{"id":"https://openalex.org/W1598947717","doi":"https://doi.org/10.23919/ecc.1999.7099790","title":"Fusion of audio and video data by neural networks for robust vowel recognition","display_name":"Fusion of audio and video data by neural networks for robust vowel recognition","publication_year":1999,"publication_date":"1999-08-01","ids":{"openalex":"https://openalex.org/W1598947717","doi":"https://doi.org/10.23919/ecc.1999.7099790","mag":"1598947717"},"language":"en","primary_location":{"id":"doi:10.23919/ecc.1999.7099790","is_oa":false,"landing_page_url":"https://doi.org/10.23919/ecc.1999.7099790","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"1999 European Control Conference (ECC)","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/A5091747480","display_name":"Kristian Kroschel","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]},{"id":"https://openalex.org/I70886390","display_name":"Karlsruhe University of Applied Sciences","ror":"https://ror.org/01c0m1t63","country_code":"DE","type":"education","lineage":["https://openalex.org/I70886390"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"K. Kroschel","raw_affiliation_strings":["Universit&#x00E4;t Karlsruhe (Technische Hochschule), Kaiserstra&#x00DF;e 12, 76128 Karlsruhe, Germany","Universit\u00e4t Karlsruhe (Technische Hochschule), Kaiserstra\u00dfe 12, 76128 Karlsruhe, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit&#x00E4;t Karlsruhe (Technische Hochschule), Kaiserstra&#x00DF;e 12, 76128 Karlsruhe, Germany","institution_ids":["https://openalex.org/I70886390"]},{"raw_affiliation_string":"Universit\u00e4t Karlsruhe (Technische Hochschule), Kaiserstra\u00dfe 12, 76128 Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080195291","display_name":"Moheb Mekhaiel","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]},{"id":"https://openalex.org/I70886390","display_name":"Karlsruhe University of Applied Sciences","ror":"https://ror.org/01c0m1t63","country_code":"DE","type":"education","lineage":["https://openalex.org/I70886390"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"M. S. Mekhaiel","raw_affiliation_strings":["Universit&#x00E4;t Karlsruhe (Technische Hochschule), Kaiserstra&#x00DF;e 12, 76128 Karlsruhe, Germany","Universit\u00e4t Karlsruhe (Technische Hochschule), Kaiserstra\u00dfe 12, 76128 Karlsruhe, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit&#x00E4;t Karlsruhe (Technische Hochschule), Kaiserstra&#x00DF;e 12, 76128 Karlsruhe, Germany","institution_ids":["https://openalex.org/I70886390"]},{"raw_affiliation_string":"Universit\u00e4t Karlsruhe (Technische Hochschule), Kaiserstra\u00dfe 12, 76128 Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108205978","display_name":"F. Berthommier","orcid":null},"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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"F. Berthommier","raw_affiliation_strings":["Institut de la Communication Parl&#x00E9;e/INPG, 46, Av. F&#x00E9;lix Viallet, 38031 Grenoble, France","Institut de la Communication Parl\u00e9e/INPG, 46, Av. F\u00e9lix Viallet, 38031 Grenoble, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut de la Communication Parl&#x00E9;e/INPG, 46, Av. F&#x00E9;lix Viallet, 38031 Grenoble, France","institution_ids":["https://openalex.org/I106785703"]},{"raw_affiliation_string":"Institut de la Communication Parl\u00e9e/INPG, 46, Av. F\u00e9lix Viallet, 38031 Grenoble, France","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0948439,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3029","last_page":"3034"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9959999918937683,"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":0.9959999918937683,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9836000204086304,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7622789144515991},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.7533307075500488},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7216387987136841},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5549985766410828},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5535523891448975},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5213064551353455},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4980168342590332},{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.43680691719055176},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.420066773891449},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3890434205532074},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3555205166339874},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3520934581756592},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.270710825920105}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7622789144515991},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.7533307075500488},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7216387987136841},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5549985766410828},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5535523891448975},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5213064551353455},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4980168342590332},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.43680691719055176},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.420066773891449},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3890434205532074},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3555205166339874},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3520934581756592},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.270710825920105},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/ecc.1999.7099790","is_oa":false,"landing_page_url":"https://doi.org/10.23919/ecc.1999.7099790","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"1999 European Control Conference (ECC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W162646390","https://openalex.org/W201959675","https://openalex.org/W1565415357","https://openalex.org/W1587950272","https://openalex.org/W1910700357","https://openalex.org/W2084844503","https://openalex.org/W2099947851","https://openalex.org/W2104095591","https://openalex.org/W2121936028","https://openalex.org/W2125713050","https://openalex.org/W2125848778","https://openalex.org/W2159686933","https://openalex.org/W2914885528"],"related_works":["https://openalex.org/W2796042130","https://openalex.org/W2142490914","https://openalex.org/W2741151796","https://openalex.org/W2306241824","https://openalex.org/W1974357398","https://openalex.org/W2963024054","https://openalex.org/W2384651879","https://openalex.org/W4212815228","https://openalex.org/W1852407300","https://openalex.org/W2777626350"],"abstract_inverted_index":{"The":[0,73,100],"performance":[1],"of":[2,20,48,66,76,85,115],"speech":[3,74],"recognition":[4,34,47],"systems":[5],"decreases":[6],"dramatically":[7],"in":[8,39],"noisy":[9],"environments.":[10],"A":[11],"robust":[12],"human-computer":[13],"interaction":[14],"system":[15,35],"should":[16],"therefore":[17],"make":[18],"use":[19],"both,":[21],"acoustic":[22],"and":[23,58,105],"visual":[24],"signals.":[25],"In":[26],"this":[27],"paper":[28],"we":[29],"present":[30],"an":[31],"automatic":[32],"vowel":[33,79],"which":[36],"can":[37],"perform":[38],"quasi":[40],"real-time.":[41],"We":[42],"focus":[43],"mainly":[44],"on":[45],"the":[46,64,67,77,82,86,97,111,116],"5":[49],"different":[50],"German":[51],"vowels":[52],"(a,":[53],"e,":[54],"i,":[55],"o,":[56],"u)":[57],"their":[59],"corresponding":[60],"visemes":[61],"(images).":[62],"First":[63],"position":[65],"continuously":[68],"moving":[69],"face":[70,101,117],"is":[71,103],"determined.":[72],"parameters":[75,84],"spoken":[78],"along":[80],"with":[81],"model":[83],"lip's":[87],"image":[88],"are":[89,118],"fed":[90],"to":[91,95],"a":[92],"neural":[93],"network":[94],"recognize":[96],"uttered":[98],"vowel.":[99],"tracking":[102],"shape-independent":[104],"hence":[106],"no":[107],"special":[108],"requirements":[109],"concerning":[110],"color":[112],"or":[113],"shape":[114],"needed.":[119]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
