{"id":54730,"date":"2018-03-09T22:42:27","date_gmt":"2018-03-09T22:42:27","guid":{"rendered":"https:\/\/www.deberes.net\/tesis\/sin-categoria\/improvements-in-speech-recognition-for-embedded-devices-by-taking-advantage-of-lip-reading-techniques\/"},"modified":"2018-03-09T22:42:27","modified_gmt":"2018-03-09T22:42:27","slug":"improvements-in-speech-recognition-for-embedded-devices-by-taking-advantage-of-lip-reading-techniques","status":"publish","type":"post","link":"https:\/\/www.deberes.net\/tesis\/sistemas-en-tiempo-real\/improvements-in-speech-recognition-for-embedded-devices-by-taking-advantage-of-lip-reading-techniques\/","title":{"rendered":"Improvements in speech recognition for embedded devices by taking advantage of lip reading techniques."},"content":{"rendered":"<h2>Tesis doctoral de <strong>  Guitarte Perez Jes\u00fas Fernando <\/strong><\/h2>\n<p>En la presente tesis doctoral la informaci\u00f3n visual contenida en el movimiento de los labios se ha utilizado para mejorar la robustez frente al ruido de sistemas de reconocimiento de voz en dispositivos con recursos limitados. El sistema aqu\u00ed descrito reduce de forma significativa la tasa de error en niveles de ruido ac\u00fastico elevado. Los algoritmos utilizados se caracterizan por su reducido consumo, tanto de tiempo de procesado como de memoria, permitiendo su uso en dispositivos integrados. Los principales aspectos a tomar en consideraci\u00f3n en un sistema de lectura de labios son la localizaci\u00f3n y seguimiento de los labios, la extracci\u00f3n de la informaci\u00f3n visual y su integraci\u00f3n con la informaci\u00f3n ac\u00fastica. En el presente trabajo se proponen soluciones a estos tres problemas adecuadas al uso en dispositivos con recursos limitados. se ha desarrollado un algoritmo para la localizaci\u00f3n y seguimiento de los labios. A partir de una clasificaci\u00f3n por color, usando contornos horizontales y un modelo sencillo de la cara el algoritmo implementado proporciona la posici\u00f3n de la boca con un consumo muy bajo de recursos. Este algoritmo se ha implementado en un tel\u00e9fono m\u00f3vil procesando una tasa de 15 im\u00e1genes por segundo en tiempo real. Por otro lado para la extracci\u00f3n de la informaci\u00f3n visual se han estudiado dos tipos de algoritmos diferentes; uno basado en un modelado de la geometr\u00eda labial y otro basado en una transformaci\u00f3n matem\u00e1tica de los pixeles incluidos en la regi\u00f3n de la boca. Se ha mostrado como en dispositivos con recursos limitados el segundo tipo proporciona mejores tasas de reconocimiento al no requerir la extracci\u00f3n precisa del contorno de los labios. Finalmente, se han estudiado tres t\u00e9cnicas para integrar la informaci\u00f3n ac\u00fastica y visual, que se diferencian en la posici\u00f3n donde tiene lugar la integraci\u00f3n en el proceso de reconocimiento: temprana, tard\u00eda e h\u00edbrida. Se ha constatado que la \u00faltima proporciona los mejores resultados<\/p>\n<p>&nbsp;<\/p>\n<h3>Datos acad\u00e9micos de la tesis doctoral \u00ab<strong>Improvements in speech recognition for embedded devices by taking advantage of lip reading techniques.<\/strong>\u00ab<\/h3>\n<ul>\n<li><strong>T\u00edtulo de la tesis:<\/strong>\u00a0 Improvements in speech recognition for embedded devices by taking advantage of lip reading techniques. <\/li>\n<li><strong>Autor:<\/strong>\u00a0  Guitarte Perez Jes\u00fas Fernando <\/li>\n<li><strong>Universidad:<\/strong>\u00a0 Zaragoza<\/li>\n<li><strong>Fecha de lectura de la tesis:<\/strong>\u00a0 26\/09\/2006<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<h3>Direcci\u00f3n y tribunal<\/h3>\n<ul>\n<li><strong>Director de la tesis<\/strong>\n<ul>\n<li>Eduardo Lleida Solano<\/li>\n<\/ul>\n<\/li>\n<li><strong>Tribunal<\/strong>\n<ul>\n<li>Presidente del tribunal: climent Nadeu camprubi <\/li>\n<li>alejandro Frangi caregnato (vocal)<\/li>\n<li>harald H\u00ed\u00b6ge (vocal)<\/li>\n<li>Jos\u00e9 Carlos Segura luna (vocal)<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Tesis doctoral de Guitarte Perez Jes\u00fas Fernando En la presente tesis doctoral la informaci\u00f3n visual contenida en el movimiento de [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"default","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""}},"footnotes":""},"categories":[8967,13610],"tags":[73059,30527,4155,120898,120899,30793],"class_list":["post-54730","post","type-post","status-publish","format-standard","hentry","category-sistemas-en-tiempo-real","category-zaragoza","tag-alejandro-frangi-caregnato","tag-climent-nadeu-camprubi","tag-eduardo-lleida-solano","tag-guitarte-perez-jesus-fernando","tag-harald-hige","tag-jose-carlos-segura-luna"],"_links":{"self":[{"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/posts\/54730","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/comments?post=54730"}],"version-history":[{"count":0,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/posts\/54730\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/media?parent=54730"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/categories?post=54730"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/tags?post=54730"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}