{"id":"https://openalex.org/W3144926571","doi":null,"title":"ADAPTIVE BIMODAL SENSOR FUSION FOR AUTOI/IATIC SPEECHREADING","display_name":"ADAPTIVE BIMODAL SENSOR FUSION FOR AUTOI/IATIC SPEECHREADING","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W3144926571","mag":"3144926571"},"language":"en","primary_location":{"id":"mag:3144926571","doi":null,"is_oa":false,"landing_page_url":"https://isl.anthropomatik.kit.edu/cmu-kit/english/4741.php","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5058854608","display_name":"Uwe Meiel","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Uwe Meiel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5058854608"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1846,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.81655277,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8192999958992004,"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":0.8192999958992004,"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":0.17499999701976776,"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/T12032","display_name":"Multisensory perception and integration","score":0.0013000000035390258,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/lip-reading","display_name":"lip reading","score":0.6919999718666077},{"id":"https://openalex.org/keywords/multimodal-sensor-fusion","display_name":"multimodal sensor fusion","score":0.8579999804496765},{"id":"https://openalex.org/keywords/adaptive-fusion","display_name":"adaptive fusion","score":0.527999997138977},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.6330000162124634},{"id":"https://openalex.org/keywords/speaker-dependent-speech-recognition","display_name":"speaker-dependent recognition","score":0.5120000243186951},{"id":"https://openalex.org/keywords/noise-robustness","display_name":"noise robustness","score":0.8790000081062317},{"id":"https://openalex.org/keywords/signal-to-noise-ratio-estimation","display_name":"signal-to-noise ratio estimation","score":0.8539999723434448}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7731785774230957},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7686160206794739},{"id":"https://openalex.org/C2910309083","wikidata":"https://www.wikidata.org/wiki/Q1069953","display_name":"Speechreading","level":2,"score":0.7336846590042114},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5471429824829102},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.43144264817237854},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.41843605041503906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4171193838119507},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.338870644569397},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3144926571","doi":null,"is_oa":false,"landing_page_url":"https://isl.anthropomatik.kit.edu/cmu-kit/english/4741.php","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W17742430","https://openalex.org/W22517275","https://openalex.org/W124086577","https://openalex.org/W1549662771","https://openalex.org/W1965084532","https://openalex.org/W1996803179","https://openalex.org/W2015394094","https://openalex.org/W2113786253","https://openalex.org/W2117671523","https://openalex.org/W2168824259"],"related_works":["https://openalex.org/W2153606381","https://openalex.org/W2171416536","https://openalex.org/W2036205336","https://openalex.org/W7145911274","https://openalex.org/W4302789782","https://openalex.org/W124086577","https://openalex.org/W2129122669","https://openalex.org/W2157190406","https://openalex.org/W2168824259","https://openalex.org/W2165589448"],"abstract_inverted_index":{"2.":[0],"SYSTEM":[1],"DESCRIPTION":[2],"We":[3,46,62,148],"present":[4],"recent":[5],"work":[6],"on":[7,31,49,171],"improving":[8],"the":[9,36,43,72,91,118,125,129,136],"performance":[10],"of":[11,24,34,52,71,90,132,135,153],"automated":[12],"speech":[13,56,99,127],"recognizers":[14],"by":[15],"using":[16],"additional":[17],"visual":[18,37],"information":[19,76],"(Lip-/Speechreading),":[20],"achieving":[21],"error":[22],"reduction":[23],"up":[25],"to":[26,41,114],"50%.":[27],"This":[28],"paper":[29],"focuses":[30],"different":[32,92],"methods":[33,67,94,111],"combining":[35],"and":[38,100,128,140,145,182],"acoustic":[39,126],"data":[40,101],"improve":[42],"recognition":[44,57,73],"performance.":[45],"show":[47],"this":[48],"an":[50,53],"extension":[51],"existing":[54],"state-of-the-art":[55],"system,":[58],"a":[59],"modular":[60],"MS-TDNN.":[61],"have":[63],"developed":[64],"adaptive":[65],"conibination":[66,93],"at":[68],"several":[69],"levels":[70],"network.":[74],"Additional":[75],"such":[77],"as":[78,160],"estimated":[79],"signal-to-noise":[80,175],"ratio":[81,176],"(SNR)":[82],"is":[83],"used":[84],"in":[85,123,164],"some":[86],"cases.":[87],"The":[88,108,138],"results":[89],"are":[95,143,167],"shown":[96],"for":[97],"clean":[98,178],"with":[102],"artificial":[103],"noise":[104,116,174],"(white,":[105],"music,":[106],"motor).":[107],"new":[109],"combination":[110],"adapt":[112],"automatically":[113],"varying":[115],"In":[117],"basic":[119],"set-up,":[120],"we":[121],"record,":[122],"parallel,":[124],"corresponding":[130],"serieij":[131],"mouth":[133],"images":[134],"speaker.":[137],"speaker":[139],"his":[141],"lip!;":[142],"found":[144],"tracked":[146],"automatically.":[147],"use":[149],"speaker-dependent":[150],"continuous":[151],"spelling":[152],"German":[154],"letter":[155,158],"strings":[156],"(26":[157],"alphabet)":[159],"our":[161,165],"task.":[162],"Words":[163],"database":[166],"8":[168],"letters":[169],"long":[170],"average.":[172],"I":[173,177],"motor":[179],"25":[180],"dB":[181,184],"10":[183],"Table":[185],"1.":[186],"Acoustic":[187],"environments":[188],"tested":[189],"(dB":[190],"SNR).":[191],"conditions":[192],"making":[193],"hand-tuned":[194],"parameters":[195],"unnecessary.":[196]},"counts_by_year":[],"updated_date":"2025-11-06T04:12:42.849631","created_date":"2021-04-13T00:00:00"}