{"id":"https://openalex.org/W2787664072","doi":"https://doi.org/10.1109/apsipa.2017.8282227","title":"Multimodal speech recognition using mouth images from depth camera","display_name":"Multimodal speech recognition using mouth images from depth camera","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2787664072","doi":"https://doi.org/10.1109/apsipa.2017.8282227","mag":"2787664072"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2017.8282227","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282227","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100757791/ATD100000413/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071509899","display_name":"Yuki Yasui","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuki Yasui","raw_affiliation_strings":["Tokyo Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101261291","display_name":"Nakamasa Inoue","orcid":"https://orcid.org/0009-0006-1145-0914"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nakamasa Inoue","raw_affiliation_strings":["Tokyo Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084374665","display_name":"Koji Iwano","orcid":"https://orcid.org/0000-0002-7373-5353"},"institutions":[{"id":"https://openalex.org/I185088104","display_name":"Tokyo City University","ror":"https://ror.org/04dt6bw53","country_code":"JP","type":"education","lineage":["https://openalex.org/I185088104"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koji Iwano","raw_affiliation_strings":["Tokyo City University, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo City University, Japan","institution_ids":["https://openalex.org/I185088104"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081629487","display_name":"Koichi Shinoda","orcid":"https://orcid.org/0000-0003-1095-3203"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koichi Shinoda","raw_affiliation_strings":["Tokyo Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5071509899"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":0.3735,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.61368925,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1233","last_page":"1236"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9952999949455261,"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":0.7516006231307983},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7294518351554871},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7144901156425476},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6755666732788086},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6211497783660889},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5256218314170837},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.4519887864589691},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42985400557518005},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3597462773323059}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7516006231307983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7294518351554871},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7144901156425476},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6755666732788086},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6211497783660889},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5256218314170837},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.4519887864589691},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42985400557518005},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3597462773323059},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/apsipa.2017.8282227","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282227","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50399611","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100757791","pdf_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100757791/ATD100000413/","source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:t2r2.star.titech.ac.jp:50399611","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100757791","pdf_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100757791/ATD100000413/","source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2787664072.pdf","grobid_xml":"https://content.openalex.org/works/W2787664072.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W154472438","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1736374775","https://openalex.org/W1905359547","https://openalex.org/W1965255698","https://openalex.org/W1986861891","https://openalex.org/W2043698530","https://openalex.org/W2110798204","https://openalex.org/W2128583887","https://openalex.org/W2164450870","https://openalex.org/W2168744723","https://openalex.org/W2184188583","https://openalex.org/W2184549941","https://openalex.org/W2289925289","https://openalex.org/W2406954482","https://openalex.org/W2964121744","https://openalex.org/W3099202502","https://openalex.org/W3144828656","https://openalex.org/W6606244218","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6637571906","https://openalex.org/W6676481782","https://openalex.org/W6686207219","https://openalex.org/W6713510121","https://openalex.org/W6785273600"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W2669956259","https://openalex.org/W4249005693","https://openalex.org/W4392946183","https://openalex.org/W3088732000","https://openalex.org/W2384651879"],"abstract_inverted_index":{"Deep":[0],"learning":[1,24],"has":[2],"been":[3],"proved":[4],"to":[5,81],"be":[6],"effective":[7,95],"in":[8],"multimodal":[9],"speech":[10,51,85],"recognition":[11,86],"using":[12],"facial":[13],"frontal":[14],"images.":[15],"In":[16,91],"this":[17],"paper,":[18],"we":[19],"propose":[20],"a":[21,26],"new":[22],"deep":[23,28],"method,":[25],"trimodal":[27],"autoencoder,":[29],"which":[30],"uses":[31],"not":[32],"only":[33],"audio":[34],"signals":[35],"and":[36,59],"face":[37],"images,":[38],"but":[39],"also":[40],"depth":[41],"images":[42],"of":[43],"faces,":[44],"as":[45],"the":[46],"inputs.":[47],"We":[48],"collected":[49],"continuous":[50],"data":[52],"from":[53,79,83],"20":[54],"speakers":[55],"with":[56,68],"Kinect":[57],"2.0":[58],"used":[60],"them":[61],"for":[62,96],"our":[63,73],"evaluation.":[64],"The":[65],"experimental":[66],"results":[67],"10dB":[69],"SNR":[70,88],"showed":[71],"that":[72],"method":[74],"reduced":[75],"errors":[76],"by":[77],"30%,":[78],"34.6%":[80],"24.2%":[82],"audio-only":[84],"when":[87],"was":[89],"10dB.":[90],"particular,":[92],"it":[93],"is":[94],"recognizing":[97],"some":[98],"consonants":[99],"including":[100],"/k/,":[101],"/t/.":[102]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}