{"id":"https://openalex.org/W2737034911","doi":"https://doi.org/10.23919/mva.2017.7986867","title":"Two features combination with gated recurrent unit for visual speech recognition","display_name":"Two features combination with gated recurrent unit for visual speech recognition","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2737034911","doi":"https://doi.org/10.23919/mva.2017.7986867","mag":"2737034911"},"language":"en","primary_location":{"id":"doi:10.23919/mva.2017.7986867","is_oa":false,"landing_page_url":"https://doi.org/10.23919/mva.2017.7986867","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Fifteenth IAPR International Conference on Machine Vision Applications (MVA)","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/A5055965834","display_name":"Masaya Iwasaki","orcid":"https://orcid.org/0000-0002-2285-3632"},"institutions":[{"id":"https://openalex.org/I207014233","display_name":"Kyushu Institute of Technology","ror":"https://ror.org/02278tr80","country_code":"JP","type":"education","lineage":["https://openalex.org/I207014233"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Masaya Iwasaki","raw_affiliation_strings":["Kyushu Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Kyushu Institute of Technology, Japan","institution_ids":["https://openalex.org/I207014233"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012247458","display_name":"Michiko Kubokawa","orcid":null},"institutions":[{"id":"https://openalex.org/I207014233","display_name":"Kyushu Institute of Technology","ror":"https://ror.org/02278tr80","country_code":"JP","type":"education","lineage":["https://openalex.org/I207014233"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Michiko Kubokawa","raw_affiliation_strings":["Kyushu Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Kyushu Institute of Technology, Japan","institution_ids":["https://openalex.org/I207014233"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058108485","display_name":"Takeshi Saitoh","orcid":"https://orcid.org/0000-0001-8844-9707"},"institutions":[{"id":"https://openalex.org/I207014233","display_name":"Kyushu Institute of Technology","ror":"https://ror.org/02278tr80","country_code":"JP","type":"education","lineage":["https://openalex.org/I207014233"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takeshi Saitoh","raw_affiliation_strings":["Kyushu Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Kyushu Institute of Technology, Japan","institution_ids":["https://openalex.org/I207014233"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5055965834"],"corresponding_institution_ids":["https://openalex.org/I207014233"],"apc_list":null,"apc_paid":null,"fwci":0.5548,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.64789899,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"326","last_page":"329"},"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":0.9997000098228455,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9962999820709229,"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":0.7641550302505493},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7226179838180542},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7146784067153931},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6551403999328613},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6410667300224304},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5734196901321411},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5106020569801331},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.48566925525665283},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41724830865859985},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4170542359352112},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0998845100402832},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08166065812110901}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7641550302505493},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7226179838180542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7146784067153931},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6551403999328613},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6410667300224304},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5734196901321411},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5106020569801331},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.48566925525665283},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41724830865859985},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4170542359352112},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0998845100402832},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08166065812110901},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/mva.2017.7986867","is_oa":false,"landing_page_url":"https://doi.org/10.23919/mva.2017.7986867","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Fifteenth IAPR International Conference on Machine Vision Applications (MVA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1454360699","https://openalex.org/W1498911878","https://openalex.org/W1526392145","https://openalex.org/W1550977693","https://openalex.org/W1924770834","https://openalex.org/W2015143272","https://openalex.org/W2060510034","https://openalex.org/W2113814270","https://openalex.org/W2136155248","https://openalex.org/W2138527036","https://openalex.org/W2148659689","https://openalex.org/W2157190406","https://openalex.org/W2162758777","https://openalex.org/W2172803778","https://openalex.org/W2173083910","https://openalex.org/W2184188583","https://openalex.org/W2474638510","https://openalex.org/W2556171197","https://openalex.org/W2608022654","https://openalex.org/W6629981029","https://openalex.org/W6631564540","https://openalex.org/W6681898093","https://openalex.org/W6682634897","https://openalex.org/W6686207219","https://openalex.org/W6729699919","https://openalex.org/W6737005002"],"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/W4297051394","https://openalex.org/W2669956259","https://openalex.org/W4249005693","https://openalex.org/W4392946183","https://openalex.org/W3088732000"],"abstract_inverted_index":{"Recently,":[0],"deep":[1],"learning":[2],"has":[3],"attracted":[4],"in":[5],"the":[6,57,66,71],"visual":[7],"speech":[8],"recognition":[9],"(VSR)":[10],"field,":[11],"however,":[12],"most":[13],"of":[14],"approaches":[15],"use":[16],"single":[17],"feature.":[18],"This":[19],"paper":[20],"proposes":[21],"two":[22],"features;":[23],"image-based":[24],"feature":[25,30,33],"by":[26],"autoencoder,":[27],"and":[28,35,56],"motion-based":[29],"based":[31],"on":[32,50],"points,":[34],"combination":[36],"approach":[37],"with":[38,65],"gated":[39],"recurrent":[40],"unit":[41],"for":[42],"VSR":[43],"task.":[44],"The":[45],"proposed":[46],"method":[47,69],"was":[48,61],"evaluated":[49],"a":[51],"public":[52],"dataset":[53],"Oulu":[54],"VS,":[55],"speaker":[58],"independent":[59],"setting":[60],"carried":[62],"out.":[63],"Compared":[64],"state-of-the-art,":[67],"our":[68],"obtained":[70],"highest":[72],"accuracy.":[73]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
