{"id":"https://openalex.org/W2734984521","doi":"https://doi.org/10.1109/access.2017.2761539","title":"3D Convolutional Neural Networks for Cross Audio-Visual Matching Recognition","display_name":"3D Convolutional Neural Networks for Cross Audio-Visual Matching Recognition","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2734984521","doi":"https://doi.org/10.1109/access.2017.2761539","mag":"2734984521"},"language":"en","primary_location":{"id":"doi:10.1109/access.2017.2761539","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2017.2761539","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2017.2761539","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064784351","display_name":"Amirsina Torfi","orcid":"https://orcid.org/0000-0003-2282-4361"},"institutions":[{"id":"https://openalex.org/I12097938","display_name":"West Virginia University","ror":"https://ror.org/011vxgd24","country_code":"US","type":"education","lineage":["https://openalex.org/I12097938"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Amirsina Torfi","raw_affiliation_strings":["Lane Department of Computer Science and Electrical Engineering, West Virginia University College of Engineering and Mineral Resources, Morgantown, WV, USA"],"raw_orcid":"https://orcid.org/0000-0003-2282-4361","affiliations":[{"raw_affiliation_string":"Lane Department of Computer Science and Electrical Engineering, West Virginia University College of Engineering and Mineral Resources, Morgantown, WV, USA","institution_ids":["https://openalex.org/I12097938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077626943","display_name":"Seyed Mehdi Iranmanesh","orcid":"https://orcid.org/0000-0002-1666-1415"},"institutions":[{"id":"https://openalex.org/I12097938","display_name":"West Virginia University","ror":"https://ror.org/011vxgd24","country_code":"US","type":"education","lineage":["https://openalex.org/I12097938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seyed Mehdi Iranmanesh","raw_affiliation_strings":["Lane Department of Computer Science and Electrical Engineering, West Virginia University College of Engineering and Mineral Resources, Morgantown, WV, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lane Department of Computer Science and Electrical Engineering, West Virginia University College of Engineering and Mineral Resources, Morgantown, WV, USA","institution_ids":["https://openalex.org/I12097938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021852735","display_name":"Nasser M. Nasrabadi","orcid":"https://orcid.org/0000-0001-8730-627X"},"institutions":[{"id":"https://openalex.org/I12097938","display_name":"West Virginia University","ror":"https://ror.org/011vxgd24","country_code":"US","type":"education","lineage":["https://openalex.org/I12097938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nasser Nasrabadi","raw_affiliation_strings":["Lane Department of Computer Science and Electrical Engineering, West Virginia University College of Engineering and Mineral Resources, Morgantown, WV, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lane Department of Computer Science and Electrical Engineering, West Virginia University College of Engineering and Mineral Resources, Morgantown, WV, USA","institution_ids":["https://openalex.org/I12097938"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068143389","display_name":"Jeremy Dawson","orcid":"https://orcid.org/0000-0002-4539-7588"},"institutions":[{"id":"https://openalex.org/I12097938","display_name":"West Virginia University","ror":"https://ror.org/011vxgd24","country_code":"US","type":"education","lineage":["https://openalex.org/I12097938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeremy Dawson","raw_affiliation_strings":["Lane Department of Computer Science and Electrical Engineering, West Virginia University College of Engineering and Mineral Resources, Morgantown, WV, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lane Department of Computer Science and Electrical Engineering, West Virginia University College of Engineering and Mineral Resources, Morgantown, WV, USA","institution_ids":["https://openalex.org/I12097938"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5064784351"],"corresponding_institution_ids":["https://openalex.org/I12097938"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":10.0802,"has_fulltext":false,"cited_by_count":117,"citation_normalized_percentile":{"value":0.9877799,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"5","issue":null,"first_page":"22081","last_page":"22091"},"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8718739748001099},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6464610695838928},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6431795954704285},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5892746448516846},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5493587255477905},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5488425493240356},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5339165329933167},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4935060739517212},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.44204461574554443},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4282894730567932},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4254944920539856}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8718739748001099},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6464610695838928},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6431795954704285},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5892746448516846},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5493587255477905},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5488425493240356},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5339165329933167},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4935060739517212},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.44204461574554443},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4282894730567932},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4254944920539856},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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":5,"locations":[{"id":"doi:10.1109/access.2017.2761539","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2017.2761539","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1706.05739","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1706.05739","pdf_url":"https://arxiv.org/pdf/1706.05739","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:doaj.org/article:89c015693af24942b08d156c3115f61c","is_oa":true,"landing_page_url":"https://doaj.org/article/89c015693af24942b08d156c3115f61c","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 