{"id":41921,"date":"1999-01-01T00:00:00","date_gmt":"1999-01-01T00:00:00","guid":{"rendered":"https:\/\/www.deberes.net\/tesis\/sin-categoria\/utilizacion-de-metodos-discriminantes-en-el-modelado-acustico-de-la-voz\/"},"modified":"1999-01-01T00:00:00","modified_gmt":"1999-01-01T00:00:00","slug":"utilizacion-de-metodos-discriminantes-en-el-modelado-acustico-de-la-voz","status":"publish","type":"post","link":"https:\/\/www.deberes.net\/tesis\/matematicas\/utilizacion-de-metodos-discriminantes-en-el-modelado-acustico-de-la-voz\/","title":{"rendered":"Utilizacion de metodos discriminantes en el modelado acustico de la voz."},"content":{"rendered":"<h2>Tesis doctoral de <strong> Francisco Diaz Perez <\/strong><\/h2>\n<p>Se analizan las posibilidades y deficiencias de los modelos ocultos de markov para el modelado ac\u00fastico. El objetivo es elevar las propiedades discriminantes de los referidos modelos para el reconocimiento del habla. Los estudios se enfocaron en tres direcciones: (1)resalte de las caracter\u00edsticas discriminantes contenidas en las plantillas espectrales mediante an\u00e1lisis de componentes principales (pca) y el an\u00e1lisis de discriminaci\u00f3n lineal (lda), (2) implementaci\u00f3n de la cuantizaci\u00f3n vectorial con m\u00e9todos alternativos conexionistas (mapas autorganizativos, y capas competitivas), y adem\u00e1s se sugiere una m\u00e9trica de distancia vectorial; y (3) desarrollo del entrenamiento discriminante de los modelos.  se concluye que el uso de la transformaci\u00f3n realizada acorde al an\u00e1lisis de discriminaci\u00f3n lineal, conjuntamente con la reducci\u00f3n de la dimensi\u00f3n y el entrenamiento discriminante, es una combinaci\u00f3n muy adecuada para aumentar la eficiencia de los sistemas de reconocimiento de voz empleando modelos ocultos de markov con funciones de probabilidades discretas. En los experimentos se mejora el m\u00e9todo notoriamente el m\u00e9todo cl\u00e1sico, pues en los conjuntos de entrenamiento de palabras aisladas y fragmentos voc\u00e1licos se alcanza el 97,92% y el 95,48% de aciertos, con una mejora de un 11,88% y de un 22,38% respectivamente; mientras que con los conjuntos de evaluaci\u00f3n se obtienen el 83,33% y el 72,14% de aciertos en cada tarea, lo que supone una mejora del 7,61% y del 11,07% respectivamente.<\/p>\n<p>&nbsp;<\/p>\n<h3>Datos acad\u00e9micos de la tesis doctoral \u00ab<strong>Utilizacion de metodos discriminantes en el modelado acustico de la voz.<\/strong>\u00ab<\/h3>\n<ul>\n<li><strong>T\u00edtulo de la tesis:<\/strong>\u00a0 Utilizacion de metodos discriminantes en el modelado acustico de la voz. <\/li>\n<li><strong>Autor:<\/strong>\u00a0 Francisco Diaz Perez <\/li>\n<li><strong>Universidad:<\/strong>\u00a0 Polit\u00e9cnica de Madrid<\/li>\n<li><strong>Fecha de lectura de la tesis:<\/strong>\u00a0 01\/01\/1999<\/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>Pedro G\u00f3mez Vilda<\/li>\n<\/ul>\n<\/li>\n<li><strong>Tribunal<\/strong>\n<ul>\n<li>Presidente del tribunal: Antonio P\u00e9rez ambite <\/li>\n<li>enric Monte moreno (vocal)<\/li>\n<li>joaquim Llisterri boix (vocal)<\/li>\n<li>vicente Quesada paloma (vocal)<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Tesis doctoral de Francisco Diaz Perez Se analizan las posibilidades y deficiencias de los modelos ocultos de markov para el [&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":[1890,332,2528,126,16008,27844,12858,2535],"tags":[30646,4153,105846,43676,16193,3367],"class_list":["post-41921","post","type-post","status-publish","format-standard","hentry","category-ciencia-de-los-ordenadores","category-ciencias-tecnologicas","category-inteligencia-artificial","category-matematicas","category-politecnica-de-madrid","category-reconocimiento-y-sintetizacion-de-habla","category-sistemas-de-reconocimiento-de-caracteres","category-tecnologia-de-los-ordenadores","tag-antonio-perez-ambite","tag-enric-monte-moreno","tag-francisco-diaz-perez","tag-joaquim-llisterri-boix","tag-pedro-gomez-vilda","tag-vicente-quesada-paloma"],"_links":{"self":[{"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/posts\/41921","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=41921"}],"version-history":[{"count":0,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/posts\/41921\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/media?parent=41921"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/categories?post=41921"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/tags?post=41921"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}