{"id":"https://openalex.org/W2138425792","doi":"https://doi.org/10.1109/icassp.2004.1326663","title":"Characterization and extraction of mouth opening parameters available for audiovisual speech enhancement","display_name":"Characterization and extraction of mouth opening parameters available for audiovisual speech enhancement","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2138425792","doi":"https://doi.org/10.1109/icassp.2004.1326663","mag":"2138425792"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326663","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/A5108205978","display_name":"F. Berthommier","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"F. Berthommier","raw_affiliation_strings":["Institut de la Communication Parl\u00e9e, INPG, Grenoble, France","Inst. de la Commun. Parlee, Inst. Nat. Polytech. de Grenoble, France"],"affiliations":[{"raw_affiliation_string":"Institut de la Communication Parl\u00e9e, INPG, Grenoble, France","institution_ids":[]},{"raw_affiliation_string":"Inst. de la Commun. Parlee, Inst. Nat. Polytech. de Grenoble, France","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5108205978"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5609,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.68245065,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"3","issue":null,"first_page":"iii","last_page":"789"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9988999962806702,"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"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9987999796867371,"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/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.8485473990440369},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6491660475730896},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6307895183563232},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.6141250729560852},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5591254830360413},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5202968716621399},{"id":"https://openalex.org/keywords/trigonometric-functions","display_name":"Trigonometric functions","score":0.43218860030174255},{"id":"https://openalex.org/keywords/envelope","display_name":"Envelope (radar)","score":0.43037787079811096},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3973812758922577},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35446974635124207},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3056562542915344},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1426427662372589}],"concepts":[{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.8485473990440369},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6491660475730896},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6307895183563232},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.6141250729560852},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5591254830360413},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5202968716621399},{"id":"https://openalex.org/C178009071","wikidata":"https://www.wikidata.org/wiki/Q93344","display_name":"Trigonometric functions","level":2,"score":0.43218860030174255},{"id":"https://openalex.org/C65155139","wikidata":"https://www.wikidata.org/wiki/Q5380912","display_name":"Envelope (radar)","level":3,"score":0.43037787079811096},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3973812758922577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35446974635124207},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3056562542915344},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1426427662372589},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2004.1326663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326663","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,"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":20,"referenced_works":["https://openalex.org/W16682072","https://openalex.org/W62584596","https://openalex.org/W1275705376","https://openalex.org/W2000749240","https://openalex.org/W2010929291","https://openalex.org/W2127211243","https://openalex.org/W2137398355","https://openalex.org/W2164899449","https://openalex.org/W2278884322","https://openalex.org/W2398101605","https://openalex.org/W2398325739","https://openalex.org/W2406000202","https://openalex.org/W3139876855","https://openalex.org/W3146437239","https://openalex.org/W6600697783","https://openalex.org/W6628334182","https://openalex.org/W6650500320","https://openalex.org/W6680239239","https://openalex.org/W6712171522","https://openalex.org/W6712393991"],"related_works":["https://openalex.org/W2055682261","https://openalex.org/W1916685473","https://openalex.org/W1993363272","https://openalex.org/W2186390138","https://openalex.org/W2790129917","https://openalex.org/W2060035984","https://openalex.org/W2992856432","https://openalex.org/W2100638064","https://openalex.org/W2174937762","https://openalex.org/W2212883587"],"abstract_inverted_index":{"The":[0],"strong":[1],"association":[2,51],"existing":[3],"between":[4],"audio":[5],"subband":[6],"envelope":[7],"parameters":[8,11,73],"and":[9,112],"video":[10,41],"extracted":[12],"using":[13],"the":[14,40,47,92,102,105,110,114],"full":[15],"DCT":[16,72],"(discrete":[17],"cosine":[18],"transform)":[19],"can":[20],"be":[21,53],"exploited":[22],"for":[23],"audiovisual":[24],"speech":[25],"enhancement,":[26],"thanks":[27],"to":[28,66,83,109,113],"a":[29,36,57,68,81],"good":[30],"prediction":[31],"of":[32,49,60,71,91,104],"amplitude":[33],"variations":[34],"by":[35,89],"statistical":[37],"model.":[38],"Since":[39],"parameter":[42,85],"space":[43],"is":[44,62,87,116],"highly":[45],"multidimensional,":[46],"causality":[48],"this":[50],"must":[52],"clarified.":[54],"At":[55],"first,":[56],"new":[58],"method":[59],"retro-marking":[61],"proposed":[63],"in":[64,97],"order":[65],"build":[67],"transformation":[69,111],"function":[70],"into":[74],"explicit":[75],"ABS":[76],"mouth":[77],"opening":[78],"parameters.":[79,94],"Secondly,":[80],"reduction":[82,115],"single":[84],"spaces":[86],"performed":[88],"selection":[90],"best":[93],"We":[95],"show":[96],"two":[98],"noisy":[99],"conditions":[100],"that":[101],"degradation":[103],"enhancement":[106],"performance":[107],"due":[108],"moderate.":[117]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
