{"id":"https://openalex.org/W2887292525","doi":"https://doi.org/10.1007/s12193-018-0267-1","title":"Multimodal speech recognition: increasing accuracy using high speed video data","display_name":"Multimodal speech recognition: increasing accuracy using high speed video data","publication_year":2018,"publication_date":"2018-08-01","ids":{"openalex":"https://openalex.org/W2887292525","doi":"https://doi.org/10.1007/s12193-018-0267-1","mag":"2887292525"},"language":"en","primary_location":{"id":"doi:10.1007/s12193-018-0267-1","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s12193-018-0267-1","pdf_url":null,"source":{"id":"https://openalex.org/S21279965","display_name":"Journal on Multimodal User Interfaces","issn_l":"1783-7677","issn":["1783-7677","1783-8738"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal on Multimodal User Interfaces","raw_type":"journal-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/A5013493484","display_name":"Denis Ivanko","orcid":"https://orcid.org/0000-0003-0412-7765"},"institutions":[{"id":"https://openalex.org/I4210103826","display_name":"St. Petersburg Institute for Informatics and Automation","ror":"https://ror.org/01ccb9w37","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210097085","https://openalex.org/I4210103826"]},{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]},{"id":"https://openalex.org/I196349391","display_name":"Universit\u00e4t Ulm","ror":"https://ror.org/032000t02","country_code":"DE","type":"education","lineage":["https://openalex.org/I196349391"]}],"countries":["DE","RU"],"is_corresponding":true,"raw_author_name":"Denis Ivanko","raw_affiliation_strings":["ITMO University, St. Petersburg, Russia","Institute of Communications Engineering, Ulm University, Ulm, Germany","St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, St. Petersburg, Russia"],"affiliations":[{"raw_affiliation_string":"ITMO University, St. Petersburg, Russia","institution_ids":["https://openalex.org/I173089394"]},{"raw_affiliation_string":"Institute of Communications Engineering, Ulm University, Ulm, Germany","institution_ids":["https://openalex.org/I196349391"]},{"raw_affiliation_string":"St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, St. Petersburg, Russia","institution_ids":["https://openalex.org/I4210103826"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032870944","display_name":"Alexey Karpov","orcid":"https://orcid.org/0000-0003-3424-652X"},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]},{"id":"https://openalex.org/I4210103826","display_name":"St. Petersburg Institute for Informatics and Automation","ror":"https://ror.org/01ccb9w37","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210097085","https://openalex.org/I4210103826"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Alexey Karpov","raw_affiliation_strings":["ITMO University, St. Petersburg, Russia","St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, St. Petersburg, Russia"],"affiliations":[{"raw_affiliation_string":"ITMO University, St. Petersburg, Russia","institution_ids":["https://openalex.org/I173089394"]},{"raw_affiliation_string":"St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, St. Petersburg, Russia","institution_ids":["https://openalex.org/I4210103826"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002620233","display_name":"Dmitrii Fedotov","orcid":null},"institutions":[{"id":"https://openalex.org/I196349391","display_name":"Universit\u00e4t Ulm","ror":"https://ror.org/032000t02","country_code":"DE","type":"education","lineage":["https://openalex.org/I196349391"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dmitrii Fedotov","raw_affiliation_strings":["Institute of Communications Engineering, Ulm University, Ulm, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Communications Engineering, Ulm University, Ulm, Germany","institution_ids":["https://openalex.org/I196349391"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024065203","display_name":"Irina Kipyatkova","orcid":"https://orcid.org/0000-0002-1264-4458"},"institutions":[{"id":"https://openalex.org/I4210103826","display_name":"St. Petersburg Institute for Informatics and Automation","ror":"https://ror.org/01ccb9w37","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210097085","https://openalex.org/I4210103826"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Irina Kipyatkova","raw_affiliation_strings":["St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, St. Petersburg, Russia"],"affiliations":[{"raw_affiliation_string":"St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, St. Petersburg, Russia","institution_ids":["https://openalex.org/I4210103826"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008249311","display_name":"Dmitry Ryumin","orcid":"https://orcid.org/0000-0002-7935-0569"},"institutions":[{"id":"https://openalex.org/I4210103826","display_name":"St. Petersburg Institute for Informatics and Automation","ror":"https://ror.org/01ccb9w37","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210097085","https://openalex.org/I4210103826"]},{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Dmitry Ryumin","raw_affiliation_strings":["ITMO University, St. Petersburg, Russia","St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, St. Petersburg, Russia"],"affiliations":[{"raw_affiliation_string":"ITMO University, St. Petersburg, Russia","institution_ids":["https://openalex.org/I173089394"]},{"raw_affiliation_string":"St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, St. Petersburg, Russia","institution_ids":["https://openalex.org/I4210103826"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023381873","display_name":"Dmitriy Ivanko","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103826","display_name":"St. Petersburg Institute for Informatics and Automation","ror":"https://ror.org/01ccb9w37","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210097085","https://openalex.org/I4210103826"]},{"id":"https://openalex.org/I196349391","display_name":"Universit\u00e4t Ulm","ror":"https://ror.org/032000t02","country_code":"DE","type":"education","lineage":["https://openalex.org/I196349391"]},{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["DE","RU"],"is_corresponding":false,"raw_author_name":"Dmitriy Ivanko","raw_affiliation_strings":["ITMO University, St. Petersburg, Russia","Institute of Communications Engineering, Ulm University, Ulm, Germany","St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, St. Petersburg, Russia"],"affiliations":[{"raw_affiliation_string":"ITMO