{"id":"https://openalex.org/W73040245","doi":"https://doi.org/10.21437/interspeech.2010-710","title":"Viseme-dependent weight optimization for CHMM-based audio-visual speech recognition","display_name":"Viseme-dependent weight optimization for CHMM-based audio-visual speech recognition","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W73040245","doi":"https://doi.org/10.21437/interspeech.2010-710","mag":"73040245"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-710","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-710","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","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/A5032870944","display_name":"Alexey Karpov","orcid":"https://orcid.org/0000-0003-3424-652X"},"institutions":[{"id":"https://openalex.org/I1313323035","display_name":"Russian Academy of Sciences","ror":"https://ror.org/05qrfxd25","country_code":"RU","type":"funder","lineage":["https://openalex.org/I1313323035"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Alexey Karpov","raw_affiliation_strings":["Russian Academy of Sciences, Moscow, Russia"],"affiliations":[{"raw_affiliation_string":"Russian Academy of Sciences, Moscow, Russia","institution_ids":["https://openalex.org/I1313323035"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007008031","display_name":"Andrey Ronzhin","orcid":"https://orcid.org/0000-0002-8903-3508"},"institutions":[{"id":"https://openalex.org/I1313323035","display_name":"Russian Academy of Sciences","ror":"https://ror.org/05qrfxd25","country_code":"RU","type":"funder","lineage":["https://openalex.org/I1313323035"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Andrey Ronzhin","raw_affiliation_strings":["Russian Academy of Sciences, Moscow, Russia"],"affiliations":[{"raw_affiliation_string":"Russian Academy of Sciences, Moscow, Russia","institution_ids":["https://openalex.org/I1313323035"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039443541","display_name":"Konstantin Markov","orcid":"https://orcid.org/0000-0003-1838-4789"},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Konstantin Markov","raw_affiliation_strings":["University of Aizu, Fukushima, Japan"],"affiliations":[{"raw_affiliation_string":"University of Aizu, Fukushima, Japan","institution_ids":["https://openalex.org/I141591182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031485141","display_name":"Milo\u0161 \u017delezn\u00fd","orcid":"https://orcid.org/0000-0003-1695-4370"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Milo\u0161 \u017delezn\u00fd","raw_affiliation_strings":["University of West Bohemia, Pilsen, Czechia"],"affiliations":[{"raw_affiliation_string":"University of West Bohemia, Pilsen, Czechia","institution_ids":["https://openalex.org/I92715842"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5032870944"],"corresponding_institution_ids":["https://openalex.org/I1313323035"],"apc_list":null,"apc_paid":null,"fwci":0.6743,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.65283361,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2678","last_page":"2681"},"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":0.9932000041007996,"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":0.9919000267982483,"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":0.8081057071685791},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7668818235397339},{"id":"https://openalex.org/keywords/asynchrony","display_name":"Asynchrony (computer programming)","score":0.7554254531860352},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7396107316017151},{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.47044888138771057},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43480274081230164},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4226647615432739},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.415315181016922},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.41361498832702637},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3459150791168213},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.22230321168899536},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.08271408081054688}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8081057071685791},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7668818235397339},{"id":"https://openalex.org/C2779019669","wikidata":"https://www.wikidata.org/wiki/Q25203946","display_name":"Asynchrony (computer programming)","level":3,"score":0.7554254531860352},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7396107316017151},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.47044888138771057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43480274081230164},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4226647615432739},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.415315181016922},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.41361498832702637},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3459150791168213},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.22230321168899536},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.08271408081054688},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2010-710","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-710","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W123443704","https://openalex.org/W1605167416","https://openalex.org/W1869491686","https://openalex.org/W2096443118","https://openalex.org/W2098562545","https://openalex.org/W2108101067","https://openalex.org/W2112348857","https://openalex.org/W2133115605","https://openalex.org/W2164450870","https://openalex.org/W3099202502","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2534656837","https://openalex.org/W1974357398","https://openalex.org/W2796042130","https://openalex.org/W2142490914","https://openalex.org/W4253235840","https://openalex.org/W2488941600","https://openalex.org/W1531133616","https://openalex.org/W4212815228","https://openalex.org/W1852407300","https://openalex.org/W2777626350"],"abstract_inverted_index":{"The":[0],"aim":[1],"of":[2,12,22,26,44,51,74,100],"the":[3,13,42,49,80],"present":[4],"study":[5],"is":[6],"to":[7,79,97],"investigate":[8],"some":[9],"key":[10],"challenges":[11],"audio-visual":[14,89,108],"speech":[15,30,55],"recognition":[16],"technology,":[17],"such":[18],"as":[19,32,34],"asynchrony":[20],"modeling":[21],"multimodal":[23,106],"speech,":[24,107],"estimation":[25],"auditory":[27],"and":[28],"visual":[29,75],"significance,":[31],"well":[33],"stream":[35,90],"weight":[36],"optimization.":[37],"Our":[38],"research":[39],"shows":[40],"that":[41,87],"use":[43],"viseme-dependent":[45],"significance":[46,114],"weights":[47,91,115],"improves":[48],"performance":[50],"state":[52,61],"asynchronous":[53],"CHMM-based":[54],"recognizer.":[56],"In":[57],"addition,":[58],"for":[59,92],"a":[60],"synchronous":[62],"MSHMMbased":[63],"recognizer,":[64],"fewer":[65],"errors":[66],"can":[67],"be":[68],"achieved":[69],"using":[70],"stationary":[71],"time":[72],"delays":[73],"data":[76],"with":[77],"respect":[78],"corresponding":[81],"audio":[82],"signal.":[83],"Evaluation":[84],"experiments":[85],"showed":[86],"individual":[88],"each":[93],"visemephoneme":[94],"pair":[95],"lead":[96],"relative":[98],"reduction":[99],"WER":[101],"by":[102],"20%.":[103],"Index":[104],"Terms:":[105],"processing,":[109],"Hidden":[110],"Markov":[111],"Models,":[112],"asynchrony,":[113]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