5, Pp 22081-22091 (2017)","raw_type":"article"},{"id":"doi:10.5281/zenodo.836306","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.836306","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.5281/zenodo.840400","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.840400","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2017.2761539","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2017.2761539","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G7759060261","display_name":null,"funder_award_id":"CNS-1650474","funder_id":"https://openalex.org/F4320337396","funder_display_name":"Division of Industrial Innovation and Partnerships"}],"funders":[{"id":"https://openalex.org/F4320337396","display_name":"Division of Industrial Innovation and Partnerships","ror":"https://ror.org/03xyg3m20"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W109538337","https://openalex.org/W1503933356","https://openalex.org/W1522734439","https://openalex.org/W1574171128","https://openalex.org/W1677182931","https://openalex.org/W1836465849","https://openalex.org/W1976526581","https://openalex.org/W1983364832","https://openalex.org/W1988910659","https://openalex.org/W1995562189","https://openalex.org/W2022799064","https://openalex.org/W2042608483","https://openalex.org/W2061489198","https://openalex.org/W2076462394","https://openalex.org/W2096733369","https://openalex.org/W2100561338","https://openalex.org/W2112026651","https://openalex.org/W2115252128","https://openalex.org/W2120480077","https://openalex.org/W2157364932","https://openalex.org/W2160815625","https://openalex.org/W2184188583","https://openalex.org/W2184549941","https://openalex.org/W2243738093","https://openalex.org/W2267805933","https://openalex.org/W2285716245","https://openalex.org/W2398406965","https://openalex.org/W2400006663","https://openalex.org/W2404704342","https://openalex.org/W2406799669","https://openalex.org/W2556171197","https://openalex.org/W2594690981","https://openalex.org/W2604379605","https://openalex.org/W2618829015","https://openalex.org/W2782289159","https://openalex.org/W2964307722","https://openalex.org/W3099202502","https://openalex.org/W3099206234","https://openalex.org/W4294242511","https://openalex.org/W4298414551","https://openalex.org/W6638667902","https://openalex.org/W6675048546","https://openalex.org/W6677618333","https://openalex.org/W6686207219","https://openalex.org/W6712999683","https://openalex.org/W6729699919","https://openalex.org/W6734491695","https://openalex.org/W6735927292","https://openalex.org/W6785273600"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2110287964","https://openalex.org/W2167701463","https://openalex.org/W4307407935"],"abstract_inverted_index":{"Audio-visual":[0],"recognition":[1,11,23,49],"(AVR)":[2],"has":[3],"been":[4],"considered":[5],"as":[6,18,20],"a":[7,21,86,101,140],"solution":[8],"for":[9,26,135,150,163,170],"speech":[10],"tasks":[12],"when":[13],"the":[14,40,48,52,57,66,69,76,83,106,112,130,156,159,185,196,204,210],"audio":[15,70],"is":[16,37,63,75],"corrupted,":[17],"well":[19],"visual":[22,72],"method":[24,154,181,189],"used":[25],"speaker":[27],"verification":[28],"in":[29,207],"multispeaker":[30],"scenarios.":[31],"The":[32,60,116,187],"approach":[33],"of":[34,51,78,85,108,158],"AVR":[35],"systems":[36],"to":[38,46,64,104,127,209],"leverage":[39],"extracted":[41],"information":[42,125,134],"from":[43],"one":[44],"modality":[45,54],"improve":[47],"ability":[50],"other":[53],"by":[55],"complementing":[56],"missing":[58],"information.":[59],"essential":[61],"problem":[62],"find":[65,129],"correspondence":[67,107],"between":[68,132],"and":[71,123,145,200],"streams,":[73],"which":[74,166],"goal":[77],"this":[79],"paper.":[80],"We":[81,173],"propose":[82],"use":[84,167],"coupled":[87],"3D":[88,168],"convolutional":[89],"neural":[90],"network":[91,143],"(3D":[92],"CNN)":[93],"architecture":[94,118,144],"that":[95,176],"can":[96,182],"map":[97],"both":[98,121],"modalities":[99],"into":[100],"representation":[102],"space":[103],"evaluate":[105],"audio-visual":[109,164],"streams":[110],"using":[111,139],"learned":[113],"multimodal":[114],"features.":[115],"proposed":[117,153,188],"will":[119],"incorporate":[120],"spatial":[122],"temporal":[124,133],"jointly":[126],"effectively":[128],"correlation":[131],"different":[136],"modalities.":[137],"By":[138],"relatively":[141],"small":[142],"much":[146],"smaller":[147],"data":[148],"set":[149],"training,":[151],"our":[152],"surpasses":[155],"performance":[157],"existing":[160],"similar":[161],"methods":[162],"matching,":[165],"CNNs":[169],"feature":[171],"representation.":[172],"also":[174],"demonstrate":[175],"an":[177],"effective":[178],"pair":[179],"selection":[180],"significantly":[183],"increase":[184],"performance.":[186],"achieves":[190],"relative":[191],"improvements":[192],"over":[193,201],"20%":[194],"on":[195,203],"equal":[197],"error":[198],"rate":[199],"7%":[202],"average":[205],"precision":[206],"comparison":[208],"state-of-the-art":[211],"method.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":20}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2017-07-21T00:00:00"}