University, St. Petersburg, Russia","institution_ids":["https://openalex.org/I173089394"]},{"raw_affiliation_string":"Institute of Communications Engineering, Ulm University, Ulm, Germany","institution_ids":["https://openalex.org/I196349391"]},{"raw_affiliation_string":"St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, St. Petersburg, Russia","institution_ids":["https://openalex.org/I4210103826"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110317553","display_name":"Wolfgang Minker","orcid":null},"institutions":[{"id":"https://openalex.org/I196349391","display_name":"Universit\u00e4t Ulm","ror":"https://ror.org/032000t02","country_code":"DE","type":"education","lineage":["https://openalex.org/I196349391"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wolfgang Minker","raw_affiliation_strings":["Institute of Communications Engineering, Ulm University, Ulm, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Communications Engineering, Ulm University, Ulm, Germany","institution_ids":["https://openalex.org/I196349391"]}]},{"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":"Milos Zelezny","raw_affiliation_strings":["University of West Bohemia, Plze\u0148, Czech Republic"],"affiliations":[{"raw_affiliation_string":"University of West Bohemia, Plze\u0148, Czech Republic","institution_ids":["https://openalex.org/I92715842"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5013493484"],"corresponding_institution_ids":["https://openalex.org/I173089394","https://openalex.org/I196349391","https://openalex.org/I4210103826"],"apc_list":{"value":2090,"currency":"EUR","value_usd":2690},"apc_paid":null,"fwci":2.3217,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.89518025,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"12","issue":"4","first_page":"319","last_page":"328"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9970999956130981,"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/T11309","display_name":"Music and Audio Processing","score":0.983299970626831,"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/computer-science","display_name":"Computer science","score":0.8759998679161072},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7638856172561646},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.574734628200531},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4994339942932129},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.48385632038116455},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43142464756965637},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.42819279432296753},{"id":"https://openalex.org/keywords/frame-rate","display_name":"Frame rate","score":0.42528748512268066},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.42524927854537964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4064321517944336},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.3972253203392029},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.1979849636554718},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11301743984222412}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8759998679161072},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7638856172561646},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.574734628200531},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4994339942932129},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.48385632038116455},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43142464756965637},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.42819279432296753},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.42528748512268066},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.42524927854537964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4064321517944336},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3972253203392029},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.1979849636554718},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11301743984222412},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s12193-018-0267-1","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s12193-018-0267-1","pdf_url":null,"source":{"id":"https://openalex.org/S21279965","display_name":"Journal on Multimodal User Interfaces","issn_l":"1783-7677","issn":["1783-7677","1783-8738"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal on Multimodal User Interfaces","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W73040245","https://openalex.org/W82494927","https://openalex.org/W101129729","https://openalex.org/W142945732","https://openalex.org/W147012460","https://openalex.org/W242871668","https://openalex.org/W1498911878","https://openalex.org/W1503808328","https://openalex.org/W1518556865","https://openalex.org/W1531976713","https://openalex.org/W1552461156","https://openalex.org/W1571194703","https://openalex.org/W1640878532","https://openalex.org/W1981758193","https://openalex.org/W1991123335","https://openalex.org/W1993087016","https://openalex.org/W2015394094","https://openalex.org/W2019898912","https://openalex.org/W2022799064","https://openalex.org/W2023100145","https://openalex.org/W2035777533","https://openalex.org/W2053101950","https://openalex.org/W2055098062","https://openalex.org/W2060510034","https://openalex.org/W2066339445","https://openalex.org/W2071828724","https://openalex.org/W2084237818","https://openalex.org/W2098923380","https://openalex.org/W2104263160","https://openalex.org/W2127015832","https://openalex.org/W2144513380","https://openalex.org/W2150387026","https://openalex.org/W2164450870","https://openalex.org/W2184188583","https://openalex.org/W2288112950","https://openalex.org/W2398828702","https://openalex.org/W2400745442","https://openalex.org/W2513259840","https://openalex.org/W2538953432","https://openalex.org/W2561675875","https://openalex.org/W2588678247","https://openalex.org/W2737429942","https://openalex.org/W2743529261","https://openalex.org/W2743709437","https://openalex.org/W2743900342","https://openalex.org/W2747419968","https://openalex.org/W2748586599","https://openalex.org/W2749046237","https://openalex.org/W3148981562","https://openalex.org/W3149793578","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W3159882232","https://openalex.org/W642007152","https://openalex.org/W2131711534","https://openalex.org/W2184127972","https://openalex.org/W2343205865","https://openalex.org/W2341426843","https://openalex.org/W2550171623","https://openalex.org/W2009814707"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
