{"id":"https://openalex.org/W2115116459","doi":null,"title":"Combining Visual and Acoustic Speech Signals with a Neural Network Improves Intelligibility","display_name":"Combining Visual and Acoustic Speech Signals with a Neural Network Improves Intelligibility","publication_year":1989,"publication_date":"1989-01-01","ids":{"openalex":"https://openalex.org/W2115116459","mag":"2115116459"},"language":"en","primary_location":{"id":"mag:2115116459","doi":null,"is_oa":false,"landing_page_url":"http://papers.nips.cc/paper/290-combining-visual-and-acoustic-speech-signals-with-a-neural-network-improves-intelligibility.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","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/A5044141636","display_name":"Terrence J. Sejnowski A B","orcid":"https://orcid.org/0000-0002-0622-7391","observed_orcids":["https://orcid.org/0000-0002-0622-7391"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Terrence J. Sejnowski","raw_affiliation_strings":["The Salk Institute and Department of Biology, The University of California at San Diego, San Diego, CA#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-0622-7391","affiliations":[{"raw_affiliation_string":"The Salk Institute and Department of Biology, The University of California at San Diego, San Diego, CA#TAB#","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018552234","display_name":"Ben P. Yuhas","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ben Yuhas","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering, The Johns Hopkins University, Baltimore, MD#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, The Johns Hopkins University, Baltimore, MD#TAB#","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111822063","display_name":"Mo\u00efse H. Goldstein","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mo\u00efse H. Goldstein","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering, The Johns Hopkins University, Baltimore, MD#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, The Johns Hopkins University, Baltimore, MD#TAB#","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":null,"display_name":"Robert E. Jenkins","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2802946424","display_name":"Johns Hopkins University Applied Physics Laboratory","ror":"https://ror.org/029pp9z10","country_code":"US","type":"facility","lineage":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert E. Jenkins","raw_affiliation_strings":["The Applied Physics Laboratory, The Johns Hopkins University, Laurel, MD#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Applied Physics Laboratory, The Johns Hopkins University, Laurel, MD#TAB#","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.652,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.76195537,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"232","last_page":"239"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9599999785423279,"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":0.9599999785423279,"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":0.03460000082850456,"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":0.0017999999690800905,"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/visual-speech","display_name":"visual speech","score":0.6140000224113464},{"id":"https://openalex.org/keywords/multimodal-speech-recognition","display_name":"multimodal speech recognition","score":0.625},{"id":"https://openalex.org/keywords/speech-intelligibility","display_name":"speech intelligibility","score":0.6639999747276306},{"id":"https://openalex.org/keywords/noise-degradation","display_name":"noise degradation","score":0.7179999947547913},{"id":"https://openalex.org/keywords/feedforward-neural-networks","display_name":"feedforward neural networks","score":0.8539999723434448},{"id":"https://openalex.org/keywords/vowel-recognition","display_name":"vowel recognition","score":0.7039999961853027},{"id":"https://openalex.org/keywords/lip-reading","display_name":"lip reading","score":0.4560000002384186},{"id":"https://openalex.org/keywords/signal-fusion","display_name":"signal fusion","score":0.49000000953674316}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8050534725189209},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7577152252197266},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5732601284980774},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.5402173399925232},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.504974901676178},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4454110562801361},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.4141068458557129},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41204673051834106},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.4116588830947876},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.40373948216438293},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3773511052131653},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2115116459","doi":null,"is_oa":false,"landing_page_url":"http://papers.nips.cc/paper/290-combining-visual-and-acoustic-speech-signals-with-a-neural-network-improves-intelligibility.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","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":21,"referenced_works":["https://openalex.org/W11614523","https://openalex.org/W36715566","https://openalex.org/W177229737","https://openalex.org/W181056519","https://openalex.org/W224625816","https://openalex.org/W286572439","https://openalex.org/W607079072","https://openalex.org/W1224808273","https://openalex.org/W1489393996","https://openalex.org/W1523707525","https://openalex.org/W1552857527","https://openalex.org/W1729109003","https://openalex.org/W1964178275","https://openalex.org/W1969938578","https://openalex.org/W1995853178","https://openalex.org/W2011417437","https://openalex.org/W2014621385","https://openalex.org/W2046216954","https://openalex.org/W2056133372","https://openalex.org/W2151096985","https://openalex.org/W2766736793"],"related_works":["https://openalex.org/W7096906769","https://openalex.org/W2151096985","https://openalex.org/W1991959239","https://openalex.org/W2622954728","https://openalex.org/W297049564","https://openalex.org/W2137317849","https://openalex.org/W2095035205","https://openalex.org/W1628005998","https://openalex.org/W2470520330","https://openalex.org/W2165589448"],"abstract_inverted_index":{"Acoustic":[0],"speech":[1,16,28,33,42,65],"recognition":[2,34,106],"degrades":[3],"in":[4,104],"the":[5,14,19,38,61,74,78,86,96,116],"presence":[6],"of":[7,85,118],"noise.":[8],"Compensatory":[9],"information":[10,43,66,90],"is":[11],"available":[12],"from":[13,107],"visual":[15,27,41,62,75],"signals":[17,29],"around":[18],"speaker's":[20],"mouth.":[21],"Previous":[22],"attempts":[23],"at":[24,44],"using":[25,48],"these":[26],"to":[30,59,72,115],"improve":[31],"automatic":[32],"systems":[35],"have":[36],"combined":[37,94],"acoustic":[39,64,87,98,109],"and":[40,63,126],"a":[45],"symbolic":[46],"level":[47],"heuristic":[49],"rules.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54],"demonstrate":[55],"an":[56],"alternative":[57],"approach":[58],"fusing":[60],"by":[67],"training":[68],"feedforward":[69],"neural":[70],"networks":[71],"map":[73],"signal":[76],"onto":[77],"corresponding":[79],"short-term":[80],"spectral":[81],"amplitude":[82],"envelope":[83],"(STSAE)":[84],"signal.":[88],"This":[89],"can":[91],"be":[92],"directly":[93],"with":[95],"degraded":[97],"STSAE.":[99],"Significant":[100],"improvements":[101],"are":[102,113],"demonstrated":[103],"vowel":[105],"noise-degraded":[108],"signals.":[110],"These":[111],"results":[112],"compared":[114],"performance":[117],"humans,":[119],"as":[120,122],"well":[121],"other":[123],"pattern":[124],"matching":[125],"estimation":[127],"algorithms.":[128]},"counts_by_year":[],"updated_date":"2026-10-17T09:40:24.721904","created_date":"2016-06-24T00:00:00"}