{"id":"https://openalex.org/W2106937330","doi":"https://doi.org/10.1109/icme.2010.5583086","title":"Exploiting multimodal data fusion in robust speech recognition","display_name":"Exploiting multimodal data fusion in robust speech recognition","publication_year":2010,"publication_date":"2010-07-01","ids":{"openalex":"https://openalex.org/W2106937330","doi":"https://doi.org/10.1109/icme.2010.5583086","mag":"2106937330"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2010.5583086","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2010.5583086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Multimedia and Expo","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/A5029779616","display_name":"Panikos Heracleous","orcid":"https://orcid.org/0000-0002-7709-8195"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Panikos Heracleous","raw_affiliation_strings":["Intelligent Robotics and Communication Laboratories, ATR, Japan","ATR, Intelligent Robotics and Communication Laboratories, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Robotics and Communication Laboratories, ATR, Japan","institution_ids":[]},{"raw_affiliation_string":"ATR, Intelligent Robotics and Communication Laboratories, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058305510","display_name":"Pierre Badin","orcid":"https://orcid.org/0000-0001-7440-820X"},"institutions":[{"id":"https://openalex.org/I106785703","display_name":"Institut polytechnique de Grenoble","ror":"https://ror.org/05sbt2524","country_code":"FR","type":"education","lineage":["https://openalex.org/I106785703","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210124956","display_name":"GIPSA-Lab","ror":"https://ror.org/02wrme198","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Pierre Badin","raw_affiliation_strings":["GIPSA-Laboratory, Speech and Cognition Department, UMR 5216, CNRS-Grenoble University, France","GIPSA-Lab, Speech and Cognition Department, UMR 5216, CNRS - Grenoble University - France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GIPSA-Laboratory, Speech and Cognition Department, UMR 5216, CNRS-Grenoble University, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006"]},{"raw_affiliation_string":"GIPSA-Lab, Speech and Cognition Department, UMR 5216, CNRS - Grenoble University - France","institution_ids":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071432574","display_name":"G\u00e9rard Bailly","orcid":"https://orcid.org/0000-0002-6053-0818"},"institutions":[{"id":"https://openalex.org/I106785703","display_name":"Institut polytechnique de Grenoble","ror":"https://ror.org/05sbt2524","country_code":"FR","type":"education","lineage":["https://openalex.org/I106785703","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210124956","display_name":"GIPSA-Lab","ror":"https://ror.org/02wrme198","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Gerard Bailly","raw_affiliation_strings":["GIPSA-Laboratory, Speech and Cognition Department, UMR 5216, CNRS-Grenoble University, France","GIPSA-Lab, Speech and Cognition Department, UMR 5216, CNRS - Grenoble University - France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GIPSA-Laboratory, Speech and Cognition Department, UMR 5216, CNRS-Grenoble University, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006"]},{"raw_affiliation_string":"GIPSA-Lab, Speech and Cognition Department, UMR 5216, CNRS - Grenoble University - France","institution_ids":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058513264","display_name":"Norihiro Hagita","orcid":"https://orcid.org/0000-0001-8007-4701"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Norihiro Hagita","raw_affiliation_strings":["Intelligent Robotics and Communication Laboratories, ATR, Japan","ATR, Intelligent Robotics and Communication Laboratories, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Robotics and Communication Laboratories, ATR, Japan","institution_ids":[]},{"raw_affiliation_string":"ATR, Intelligent Robotics and Communication Laboratories, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"112","issue":null,"first_page":"568","last_page":"572"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9937999844551086,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8478598594665527},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.846098005771637},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7751468420028687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47959887981414795},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.479183554649353},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.47538816928863525},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.47038522362709045},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4646645784378052},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4635526239871979},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.4568648040294647},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.44853147864341736},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4275358319282532},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4248409569263458},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.37501218914985657}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8478598594665527},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.846098005771637},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7751468420028687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47959887981414795},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.479183554649353},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.47538816928863525},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.47038522362709045},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4646645784378052},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4635526239871979},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.4568648040294647},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.44853147864341736},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4275358319282532},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4248409569263458},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.37501218914985657},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icme.2010.5583086","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2010.5583086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-00508288v1","is_oa":false,"landing_page_url":"https://hal.science/hal-00508288","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICME 2010 - IEEE International Conference on Multimedia and Expo, Jul 2010, Singapour, Singapore. in press","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W96337034","https://openalex.org/W1211067074","https://openalex.org/W1540787848","https://openalex.org/W1558063916","https://openalex.org/W1589867908","https://openalex.org/W1922557984","https://openalex.org/W1999209169","https://openalex.org/W2028971373","https://openalex.org/W2039640471","https://openalex.org/W2055115647","https://openalex.org/W2095026407","https://openalex.org/W2096391593","https://openalex.org/W2109455879","https://openalex.org/W2160594205","https://openalex.org/W2395296935","https://openalex.org/W2409998918","https://openalex.org/W3014296750","https://openalex.org/W4302613066","https://openalex.org/W4320342197","https://openalex.org/W6635242571","https://openalex.org/W6683361140","https://openalex.org/W6775121089","https://openalex.org/W6845679800"],"related_works":["https://openalex.org/W2157598242","https://openalex.org/W3159882232","https://openalex.org/W4241650944","https://openalex.org/W2620660273","https://openalex.org/W4243125559","https://openalex.org/W1541790149","https://openalex.org/W2964829415","https://openalex.org/W2131711534","https://openalex.org/W642007152","https://openalex.org/W2341426843"],"abstract_inverted_index":{"This":[0],"article":[1],"introduces":[2],"automatic":[3,48],"speech":[4,37,64,78,84,106],"recognition":[5,50,86],"based":[6],"on":[7],"Electro-Magnetic":[8],"Articulography":[9],"(EMA).":[10],"Movements":[11],"of":[12,58,98],"the":[13,56,59,96,99],"tongue,":[14],"lips,":[15],"and":[16,35,72,85],"jaw":[17],"are":[18,25,52],"tracked":[19],"by":[20],"an":[21,104],"EMA":[22,60,83,100],"device,":[23],"which":[24],"used":[26],"as":[27],"features":[28],"to":[29,54,62],"create":[30],"Hidden":[31],"Markov":[32],"Models":[33],"(HMM)":[34],"recognize":[36],"only":[38],"from":[39],"articulation,":[40],"that":[41,95],"is,":[42],"without":[43],"any":[44],"audio":[45,77,105],"information.":[46],"Also,":[47],"phoneme":[49],"experiments":[51,87],"conducted":[53],"examine":[55],"contribution":[57],"parameters":[61,101],"robust":[63],"recognition.":[65],"Using":[66],"feature":[67],"fusion,":[68,71],"multistream":[69],"HMM":[70],"late":[73],"fusion":[74],"methods,":[75],"noisy":[76,110],"has":[79],"been":[80,89],"integrated":[81],"with":[82],"have":[88],"conducted.":[90],"The":[91],"achieved":[92],"results":[93],"show":[94],"integration":[97],"significantly":[102],"increases":[103],"recognizer's":[107],"accuracy,":[108],"in":[109],"environments.":[111]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}