{"id":"https://openalex.org/W2078517841","doi":"https://doi.org/10.1145/2393347.2396408","title":"Robust AAM-based audio-visual speech recognition against face direction changes","display_name":"Robust AAM-based audio-visual speech recognition against face direction changes","publication_year":2012,"publication_date":"2012-10-29","ids":{"openalex":"https://openalex.org/W2078517841","doi":"https://doi.org/10.1145/2393347.2396408","mag":"2078517841"},"language":"en","primary_location":{"id":"doi:10.1145/2393347.2396408","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2393347.2396408","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM international conference on Multimedia","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/A5070660642","display_name":"Yuto Komai","orcid":null},"institutions":[{"id":"https://openalex.org/I65837984","display_name":"Kobe University","ror":"https://ror.org/03tgsfw79","country_code":"JP","type":"education","lineage":["https://openalex.org/I65837984"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuto Komai","raw_affiliation_strings":["Kobe University, Kobe, Japan","[Kobe University, Kobe, JAPAN]"],"affiliations":[{"raw_affiliation_string":"Kobe University, Kobe, Japan","institution_ids":["https://openalex.org/I65837984"]},{"raw_affiliation_string":"[Kobe University, Kobe, JAPAN]","institution_ids":["https://openalex.org/I65837984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022196026","display_name":"Nan Yang","orcid":"https://orcid.org/0000-0002-3071-0244"},"institutions":[{"id":"https://openalex.org/I65837984","display_name":"Kobe University","ror":"https://ror.org/03tgsfw79","country_code":"JP","type":"education","lineage":["https://openalex.org/I65837984"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nan Yang","raw_affiliation_strings":["Kobe University, Kobe, Japan","[Kobe University, Kobe, JAPAN]"],"affiliations":[{"raw_affiliation_string":"Kobe University, Kobe, Japan","institution_ids":["https://openalex.org/I65837984"]},{"raw_affiliation_string":"[Kobe University, Kobe, JAPAN]","institution_ids":["https://openalex.org/I65837984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009283470","display_name":"Tetsuya Takiguchi","orcid":"https://orcid.org/0000-0001-5005-7679"},"institutions":[{"id":"https://openalex.org/I65837984","display_name":"Kobe University","ror":"https://ror.org/03tgsfw79","country_code":"JP","type":"education","lineage":["https://openalex.org/I65837984"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuya Takiguchi","raw_affiliation_strings":["Kobe University, Kobe, Japan","[Kobe University, Kobe, JAPAN]"],"affiliations":[{"raw_affiliation_string":"Kobe University, Kobe, Japan","institution_ids":["https://openalex.org/I65837984"]},{"raw_affiliation_string":"[Kobe University, Kobe, JAPAN]","institution_ids":["https://openalex.org/I65837984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040766342","display_name":"Yasuo Ariki","orcid":"https://orcid.org/0000-0003-3473-2026"},"institutions":[{"id":"https://openalex.org/I65837984","display_name":"Kobe University","ror":"https://ror.org/03tgsfw79","country_code":"JP","type":"education","lineage":["https://openalex.org/I65837984"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasuo Ariki","raw_affiliation_strings":["Kobe University, Kobe, Japan","[Kobe University, Kobe, JAPAN]"],"affiliations":[{"raw_affiliation_string":"Kobe University, Kobe, Japan","institution_ids":["https://openalex.org/I65837984"]},{"raw_affiliation_string":"[Kobe University, Kobe, JAPAN]","institution_ids":["https://openalex.org/I65837984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5070660642"],"corresponding_institution_ids":["https://openalex.org/I65837984"],"apc_list":null,"apc_paid":null,"fwci":1.4691,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.85529699,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1161","last_page":"1164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9976999759674072,"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":0.9976999759674072,"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/T11448","display_name":"Face recognition and analysis","score":0.9976999759674072,"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"}},{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.9602000117301941,"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":0.7642935514450073},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.720035195350647},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.6742876172065735},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.6507408618927002},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6262612342834473},{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.5522218346595764},{"id":"https://openalex.org/keywords/active-appearance-model","display_name":"Active appearance