{"id":"https://openalex.org/W2525342915","doi":"https://doi.org/10.1587/transinf.2016slp0019","title":"Investigation of DNN-Based Audio-Visual Speech Recognition","display_name":"Investigation of DNN-Based Audio-Visual Speech Recognition","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2525342915","doi":"https://doi.org/10.1587/transinf.2016slp0019","mag":"2525342915"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2016slp0019","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2016slp0019","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E99.D/10/E99.D_2016SLP0019/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E99.D/10/E99.D_2016SLP0019/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101808735","display_name":"Satoshi Tamura","orcid":"https://orcid.org/0000-0001-6916-4618"},"institutions":[{"id":"https://openalex.org/I42405503","display_name":"Gifu University","ror":"https://ror.org/024exxj48","country_code":"JP","type":"education","lineage":["https://openalex.org/I42405503"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi TAMURA","raw_affiliation_strings":["Gifu University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gifu University","institution_ids":["https://openalex.org/I42405503"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101639573","display_name":"Hiroshi Ninomiya","orcid":"https://orcid.org/0000-0003-3418-3178"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi NINOMIYA","raw_affiliation_strings":["Nagoya University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077234015","display_name":"Norihide Kitaoka","orcid":"https://orcid.org/0000-0003-2028-8585"},"institutions":[{"id":"https://openalex.org/I922474255","display_name":"Tokushima University","ror":"https://ror.org/044vy1d05","country_code":"JP","type":"education","lineage":["https://openalex.org/I922474255"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Norihide KITAOKA","raw_affiliation_strings":["Tokushima University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokushima University","institution_ids":["https://openalex.org/I922474255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040638962","display_name":"Shin Osuga","orcid":null},"institutions":[{"id":"https://openalex.org/I4210166078","display_name":"Aisin (United States)","ror":"https://ror.org/05wdedb75","country_code":"US","type":"company","lineage":["https://openalex.org/I4210098271","https://openalex.org/I4210166078"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shin OSUGA","raw_affiliation_strings":["Aisin Seiki Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aisin Seiki Co., Ltd","institution_ids":["https://openalex.org/I4210166078"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112017946","display_name":"Yurie Iribe","orcid":null},"institutions":[{"id":"https://openalex.org/I45205469","display_name":"Aichi Prefectural University","ror":"https://ror.org/047n0b268","country_code":"JP","type":"education","lineage":["https://openalex.org/I45205469"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yurie IRIBE","raw_affiliation_strings":["Aichi Prefectural University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aichi Prefectural University","institution_ids":["https://openalex.org/I45205469"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042118446","display_name":"Kazuya Takeda","orcid":"https://orcid.org/0000-0002-0330-1787"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuya TAKEDA","raw_affiliation_strings":["Nagoya University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008108612","display_name":"Satoru Hayamizu","orcid":null},"institutions":[{"id":"https://openalex.org/I42405503","display_name":"Gifu University","ror":"https://ror.org/024exxj48","country_code":"JP","type":"education","lineage":["https://openalex.org/I42405503"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoru HAYAMIZU","raw_affiliation_strings":["Gifu University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gifu University","institution_ids":["https://openalex.org/I42405503"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5105,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.65177367,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"E99.D","issue":"10","first_page":"2444","last_page":"2451"},"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":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983000159263611,"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":0.8637667894363403},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7971186637878418},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6891574859619141},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6006852984428406},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4940045475959778},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4443415403366089},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