{"id":"https://openalex.org/W2116497041","doi":"https://doi.org/10.1109/iros.2007.4399300","title":"Coarse speech recognition by audio-visual integration based on missing feature theory","display_name":"Coarse speech recognition by audio-visual integration based on missing feature theory","publication_year":2007,"publication_date":"2007-10-01","ids":{"openalex":"https://openalex.org/W2116497041","doi":"https://doi.org/10.1109/iros.2007.4399300","mag":"2116497041"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2007.4399300","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2007.4399300","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":"proceedings-article"},"type":"conference-paper","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/A5063146181","display_name":"Tomoaki Koiwa","orcid":null},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoaki Koiwa","raw_affiliation_strings":["Graduate School of Information Science and Engineering, Honda Research Institute Japan Company Limited, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Engineering, Honda Research Institute Japan Company Limited, Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091708408","display_name":"Kazuhiro Nakadai","orcid":"https://orcid.org/0000-0002-6134-4558"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhiro Nakadai","raw_affiliation_strings":["Graduate School of Information Science and Engineering, Honda Research Institute Japan Company Limited, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Engineering, Honda Research Institute Japan Company Limited, Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001435105","display_name":"Jun\u2010ichi Imura","orcid":"https://orcid.org/0000-0002-9273-134X"},"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":"Jun-ichi Imura","raw_affiliation_strings":["Graduate School of Information Science and Engineering, Tokyo Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Engineering, Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8101,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.85745891,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1751","last_page":"1756"},"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":0.9984999895095825,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8393214344978333},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7870181202888489},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7780013680458069},{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.6789889335632324},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6756954193115234},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5451809763908386},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49986767768859863},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4528837502002716},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4246407747268677},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4224185347557068},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4156065285205841},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.41514796018600464},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.3352254629135132}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8393214344978333},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7870181202888489},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7780013680458069},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.6789889335632324},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6756954193115234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5451809763908386},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49986767768859863},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4528837502002716},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4246407747268677},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4224185347557068},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4156065285205841},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.41514796018600464},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3352254629135132},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros.2007.4399300","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2007.4399300","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W43463692","https://openalex.org/W289804034","https://openalex.org/W1565021911","https://openalex.org/W1604074770","https://openalex.org/W1904457459","https://openalex.org/W1922557984","https://openalex.org/W1970533835","https://openalex.org/W2013699441","https://openalex.org/W2026257980","https://openalex.org/W2055957740","https://openalex.org/W2095941401","https://openalex.org/W2107644596","https://openalex.org/W2116708935","https://openalex.org/W2121065047","https://openalex.org/W2129800309","https://openalex.org/W2146871184","https://openalex.org/W2147673046","https://openalex.org/W2147737628","https://openalex.org/W2150444217","https://openalex.org/W2150946027","https://openalex.org/W2542469892","https://openalex.org/W6601839116","https://openalex.org/W6610316520","https://openalex.org/W6633899200","https://openalex.org/W6678139903"],"related_works":["https://openalex.org/W2157598242","https://openalex.org/W2131711534","https://openalex.org/W1583620810","https://openalex.org/W2341426843","https://openalex.org/W1911859126","https://openalex.org/W642007152","https://openalex.org/W4387712795","https://openalex.org/W2110852049","https://openalex.org/W2138377320","https://openalex.org/W2794873916"],"abstract_inverted_index":{"Audio-visual":[0],"speech":[1,13,99],"recognition":[2,14,100],"(AVSR)":[3],"is":[4,58,80],"a":[5,22,81],"promising":[6],"approach":[7],"to":[8,45,66],"improve":[9],"noise":[10,107],"robustness":[11,108],"of":[12,109],"in":[15,36],"the":[16,37,106],"real":[17,38],"world.":[18],"A":[19],"phoneme":[20,86],"and":[21,29,73,87],"viseme":[23,88],"are":[24,41],"used":[25],"as":[26],"an":[27],"auditory":[28],"visual":[30,74],"unit":[31],"for":[32,76],"AVSR,":[33],"respectively.":[34],"However,":[35],"world,":[39],"they":[40],"often":[42],"misclassified":[43],"due":[44],"additional":[46],"input":[47],"noises.":[48],"To":[49],"solve":[50],"this":[51],"problem,":[52],"we":[53],"propose":[54],"two":[55],"approaches.":[56],"One":[57],"audio-visual":[59,98],"integration":[60],"based":[61,90,101],"on":[62,91,102],"missing":[63,69],"feature":[64],"theory":[65],"cope":[67],"with":[68],"or":[70],"unreliable":[71],"audio":[72],"features":[75],"recognition.":[77,93],"The":[78],"other":[79],"biologically-inspired":[82],"approach,":[83],"that":[84,97],"is,":[85],"grouping":[89],"coarse-to-fine":[92],"Preliminary":[94],"experiments":[95],"show":[96],"these":[103],"approaches":[104],"improves":[105],"AVSR":[110],"drastically.":[111]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}