{"id":"https://openalex.org/W124086577","doi":"https://doi.org/10.21437/icslp.1994-139","title":"See me, hear me: integrating automatic speech recognition and lip-reading","display_name":"See me, hear me: integrating automatic speech recognition and lip-reading","publication_year":1994,"publication_date":"1994-09-18","ids":{"openalex":"https://openalex.org/W124086577","doi":"https://doi.org/10.21437/icslp.1994-139","mag":"124086577"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.1994-139","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1994-139","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"3rd International Conference on Spoken Language Processing (ICSLP 1994)","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/A5019046675","display_name":"Paul Duchnowski","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Paul Duchnowski","raw_affiliation_strings":["University o f K a r lsruhe, K a r lsruhe, G"],"affiliations":[{"raw_affiliation_string":"University o f K a r lsruhe, K a r lsruhe, G","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065376703","display_name":"Uwe Meier","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Uwe Meier","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5110453805","display_name":"Alex Waibel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alex Waibel","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019046675"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4275,"has_fulltext":false,"cited_by_count":94,"citation_normalized_percentile":{"value":0.9231068,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"547","last_page":"550"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.7587000131607056,"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":0.7587000131607056,"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":0.7513995170593262},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.6428459882736206},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.632165253162384},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4432622194290161},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3433294892311096},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.22998079657554626}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7513995170593262},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.6428459882736206},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.632165253162384},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4432622194290161},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3433294892311096},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.22998079657554626},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/icslp.1994-139","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1994-139","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"3rd International Conference on Spoken Language Processing (ICSLP 1994)","raw_type":"proceedings-article"},{"id":"pmh:oai:EVASTAR-Karlsruhe.de:166296","is_oa":false,"landing_page_url":"https://publikationen.bibliothek.kit.edu/166296","pdf_url":null,"source":{"id":"https://openalex.org/S4306401992","display_name":"Repository KITopen (Karlsruhe Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I102335020","host_organization_name":"Karlsruhe Institute of Technology","host_organization_lineage":["https://openalex.org/I102335020"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doc-type:bookPart"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.31.5304","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.31.5304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ri.cmu.edu/afs/cs.cmu.edu/user/uwem/WWW/work/papers/94.icslp.ps.gz","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2611614995","https://openalex.org/W2368651715","https://openalex.org/W2789919619","https://openalex.org/W1552159754","https://openalex.org/W2148757832","https://openalex.org/W2293457016","https://openalex.org/W2131420137","https://openalex.org/W3169305685","https://openalex.org/W1515542156","https://openalex.org/W3107474891"],"abstract_inverted_index":{"We":[0,65],"present":[1],"recent":[2],"work":[3],"on":[4],"integration":[5,122],"of":[6,28,34,49,56,90,98,105,117,123,137],"visual":[7,51,78,107],"information":[8,52,110],"(automatic":[9],"lip-reading)":[10],"with":[11,141],"acoustic":[12,109],"speech":[13,17],"for":[14,68],"better":[15],"overall":[16],"recognition.":[18],"A":[19],"Multi-State":[20],"Time":[21],"Delay":[22],"Neural":[23],"Network":[24],"performs":[25],"the":[26,50,58,77,91,106],"recognition":[27,102,136],"spelled":[29],"letter":[30],"sequences":[31],"taking":[32],"advantage":[33],"lip":[35],"images":[36],"from":[37],"a":[38,63,96,131],"standard":[39],"camera.":[40],"The":[41],"problems":[42],"addressed":[43],"include":[44],"efficient":[45],"but":[46],"effective":[47],"representation":[48],"and":[53,86,108],"optimum":[54],"manner":[55],"combining":[57],"two":[59],"modalities":[60],"when":[61,139],"rendering":[62],"decision.":[64],"show":[66],"results":[67],"several":[69],"alternatives":[70],"to":[71],"direct":[72],"gray":[73],"level":[74],"image":[75],"as":[76],"evidence.":[79],"These":[80],"are:":[81],"Principal":[82],"Components,":[83],"Linear":[84],"Discriminants,":[85],"DFT":[87],"coefficients.":[88],"Dimensionality":[89],"input":[92,126],"is":[93,111],"decreased":[94],"by":[95],"factor":[97],"12":[99],"while":[100],"maintaining":[101],"rates.":[103],"Combination":[104],"performed":[112],"at":[113],"three":[114],"different":[115],"levels":[116],"abstraction.":[118],"Results":[119],"suggest":[120],"that":[121],"higher":[124],"order":[125],"features":[127],"works":[128],"best.":[129],"On":[130],"continuous":[132],"spelling":[133],"task,":[134],"visual-alone":[135],"45-55%,":[138],"combined":[140],"a...":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":7},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}
