{"id":"https://openalex.org/W175149386","doi":"https://doi.org/10.21437/interspeech.2010-467","title":"Estimation of speech lip features from discrete cosinus transform","display_name":"Estimation of speech lip features from discrete cosinus transform","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W175149386","doi":"https://doi.org/10.21437/interspeech.2010-467","mag":"175149386"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-467","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-467","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-00536131/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006810592","display_name":"Zuheng Ming","orcid":"https://orcid.org/0000-0002-1094-3112"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zuheng Ming","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085944842","display_name":"Denis Beautemps","orcid":"https://orcid.org/0000-0001-9625-3018"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Denis Beautemps","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017170149","display_name":"Gang Feng","orcid":"https://orcid.org/0000-0002-4192-2058"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gang Feng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5077855925","display_name":"S. Schmerber","orcid":"https://orcid.org/0000-0003-0189-5574"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S\u00e9bastien Schmerber","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5006810592"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0131462,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1612","last_page":"1615"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9771999716758728,"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":0.9771999716758728,"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/T11448","display_name":"Face recognition and analysis","score":0.9179999828338623,"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/speech-recognition","display_name":"Speech recognition","score":0.6230975985527039},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6021860837936401},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.5249963998794556},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4414750039577484},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3478241562843323},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11076802015304565}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6230975985527039},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6021860837936401},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5249963998794556},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4414750039577484},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3478241562843323},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11076802015304565},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2010-467","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-467","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-00536131v1","is_oa":true,"landing_page_url":"https://hal.science/hal-00536131","pdf_url":"https://hal.science/hal-00536131/document","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Interspeech 2010 - 11th Annual Conference of the International Speech Communication Association, Sep 2010, Makuhari, Japan. pp.1612 - 1615","raw_type":"Conference papers"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.473.4278","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.473.4278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://halshs.archives-ouvertes.fr/docs/00/53/61/31/PDF/zuhengBeautempsGangSchmerber_Interspeech2010_v_3004_21h.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-00536131v1","is_oa":true,"landing_page_url":"https://hal.science/hal-00536131","pdf_url":"https://hal.science/hal-00536131/document","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Interspeech 2010 - 11th Annual Conference of the International Speech Communication Association, Sep 2010, Makuhari, Japan. pp.1612 - 1615","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W175149386.pdf","grobid_xml":"https://content.openalex.org/works/W175149386.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W104873306","https://openalex.org/W194243062","https://openalex.org/W604781219","https://openalex.org/W1523010034","https://openalex.org/W1604074770","https://openalex.org/W1664248204","https://openalex.org/W1970027736","https://openalex.org/W1984483979","https://openalex.org/W2014621385","https://openalex.org/W2015394094","https://openalex.org/W2054608764","https://openalex.org/W2058970032","https://openalex.org/W2091930743","https://openalex.org/W2096391593","https://openalex.org/W2106137268","https://openalex.org/W2118258383","https://openalex.org/W2121486117","https://openalex.org/W2125013164","https://openalex.org/W2481376636","https://openalex.org/W2487271655","https://openalex.org/W2511186018","https://openalex.org/W3040607653"],"related_works":["https://openalex.org/W2033914206","https://openalex.org/W2146076056","https://openalex.org/W2163831990","https://openalex.org/W3003836766","https://openalex.org/W2046077695","https://openalex.org/W2378160586","https://openalex.org/W2042327336","https://openalex.org/W2996038082","https://openalex.org/W3047965787","https://openalex.org/W3184582087"],"abstract_inverted_index":{"This":[0],"study":[1],"is":[2,27,54],"a":[3,57,64,70,97,118],"contribution":[4],"to":[5,69,77,90,106],"the":[6,15,30,44,47,73,82,88,92,110,114,125],"field":[7],"of":[8,18,33,43,46,50,56,72,81,104,121],"visual":[9],"speech":[10],"processing.":[11],"It":[12],"focuses":[13],"on":[14,29],"automatic":[16],"extraction":[17],"Speech":[19],"lip":[20,48,94,111,115],"features":[21,35,95],"from":[22,36,39,124],"natural":[23],"lips.":[24],"The":[25,52,85],"method":[26],"based":[28],"direct":[31],"prediction":[32],"these":[34],"predictors":[37,122],"derived":[38,123],"an":[40],"adequate":[41],"transformation":[42,53],"pixels":[45],"region":[49],"interest.":[51],"made":[55],"2-D":[58],"Discrete":[59],"Cosine":[60],"Transform":[61],"combined":[62],"with":[63,96],"Principal":[65],"Component":[66],"Analysis":[67],"applied":[68],"subset":[71],"DCT":[74],"coefficients":[75],"corresponding":[76],"about":[78],"1":[79,105],"%":[80],"total":[83],"DCTs.":[84],"results":[86],"show":[87],"possibility":[89],"estimate":[91],"geometric":[93],"good":[98],"accuracy":[99],"(a":[100],"root":[101],"mean":[102],"square":[103],"1.4":[107],"mm":[108],"for":[109],"aperture":[112],"and":[113],"width)":[116],"using":[117],"reduce":[119],"set":[120],"PCA.":[126]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}