{"id":"https://openalex.org/W2151925976","doi":"https://doi.org/10.1109/iscslp.2010.5684915","title":"Audio visual speech recognition based on multi-stream DBN models with Articulatory Features","display_name":"Audio visual speech recognition based on multi-stream DBN models with Articulatory Features","publication_year":2010,"publication_date":"2010-11-01","ids":{"openalex":"https://openalex.org/W2151925976","doi":"https://doi.org/10.1109/iscslp.2010.5684915","mag":"2151925976"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2010.5684915","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684915","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th International Symposium on Chinese Spoken Language Processing","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/A5102021514","display_name":"Dongmei Jiang","orcid":"https://orcid.org/0000-0002-6238-8499"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dong-mei Jiang","raw_affiliation_strings":["Shaanxi Provincial Key Laboratory on Speech, Image and Information Processing, School of Computer, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Shaanxi Provincial Key Laboratory on Speech, Image and Information Processing, School of Computer, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046523454","display_name":"Peng Wu","orcid":"https://orcid.org/0000-0001-6259-4703"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Wu","raw_affiliation_strings":["Shaanxi Provincial Key Laboratory on Speech, Image and Information Processing, School of Computer, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Shaanxi Provincial Key Laboratory on Speech, Image and Information Processing, School of Computer, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063831487","display_name":"Feng-na Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Feng-na Wang","raw_affiliation_strings":["Department ETRO, Vrije Universiteit Brussel, Brussels, Belgium"],"affiliations":[{"raw_affiliation_string":"Department ETRO, Vrije Universiteit Brussel, Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073820422","display_name":"Hichem Sahli","orcid":"https://orcid.org/0000-0002-1774-2970"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Hichem Sahli","raw_affiliation_strings":["Department ETRO, Vrije Universiteit Brussel, Brussels, Belgium"],"affiliations":[{"raw_affiliation_string":"Department ETRO, Vrije Universiteit Brussel, Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109242855","display_name":"W. Verhelst","orcid":null},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Wer Verhelst","raw_affiliation_strings":["Department ETRO, Vrije Universiteit Brussel, Brussels, Belgium"],"affiliations":[{"raw_affiliation_string":"Department ETRO, Vrije Universiteit Brussel, Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102021514"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.3383,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.61652273,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"190","last_page":"193"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.998199999332428,"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":0.9955000281333923,"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/dynamic-bayesian-network","display_name":"Dynamic Bayesian network","score":0.7962900400161743},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7069559693336487},{"id":"https://openalex.org/keywords/deep-belief-network","display_name":"Deep belief network","score":0.6460800170898438},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6277655959129333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5519015789031982},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5335263609886169},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5140860676765442},{"id":"https://openalex.org/keywords/asynchrony","display_name":"Asynchrony (computer programming)","score":0.5124004483222961},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4169726073741913},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3883078694343567},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.26995986700057983},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.2675425410270691}],"concepts":[{"id":"https://openalex.org/C82142266","wikidata":"https://www.wikidata.org/wiki/Q3456604","display_name":"Dynamic Bayesian network","level":3,"score":0.7962900400161743},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7069559693336487},{"id":"https://openalex.org/C97385483","wikidata":"https://www.wikidata.org/wiki/Q16954980","display_name":"Deep belief network","level":3,"score":0.6460800170898438},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6277655959129333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5519015789031982},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5335263609886169},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5140860676765442},{"id":"https://openalex.org/C2779019669","wikidata":"https://www.wikidata.org/wiki/Q25203946","display_name":"Asynchrony (computer programming)","level":3,"score":0.5124004483222961},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4169726073741913},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3883078694343567},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.26995986700057983},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.2675425410270691},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iscslp.2010.5684915","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684915","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:vubissmart:VUBISSMART:2000:62244","is_oa":false,"landing_page_url":"https://biblio.vub.ac.be/vubir/audio-visual-speech-recognition-based-on-multistream-dbn-models-with-articulatory-features(355f8c3c-0c8c-4160-b5e4-d1ce6b281636).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306402573","display_name":"VUBIR (Vrije Universiteit Brussel)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I13469542","host_organization_name":"Vrije Universiteit Brussel","host_organization_lineage":["https://openalex.org/I13469542"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2121486117","https://openalex.org/W2148226542","https://openalex.org/W2157827878","https://openalex.org/W2164450870","https://openalex.org/W2167159094","https://openalex.org/W4244018879","https://openalex.org/W6684209796"],"related_works":["https://openalex.org/W2017210410","https://openalex.org/W1993009522","https://openalex.org/W1530536511","https://openalex.org/W2585432886","https://openalex.org/W2165991108","https://openalex.org/W1995792634","https://openalex.org/W3082895349","https://openalex.org/W2565516711","https://openalex.org/W3004069267","https://openalex.org/W2135672910"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2],"multi-stream":[3,100],"Dynamic":[4],"Bayesian":[5],"Network":[6],"model":[7,55,61,75,102],"with":[8,50,81],"Articulatory":[9],"Features":[10],"(AF_AV_DBN)":[11],"for":[12,113],"audio":[13,41,98,109],"visual":[14,42,99],"speech":[15],"recognition.":[16],"Conditional":[17],"probability":[18],"distributions":[19],"of":[20,90,94,107,118],"the":[21,26,29,51,64,68,73,77,97,105,108,116,120],"nodes":[22],"are":[23,36],"defined":[24],"considering":[25],"asynchronies":[27],"between":[28,67],"articulatory":[30],"features":[31],"(AFs).":[32],"Speech":[33],"recognition":[34,79,83,121],"experiments":[35],"carried":[37],"out":[38],"on":[39],"an":[40],"connected":[43],"digit":[44],"database.":[45],"Results":[46],"show":[47],"that":[48],"comparing":[49],"state":[52,58],"synchronous":[53],"DBN":[54,60],"(SS_DBN)":[56],"and":[57,92],"asynchronous":[59],"(SA_DBN),":[62],"when":[63],"asynchrony":[65],"constraint":[66],"AFs":[69],"is":[70,123],"appropriately":[71],"set,":[72],"AF_AV_DBN":[74,101],"gets":[76],"highest":[78],"rates,":[80],"average":[82],"rate":[84,122],"improved":[85,124],"to":[86,127],"89.38%":[87],"from":[88,125],"87.02%":[89],"SS_DBN":[91],"88.32%":[93],"SA_DBN.":[95],"Moreover,":[96],"greatly":[103],"improves":[104],"robustness":[106],"only":[110],"AF_A_DBN":[111],"model,":[112],"example,":[114],"under":[115],"noise":[117],"-10dB,":[119],"20.75%":[126],"76.24%.":[128]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}