{"id":"https://openalex.org/W2061052028","doi":"https://doi.org/10.1109/ispacs.2012.6473460","title":"Speaker dependent visual word recognition by using sequential mouth shape codes","display_name":"Speaker dependent visual word recognition by using sequential mouth shape codes","publication_year":2012,"publication_date":"2012-11-01","ids":{"openalex":"https://openalex.org/W2061052028","doi":"https://doi.org/10.1109/ispacs.2012.6473460","mag":"2061052028"},"language":"en","primary_location":{"id":"doi:10.1109/ispacs.2012.6473460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispacs.2012.6473460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 International Symposium on Intelligent Signal Processing and Communications Systems","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/A5059483903","display_name":"Takuro Tasaka","orcid":null},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takuro Tasaka","raw_affiliation_strings":["Department of System Design Engineering, Keio University, Yokohama, Japan","Department of System Design Engineering, Keio University, 3\u201014\u20101, Hiyoshi, Yokohama 223\u20108522, Japan"],"affiliations":[{"raw_affiliation_string":"Department of System Design Engineering, Keio University, Yokohama, Japan","institution_ids":["https://openalex.org/I203951103"]},{"raw_affiliation_string":"Department of System Design Engineering, Keio University, 3\u201014\u20101, Hiyoshi, Yokohama 223\u20108522, Japan","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105504673","display_name":"Nozomu Hamada","orcid":null},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nozomu Hamada","raw_affiliation_strings":["Department of System Design Engineering, Keio University, Yokohama, Japan","Department of System Design Engineering, Keio University, 3\u201014\u20101, Hiyoshi, Yokohama 223\u20108522, Japan"],"affiliations":[{"raw_affiliation_string":"Department of System Design Engineering, Keio University, Yokohama, Japan","institution_ids":["https://openalex.org/I203951103"]},{"raw_affiliation_string":"Department of System Design Engineering, Keio University, 3\u201014\u20101, Hiyoshi, Yokohama 223\u20108522, Japan","institution_ids":["https://openalex.org/I203951103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5059483903"],"corresponding_institution_ids":["https://openalex.org/I203951103"],"apc_list":null,"apc_paid":null,"fwci":0.2482,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.55551328,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"96","last_page":"101"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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/T11447","display_name":"Blind Source Separation Techniques","score":0.9883999824523926,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9824000000953674,"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/speech-recognition","display_name":"Speech recognition","score":0.8307050466537476},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7845388650894165},{"id":"https://openalex.org/keywords/consonant","display_name":"Consonant","score":0.5607393980026245},{"id":"https://openalex.org/keywords/word-recognition","display_name":"Word recognition","score":0.5266435146331787},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.511237382888794},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.49086982011795044},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46189084649086},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4483897089958191},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.4104442596435547},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3598310649394989},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3563305139541626},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09277874231338501}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8307050466537476},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7845388650894165},{"id":"https://openalex.org/C2778203577","wikidata":"https://www.wikidata.org/wiki/Q38035","display_name":"Consonant","level":3,"score":0.5607393980026245},{"id":"https://openalex.org/C150856459","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word recognition","level":3,"score":0.5266435146331787},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.511237382888794},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.49086982011795044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46189084649086},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4483897089958191},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.4104442596435547},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3598310649394989},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3563305139541626},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09277874231338501},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ispacs.2012.6473460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispacs.2012.6473460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 International Symposium on Intelligent Signal Processing and Communications Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1531133616","https://openalex.org/W1592480967","https://openalex.org/W1985605296","https://openalex.org/W2041180218","https://openalex.org/W2088109224","https://openalex.org/W2147176022","https://openalex.org/W2152558472","https://openalex.org/W2156332321","https://openalex.org/W2320085336"],"related_works":["https://openalex.org/W1964706935","https://openalex.org/W2020946215","https://openalex.org/W2801025542","https://openalex.org/W2165258585","https://openalex.org/W1966580183","https://openalex.org/W2083136263","https://openalex.org/W4213283234","https://openalex.org/W4252296115","https://openalex.org/W2373394249","https://openalex.org/W1989026474"],"abstract_inverted_index":{"Visual":[0],"speech":[1,12,24],"recognition":[2,13,25,97,142],"or":[3],"lip":[4,49,96],"reading":[5,50],"is":[6,26,44,78,114],"an":[7,45],"approach":[8,47],"for":[9,34,51,83],"noise":[10],"robust":[11],"by":[14,56,99],"adding":[15],"speaker's":[16],"visual":[17],"cues":[18],"to":[19,28,106,116],"audio":[20],"information.":[21],"Basically":[22],"visual-only":[23],"applicable":[27],"speaker":[29],"verification":[30],"and":[31,67,86,101],"multimedia":[32],"interface":[33],"supporting":[35],"speaking":[36],"impaired":[37],"person.":[38],"The":[39,110,132],"sequential":[40,124],"mouth-shape":[41,104],"code":[42],"method":[43,77,112],"effective":[46],"of":[48,60,75,121],"particularly":[52],"uttered":[53],"Japanese":[54],"words":[55,119],"utilizing":[57],"two":[58],"kinds":[59],"distinctive":[61],"mouth":[62,69],"shapes,":[63,70],"known":[64],"as":[65],"first":[66],"last":[68],"appeared":[71],"intermittently.":[72],"One":[73],"advantage":[74],"this":[76],"its":[79],"low":[80],"computational":[81],"burden":[82],"the":[84,122,137,145],"learning":[85],"word":[87,95],"registration":[88],"processes.":[89],"This":[90],"paper":[91],"proposes":[92],"a":[93],"novel":[94],"system":[98,139],"detecting":[100],"determining":[102],"initial":[103],"codes":[105,126],"recognize":[107],"uttering":[108],"consonants.":[109],"proposed":[111,138],"eventually":[113],"able":[115],"discriminate":[117],"different":[118,129],"consisting":[120],"same":[123],"vowel":[125],"though":[127],"containing":[128],"consonant":[130],"codes.":[131],"conducted":[133],"experiments":[134],"demonstrate":[135],"that":[136],"provides":[140],"higher":[141],"rate":[143],"than":[144],"conventional":[146],"ones.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}
