829305295"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"applications":[3],"of":[4,7,26,37,54,61],"special":[5],"types":[6],"deep":[8,27,55],"neural":[9],"networks":[10,29],"(DNNs)":[11],"for":[12,59],"audio-visual":[13,113],"biometrics.":[14],"A":[15],"common":[16],"example":[17],"is":[18,67],"the":[19,23,33,47,51,72,89,93,103,115],"DBN-DNN":[20],"that":[21,49,81],"uses":[22,50],"generative":[24,52],"weights":[25,53],"belief":[28],"(DBNs)":[30],"to":[31,92],"initialize":[32],"feature":[34],"detecting":[35],"layers":[36],"deterministic":[38],"feed":[39],"forward":[40],"DNNs.":[41,62],"In":[42],"this":[43],"paper,":[44],"we":[45],"propose":[46],"DBM-DNN":[48,90],"Boltzmann":[56],"machines":[57],"(DBMs)":[58],"initialization":[60],"Then,":[63],"a":[64],"softmax":[65],"layer":[66],"added":[68],"on":[69,109],"top":[70],"and":[71,102,117],"DNNs":[73],"are":[74],"trained":[75],"discriminatively.":[76],"Our":[77],"experimental":[78],"results":[79],"show":[80],"lower":[82],"error":[83],"rates":[84],"can":[85],"be":[86],"achieved":[87],"using":[88],"compared":[91],"support":[94],"vector":[95],"machine":[96],"(SVM),":[97],"linear":[98],"regression-based":[99],"classifier":[100],"(LRC)":[101],"DBN-DNN.":[104],"Experiments":[105],"were":[106],"carried":[107],"out":[108],"two":[110],"publicly":[111],"available":[112],"datasets:":[114],"VidTIMIT":[116],"MOBIO.":[118]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}