{"id":"https://openalex.org/W2119057959","doi":"https://doi.org/10.1109/icassp.2004.1326082","title":"Automated lip-reading for improved speech intelligibility","display_name":"Automated lip-reading for improved speech intelligibility","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2119057959","doi":"https://doi.org/10.1109/icassp.2004.1326082","mag":"2119057959"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326082","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326082","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","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/A5037241088","display_name":"Matthew McClain","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"M. McClain","raw_affiliation_strings":["MIT Lincoln Laboratories, Lexington, MA, USA","Lincoln Lab., MIT, Lexington, MA, USA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratories, Lexington, MA, USA","institution_ids":["https://openalex.org/I4210122954"]},{"raw_affiliation_string":"Lincoln Lab., MIT, Lexington, MA, USA","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111908794","display_name":"Kevin Brady","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"K. Brady","raw_affiliation_strings":["MIT Lincoln Laboratories, Lexington, MA, USA","Lincoln Lab., MIT, Lexington, MA, USA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratories, Lexington, MA, USA","institution_ids":["https://openalex.org/I4210122954"]},{"raw_affiliation_string":"Lincoln Lab., MIT, Lexington, MA, USA","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086705866","display_name":"M.S. Brandstein","orcid":"https://orcid.org/0009-0008-7883-3658"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Brandstein","raw_affiliation_strings":["MIT Lincoln Laboratories, Lexington, MA, USA","Lincoln Lab., MIT, Lexington, MA, USA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratories, Lexington, MA, USA","institution_ids":["https://openalex.org/I4210122954"]},{"raw_affiliation_string":"Lincoln Lab., MIT, Lexington, MA, USA","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009507416","display_name":"Thomas F. Quatieri","orcid":"https://orcid.org/0000-0003-1925-6340"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"T. Quatieri","raw_affiliation_strings":["MIT Lincoln Laboratories, Lexington, MA, USA","Lincoln Lab., MIT, Lexington, MA, USA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratories, Lexington, MA, USA","institution_ids":["https://openalex.org/I4210122954"]},{"raw_affiliation_string":"Lincoln Lab., MIT, Lexington, MA, USA","institution_ids":["https://openalex.org/I4210122954"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5037241088"],"corresponding_institution_ids":["https://openalex.org/I4210122954"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.18660339,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"701"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12032","display_name":"Multisensory perception and integration","score":0.9886000156402588,"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/intelligibility","display_name":"Intelligibility (philosophy)","score":0.8234677910804749},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.751051127910614},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6907599568367004},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.42681193351745605},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37218785285949707},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09467312693595886}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.8234677910804749},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.751051127910614},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6907599568367004},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.42681193351745605},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37218785285949707},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09467312693595886},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2004.1326082","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326082","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310207","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33"},{"id":"https://openalex.org/F4320310575","display_name":"California Polytechnic State University, San Luis Obispo","ror":"https://ror.org/001gpfp45"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W17997738","https://openalex.org/W160552598","https://openalex.org/W198103728","https://openalex.org/W1969365714","https://openalex.org/W1977020887","https://openalex.org/W2015394094","https://openalex.org/W2038010270","https://openalex.org/W2122817389","https://openalex.org/W3144747696","https://openalex.org/W6600774203","https://openalex.org/W6608161445"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2013974941","https://openalex.org/W2127461790","https://openalex.org/W2069324367"],"abstract_inverted_index":{"Various":[0],"psycho-acoustical":[1],"experiments":[2,89],"have":[3],"concluded":[4],"that":[5,91,102],"visual":[6,39,60,79,116],"features":[7,61,95,117],"strongly":[8],"affect":[9],"the":[10,23,34,73,77,85,92],"perception":[11],"of":[12,25,36,57,72,100],"speech.":[13],"This":[14],"contribution":[15],"is":[16,28,62],"most":[17],"pronounced":[18],"in":[19,51,106,121],"noisy":[20,52],"environments":[21],"where":[22],"intelligibility":[24,50,55,66,101],"audio-only":[26],"speech":[27,49,108,128],"quickly":[29],"degraded.":[30],"The":[31,54],"paper":[32],"explores":[33],"effectiveness":[35],"using":[37],"extracted":[38,59,78,93,115],"features,":[40,80],"such":[41],"as":[42,81,83],"lip":[43],"height":[44],"and":[45,110],"width,":[46],"for":[47],"improving":[48],"environments.":[53],"content":[56],"these":[58,114],"investigated":[63],"through":[64],"an":[65,69],"test":[67],"on":[68,84],"animated":[70],"rendition":[71],"video":[74,94],"generated":[75],"from":[76],"well":[82],"original":[86],"video.":[87],"These":[88],"demonstrate":[90],"do":[96],"contain":[97],"important":[98],"aspects":[99],"may":[103],"be":[104,119],"utilized":[105],"augmenting":[107],"enhancement":[109],"coding":[111],"applications.":[112],"Alternatively,":[113],"can":[118],"transmitted":[120],"a":[122],"bandwidth":[123],"effective":[124],"way":[125],"to":[126],"augment":[127],"coders.":[129]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
