{"id":"https://openalex.org/W2755403114","doi":"https://doi.org/10.1109/icip.2017.8297030","title":"Multi-view visual speech recognition based on multi task learning","display_name":"Multi-view visual speech recognition based on multi task learning","publication_year":2017,"publication_date":"2017-09-01","ids":{"openalex":"https://openalex.org/W2755403114","doi":"https://doi.org/10.1109/icip.2017.8297030","mag":"2755403114"},"language":"en","primary_location":{"id":"doi:10.1109/icip.2017.8297030","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2017.8297030","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Image Processing (ICIP)","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/A5023561341","display_name":"HouJeung Han","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"HouJeung Han","raw_affiliation_strings":["Korea Advanced institute of Science and Technology, School of Electrical Engineering, Daejeon, Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced institute of Science and Technology, School of Electrical Engineering, Daejeon, Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072712913","display_name":"Sunghun Kang","orcid":"https://orcid.org/0000-0003-2632-7522"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sunghun Kang","raw_affiliation_strings":["Korea Advanced institute of Science and Technology, School of Electrical Engineering, Daejeon, Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced institute of Science and Technology, School of Electrical Engineering, Daejeon, Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073287748","display_name":"Chang D. Yoo","orcid":"https://orcid.org/0000-0002-0756-7179"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chang D. Yoo","raw_affiliation_strings":["Korea Advanced institute of Science and Technology, School of Electrical Engineering, Daejeon, Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced institute of Science and Technology, School of Electrical Engineering, Daejeon, Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5023561341"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":0.5548,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.65714483,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3983","last_page":"3987"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9922999739646912,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.8552133440971375},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7190708518028259},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6634558439254761},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5948282480239868},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.5830202102661133},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5548344254493713},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5065616369247437},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4650159180164337},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.45835649967193604},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4422450363636017},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36993592977523804},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3554246127605438}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8552133440971375},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7190708518028259},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6634558439254761},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5948282480239868},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5830202102661133},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5548344254493713},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5065616369247437},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4650159180164337},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.45835649967193604},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4422450363636017},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36993592977523804},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3554246127605438},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip.2017.8297030","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2017.8297030","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1526392145","https://openalex.org/W1836465849","https://openalex.org/W2010318909","https://openalex.org/W2015394094","https://openalex.org/W2060510034","https://openalex.org/W2079735306","https://openalex.org/W2187089797","https://openalex.org/W2243738093","https://openalex.org/W2267805933","https://openalex.org/W2404704342","https://openalex.org/W2511073133","https://openalex.org/W2556171197","https://openalex.org/W2594690981","https://openalex.org/W2604379605","https://openalex.org/W2605246626","https://openalex.org/W2949117887","https://openalex.org/W2963192365","https://openalex.org/W2964121744","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6734491695"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2039546652","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175"],"abstract_inverted_index":{"Visual":[0],"speech":[1],"recognition":[2,160],"(VSR),":[3],"also":[4,151],"known":[5],"as":[6,106],"lipreading":[7,154],"is":[8,84,104,123],"a":[9,57,87],"task":[10],"that":[11,28,72,91,129],"recognizes":[12],"word":[13,63,96],"or":[14],"phrase":[15],"using":[16],"video":[17],"clip":[18],"of":[19,35,115,162],"lip":[20,47],"movement.":[21,39],"Traditional":[22],"VSR":[23,34,148],"methods":[24,149],"are":[25,30,98],"limited":[26],"in":[27,86],"they":[29],"based":[31,134],"mostly":[32],"on":[33,135,165],"frontal":[36],"view":[37,68],"facial":[38],"This":[40,156],"limitation":[41],"should":[42],"be":[43],"relaxed":[44],"to":[45,145],"include":[46],"movement":[48],"from":[49,65],"all":[50],"angles.":[51],"In":[52],"this":[53],"paper,":[54],"we":[55],"propose":[56],"pose-invariant":[58],"network":[59,76],"which":[60],"can":[61],"recognize":[62],"spoken":[64,97],"any":[66],"arbitrary":[67],"input.":[69],"The":[70,125],"architecture":[71],"combines":[73],"convolutional":[74],"neural":[75],"(CNN)":[77],"with":[78],"bidirectional":[79],"long":[80],"short-term":[81],"memory":[82],"(LSTM)":[83],"trained":[85],"multi-task":[88,118,138],"manner":[89],"such":[90],"the":[92,95,107,113,116,130,136],"pose":[93,102],"and":[94,150],"jointly":[99],"classified.":[100],"Here,":[101],"classification":[103],"considered":[105],"auxiliary":[108],"task.":[109],"To":[110],"comparatively":[111],"evaluate":[112],"performance":[114,161],"proposed":[117,137],"learning,":[119],"OuluVS2":[120,166],"benchmark":[121],"dataset":[122],"considered.":[124],"experimental":[126],"results":[127],"show":[128],"deep":[131,157],"model":[132,158],"learned":[133],"learning":[139],"method":[140],"prove":[141],"its":[142],"advantage":[143],"compared":[144],"previous":[146,152],"single-view":[147],"multi-view":[153],"methods.":[155],"achieved":[159],"95.0%":[163],"accuracy":[164],"dataset.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}