model","score":0.5409231781959534},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5158397555351257},{"id":"https://openalex.org/keywords/three-dimensional-face-recognition","display_name":"Three-dimensional face recognition","score":0.47689107060432434},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4394236207008362},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.419084370136261},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3671216070652008},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3121557831764221},{"id":"https://openalex.org/keywords/face-detection","display_name":"Face detection","score":0.233392596244812},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.21802061796188354},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1590239703655243},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.06560751795768738}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7642935514450073},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.720035195350647},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6742876172065735},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.6507408618927002},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6262612342834473},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.5522218346595764},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.5409231781959534},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5158397555351257},{"id":"https://openalex.org/C88799230","wikidata":"https://www.wikidata.org/wiki/Q3398329","display_name":"Three-dimensional face recognition","level":5,"score":0.47689107060432434},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4394236207008362},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.419084370136261},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3671216070652008},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3121557831764221},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.233392596244812},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.21802061796188354},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1590239703655243},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.06560751795768738},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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":1,"locations":[{"id":"doi:10.1145/2393347.2396408","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2393347.2396408","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W82494927","https://openalex.org/W142803501","https://openalex.org/W196088823","https://openalex.org/W1597029646","https://openalex.org/W2029835507","https://openalex.org/W2032352564","https://openalex.org/W2083449369","https://openalex.org/W2124174353","https://openalex.org/W2141188246","https://openalex.org/W2148956009","https://openalex.org/W2172803778","https://openalex.org/W2405022146","https://openalex.org/W4285719527","https://openalex.org/W6603350892","https://openalex.org/W6607899525","https://openalex.org/W6657940589","https://openalex.org/W6713636154"],"related_works":["https://openalex.org/W1974357398","https://openalex.org/W2796042130","https://openalex.org/W2142490914","https://openalex.org/W1578309724","https://openalex.org/W2153462642","https://openalex.org/W394601115","https://openalex.org/W4212815228","https://openalex.org/W2068763531","https://openalex.org/W1852407300","https://openalex.org/W2777626350"],"abstract_inverted_index":{"As":[0],"one":[1],"of":[2,49,66],"the":[3,29,47,50,55,59,67,77,82,103,111,115,127],"techniques":[4],"for":[5],"robust":[6],"speech":[7,13,39],"recognition":[8,14,40,60,128],"under":[9],"noisy":[10],"environments,":[11],"audio-visual":[12],"(AVSR)":[15],"using":[16,105],"lip":[17,51],"dynamic":[18],"scene":[19],"information":[20,24],"together":[21],"with":[22],"audio":[23],"is":[25,79],"attracting":[26],"attention,":[27],"and":[28,58],"research":[30],"has":[31],"advanced":[32],"in":[33,37,75],"recent":[34],"years.":[35],"However,":[36],"visual":[38],"(VSR),":[41],"when":[42,114],"a":[43,87,124],"face":[44,78,116],"turns":[45],"sideways,":[46],"shape":[48],"as":[52],"viewed":[53,80,93,101],"from":[54,81,94,102],"camera":[56],"changes":[57,118],"accuracy":[61,129],"degrades":[62],"significantly.":[63,131],"Therefore,":[64],"many":[65],"conventional":[68],"VSR":[69,88],"methods":[70],"are":[71,100],"limited":[72],"to":[73,90,123],"situations":[74],"which":[76],"front.":[83],"This":[84],"paper":[85],"proposes":[86],"method":[89],"convert":[91],"faces":[92,98],"various":[95],"directions":[96],"into":[97],"that":[99],"front":[104],"Active":[106],"Appearance":[107],"Models":[108],"(AAM).":[109],"In":[110],"experiment,":[112],"even":[113],"direction":[117],"about":[119],"30":[120],"degrees":[121],"relative":[122],"frontal":[125],"view,":[126],"improved":[130]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
