{"id":"https://openalex.org/W1565194362","doi":"https://doi.org/10.21437/interspeech.2009-576","title":"Enhancing audio speech using visual speech features","display_name":"Enhancing audio speech using visual speech features","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W1565194362","doi":"https://doi.org/10.21437/interspeech.2009-576","mag":"1565194362"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-576","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-576","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","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/A5037461866","display_name":"Ibrahim Almajai","orcid":null},"institutions":[{"id":"https://openalex.org/I1118541","display_name":"University of East Anglia","ror":"https://ror.org/026k5mg93","country_code":"GB","type":"education","lineage":["https://openalex.org/I1118541"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ibrahim Almajai","raw_affiliation_strings":["#N#University of East Anglia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"#N#University of East Anglia","institution_ids":["https://openalex.org/I1118541"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023076395","display_name":"Ben Milner","orcid":null},"institutions":[{"id":"https://openalex.org/I1118541","display_name":"University of East Anglia","ror":"https://ror.org/026k5mg93","country_code":"GB","type":"education","lineage":["https://openalex.org/I1118541"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ben Milner","raw_affiliation_strings":["University of East Anglia, Norwich, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of East Anglia, Norwich, United Kingdom","institution_ids":["https://openalex.org/I1118541"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3572,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.53414586,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1959","last_page":"1962"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9962000250816345,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7554157376289368},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7539253234863281},{"id":"https://openalex.org/keywords/wiener-filter","display_name":"Wiener filter","score":0.6505941152572632},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6376479864120483},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5211648941040039},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.47741377353668213},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4654581844806671},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.46234264969825745},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4605499804019928},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.4254681468009949},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4151885211467743},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38435888290405273},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.20973795652389526},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.17674386501312256}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7554157376289368},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7539253234863281},{"id":"https://openalex.org/C18537770","wikidata":"https://www.wikidata.org/wiki/Q25523","display_name":"Wiener filter","level":2,"score":0.6505941152572632},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6376479864120483},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5211648941040039},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.47741377353668213},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4654581844806671},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.46234264969825745},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4605499804019928},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.4254681468009949},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4151885211467743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38435888290405273},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.20973795652389526},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.17674386501312256},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2009-576","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-576","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.302.6501","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.302.6501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.computing.surrey.ac.uk/personal/st/I.Almajai/docs/Enhancing Audio Speech using Visual Speech Features.pdf","raw_type":"text"},{"id":"pmh:oai:alma.44SUR_INST:11138855070002346","is_oa":false,"landing_page_url":"http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000276842801020&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=11d2a86992e85fb529977dad66a846d5","pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"event"},{"id":"pmh:oai:epubs.surrey.ac.uk:830282","is_oa":false,"landing_page_url":"http://epubs.surrey.ac.uk/830282/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400680","display_name":"Surrey Research Insight Open Access (The University of Surrey)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28290843","host_organization_name":"University of Surrey","host_organization_lineage":["https://openalex.org/I28290843"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},{"id":"pmh:oai:ueaeprints.uea.ac.uk:22026","is_oa":false,"landing_page_url":"https://ueaeprints.uea.ac.uk/id/eprint/22026/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400384","display_name":"UEA Digital Repository (University of East Anglia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1118541","host_organization_name":"University of East Anglia","host_organization_lineage":["https://openalex.org/I1118541"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1554064406","https://openalex.org/W1948357167","https://openalex.org/W2038010270","https://openalex.org/W2116529913","https://openalex.org/W2127211243","https://openalex.org/W2138425792","https://openalex.org/W2149535104","https://openalex.org/W2170912900","https://openalex.org/W3099202502","https://openalex.org/W3143833948","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3211091508","https://openalex.org/W1976952689","https://openalex.org/W2070982348","https://openalex.org/W1984921740","https://openalex.org/W2496295964","https://openalex.org/W1572861854","https://openalex.org/W2539491809","https://openalex.org/W2336887028","https://openalex.org/W2020464095","https://openalex.org/W823775484"],"abstract_inverted_index":{"This":[0,35],"work":[1],"presents":[2],"a":[3,29,50,52,83],"novel":[4],"approach":[5],"to":[6,86,97],"speech":[7,14,24,27,38,60,79,93,115],"enhancement":[8],"by":[9,43],"exploiting":[10],"the":[11,16,65,105,108],"bimodality":[12],"of":[13,55,92,107],"and":[15,22,48,94],"correlation":[17],"that":[18],"exists":[19],"between":[20],"audio":[21,57,77],"visual":[23,41,59],"features.":[25,61],"For":[26],"enhancement,":[28,116],"visually-derived":[30],"Wiener":[31,66,110,117],"filter":[32,67,118],"is":[33],"developed.":[34],"obtains":[36],"clean":[37,56],"statistics":[39,63,96],"from":[40,58],"features":[42],"modelling":[44],"their":[45],"joint":[46],"density":[47],"making":[49],"maximum":[51],"posteriori":[53],"estimate":[54],"Noise":[62],"for":[64],"utilise":[68],"an":[69],"audio-visual":[70],"voice":[71],"activity":[72],"detector":[73],"which":[74],"classifies":[75],"input":[76],"as":[78],"or":[80],"nonspeech,":[81],"enabling":[82],"noise":[84,95],"model":[85],"be":[87,98],"updated.":[88],"Analysis":[89],"shows":[90],"estimation":[91],"effective":[99],"with":[100],"human":[101],"listening":[102],"tests":[103],"measuring":[104],"effectiveness":[106],"resulting":[109],"filter.":[111],"Index":[112],"Terms:":[113],"Audio-visual,":[114],"1.":[119]},"counts_by_year":[{"year":2018,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}