42449772357940674},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.41825181245803833},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3373105525970459}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8637667894363403},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7971186637878418},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6891574859619141},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6006852984428406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4940045475959778},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4443415403366089},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42449772357940674},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.41825181245803833},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3373105525970459},{"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:10.1587/transinf.2016slp0019","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2016slp0019","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E99.D/10/E99.D_2016SLP0019/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2016slp0019","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2016slp0019","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E99.D/10/E99.D_2016SLP0019/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G2360604065","display_name":"Investigation of method optimization for multi-modal speech recognition","funder_award_id":"25730109","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2525342915.pdf","grobid_xml":"https://content.openalex.org/works/W2525342915.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W11855449","https://openalex.org/W1520736967","https://openalex.org/W1582624286","https://openalex.org/W1908325895","https://openalex.org/W1990353734","https://openalex.org/W1993882792","https://openalex.org/W2022799064","https://openalex.org/W2029199293","https://openalex.org/W2050693797","https://openalex.org/W2060108923","https://openalex.org/W2076462394","https://openalex.org/W2086677518","https://openalex.org/W2100969003","https://openalex.org/W2110798204","https://openalex.org/W2123237149","https://openalex.org/W2128653836","https://openalex.org/W2136922672","https://openalex.org/W2146871184","https://openalex.org/W2157190406","https://openalex.org/W2184188583","https://openalex.org/W2254457717","https://openalex.org/W2289925289","https://openalex.org/W2394553851","https://openalex.org/W2397904770","https://openalex.org/W2400006663","https://openalex.org/W2400967734","https://openalex.org/W2406846463","https://openalex.org/W2539140714","https://openalex.org/W2542739697","https://openalex.org/W2545925890","https://openalex.org/W3162900885"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861","https://openalex.org/W4297807400","https://openalex.org/W1491159402"],"abstract_inverted_index":{"Audio-Visual":[0],"Speech":[1],"Recognition":[2],"(AVSR)":[3],"is":[4,83,95,168],"one":[5],"of":[6,11,32,34],"techniques":[7,58],"to":[8,55,113,140],"enhance":[9],"robustness":[10],"speech":[12,38,60],"recognizer":[13],"in":[14,36,69,89],"noisy":[15],"or":[16],"real":[17],"environments.":[18],"On":[19],"the":[20,37,70,90,138,143,169],"other":[21],"hand,":[22],"Deep":[23,158],"Neural":[24],"Networks":[25],"(DNNs)":[26],"have":[27],"recently":[28],"attracted":[29],"a":[30,62,66,86,93,98,132,153,174],"lot":[31],"attentions":[33],"researchers":[35],"recognition":[39,46,129],"field,":[40],"because":[41],"we":[42,105,117,136],"can":[43],"drastically":[44],"improve":[45],"performance":[47],"by":[48,173],"using":[49,85,124,131,156,181],"DNNs.":[50,125],"There":[51],"are":[52],"two":[53],"ways":[54],"employ":[56],"DNN":[57,94],"for":[59],"recognition:":[61],"hybrid":[63,71,175],"approach":[64,72,92,176],"and":[65,107,121,135,162,177],"tandem":[67,91,179],"approach;":[68],"an":[73],"emission":[74],"probability":[75],"on":[76],"each":[77],"Hidden":[78],"Markov":[79],"Model":[80],"(HMM)":[81],"state":[82],"computed":[84],"DNN,":[87],"while":[88],"composed":[96],"into":[97],"feature":[99],"extraction":[100],"scheme.":[101],"In":[102],"this":[103],"paper,":[104],"investigate":[106],"compare":[108],"several":[109],"DNN-based":[110,145],"AVSR":[111,146],"methods":[112],"mainly":[114],"clarify":[115],"how":[116],"should":[118],"incorporate":[119],"audio":[120,157],"visual":[122,163],"modalities":[123],"We":[126],"carried":[127],"out":[128,142,151],"experiments":[130],"corpus":[133],"CENSREC-1-AV,":[134],"discuss":[137],"results":[139],"find":[141],"best":[144],"modeling.":[147],"Then":[148],"it":[149],"turns":[150],"that":[152],"tandem-based":[154],"method":[155],"Bottle-Neck":[159],"Features":[160],"(DBNFs)":[161],"ones":[164],"with":[165],"multi-stream":[166],"HMMs":[167],"most":[170],"suitable,":[171],"followed":[172],"another":[178],"scheme":[180],"audio-visual":[182],"DBNFs.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}