{"id":"https://openalex.org/W1554064406","doi":"https://doi.org/10.21437/interspeech.2006-619","title":"Analysis of correlation between audio and visual speech features for clean audio feature prediction in noise","display_name":"Analysis of correlation between audio and visual speech features for clean audio feature prediction in noise","publication_year":2006,"publication_date":"2006-09-17","ids":{"openalex":"https://openalex.org/W1554064406","doi":"https://doi.org/10.21437/interspeech.2006-619","mag":"1554064406"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2006-619","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ibrahim Almajai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023076395","display_name":"Ben Milner","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ben Milner","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5063817485","display_name":"Jonathan Darch","orcid":"https://orcid.org/0000-0001-6796-9041"},"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":"Jonathan Darch","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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9401,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.84718479,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"paper 1634","last_page":"Thu2WeO.5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9988999962806702,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/correlation","display_name":"Correlation","score":0.7035331726074219},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6931231021881104},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.6732690930366516},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6693901419639587},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6203017830848694},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.5761488676071167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5740464329719543},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.5613371729850769},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5287953019142151},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5113789439201355},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.48647305369377136},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4619792699813843},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.45440974831581116},{"id":"https://openalex.org/keywords/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.41324034333229065},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41147318482398987},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.18549060821533203},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16582316160202026},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07497566938400269}],"concepts":[{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.7035331726074219},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6931231021881104},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.6732690930366516},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6693901419639587},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6203017830848694},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.5761488676071167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5740464329719543},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.5613371729850769},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5287953019142151},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5113789439201355},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.48647305369377136},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4619792699813843},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.45440974831581116},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.41324034333229065},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41147318482398987},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.18549060821533203},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16582316160202026},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07497566938400269},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2006-619","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.174.6775","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.174.6775","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/icslp13-9-2006.pdf","raw_type":"text"},{"id":"pmh:oai:alma.44SUR_INST:11138602500002346","is_oa":false,"landing_page_url":"http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000269965901355&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:830242","is_oa":false,"landing_page_url":"http://epubs.surrey.ac.uk/830242/","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:22604","is_oa":false,"landing_page_url":"https://ueaeprints.uea.ac.uk/id/eprint/22604/","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":0.6700000166893005,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W62584596","https://openalex.org/W122772053","https://openalex.org/W2014621385","https://openalex.org/W2038010270","https://openalex.org/W2069238044","https://openalex.org/W2120535071","https://openalex.org/W2127211243","https://openalex.org/W2152826766","https://openalex.org/W2592974517","https://openalex.org/W3099202502"],"related_works":["https://openalex.org/W2046217390","https://openalex.org/W4365503437","https://openalex.org/W2362995206","https://openalex.org/W2004825552","https://openalex.org/W37481168","https://openalex.org/W165161405","https://openalex.org/W2766569399","https://openalex.org/W2156831951","https://openalex.org/W2019253074","https://openalex.org/W1992816027"],"abstract_inverted_index":{"The":[0,16,72,115],"aim":[1],"of":[2,80,87,117],"this":[3],"work":[4],"is":[5,18,42,74],"to":[6,19,106],"examine":[7],"the":[8,38,78,92,120,124],"correlation":[9,66,73,105,125],"between":[10],"audio":[11,27,40,47,88],"and":[12,50,52,61],"visual":[13,21,54,93,107],"speech":[14,35],"features.":[15,94],"motivation":[17],"find":[20],"features":[22,48,55,89,98,108],"that":[23,97],"can":[24,31],"provide":[25],"clean":[26],"feature":[28],"estimates":[29],"which":[30],"be":[32],"used":[33],"for":[34],"enhancement":[36],"when":[37],"original":[39],"signal":[41],"corrupted":[43],"by":[44],"noise.":[45],"Two":[46],"(MFCCs":[49],"formants)":[51],"three":[53],"(active":[56],"appearance":[57],"model,":[58],"2-D":[59],"DCT":[60],"cross-DCT)":[62],"are":[63],"considered":[64],"with":[65],"measured":[67],"using":[68],"multiple":[69],"linear":[70],"regression.":[71],"then":[75],"exploited":[76],"through":[77],"development":[79],"a":[81,83],"maximum":[82],"posteriori":[84],"(MAP)":[85],"prediction":[86,118],"solely":[90],"from":[91],"Experiments":[95],"reveal":[96],"representing":[99,111],"broad":[100],"spectral":[101,113],"information":[102],"have":[103],"higher":[104],"than":[109],"those":[110],"finer":[112],"detail.":[114],"accuracy":[116],"follows":[119],"results":[121],"found":[122],"in":[123],"measurements.":[126],"Index":[127],"Terms:":[128],"audio-visual":[129],"speech,":[130],"correlation,":[131],"AAM,":[132],"formants":[133],"1.":[134]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}