{"id":3011,"date":"2024-11-22T15:59:00","date_gmt":"2024-11-22T14:59:00","guid":{"rendered":"https:\/\/aholab.ehu.eus\/aholab\/?p=3011"},"modified":"2025-06-06T11:43:37","modified_gmt":"2025-06-06T09:43:37","slug":"personalized-speech-synthesis-using-deep-learning","status":"publish","type":"post","link":"https:\/\/aholab.ehu.eus\/aholab\/personalized-speech-synthesis-using-deep-learning\/","title":{"rendered":"2024, Victor Garc\u00eda: Personalized Speech Synthesis using Deep Learning"},"content":{"rendered":"\n<p><strong>Student: <\/strong>Victor Garc\u00eda Romillo<strong><br>Supervisor:<\/strong> Eva Navas Cord\u00f3n e Inma Hern\u00e1ez Rioja<\/p>\n\n\n\n<p><strong>Viva:<\/strong> 22\/11\/2024<\/p>\n\n\n\n<p><strong><u>DESCRIPTION<\/u><\/strong><br>The aim of this project is to generate improvements in speech technologies, especially in the Text-to-Speech field, so that people affected by speech disorders could be benefited by the use of this technology. The current Text-to-Speech developed models are built using DNNs and offer high-quality voices, but still have large margin of improvement. The main objectives to be fulfilled are:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Improve the robustness of current systems at synthesis time.<\/li>\n\n\n\n<li>Reduce the dependence on huge amounts of data to train the models.<\/li>\n\n\n\n<li>Obtain personalized synthetic voices trough improvements over the current systems, especially focusing on personalization from voices with some pathology.<\/li>\n<\/ul>\n\n\n\n<figure class=\"wp-block-embed is-type-wp-embed is-provider-aholab wp-block-embed-aholab\"><div class=\"wp-block-embed__wrapper\">\n<blockquote class=\"wp-embedded-content\" data-secret=\"34QqcuwCoL\"><a href=\"https:\/\/aholab.ehu.eus\/aholab\/download\/victor-garcia-personalized-speech-synthesis-using-deep-learning\/\">Victor Garc\u00eda: Personalized Speech Synthesis using Deep Learning<\/a><\/blockquote><iframe loading=\"lazy\" class=\"wp-embedded-content\" sandbox=\"allow-scripts\" security=\"restricted\" style=\"position: absolute; visibility: hidden;\" title=\"&#8220;Victor Garc\u00eda: Personalized Speech Synthesis using Deep Learning&#8221; &#8212; aholab\" src=\"https:\/\/aholab.ehu.eus\/aholab\/download\/victor-garcia-personalized-speech-synthesis-using-deep-learning\/embed\/#?secret=yUA9nTTw6z#?secret=34QqcuwCoL\" data-secret=\"34QqcuwCoL\" width=\"600\" height=\"338\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"><\/iframe>\n<\/div><\/figure>\n","protected":false},"excerpt":{"rendered":"<p>Student: Victor Garc\u00eda RomilloSupervisor: Eva Navas Cord\u00f3n e Inma Hern\u00e1ez Rioja Viva: 22\/11\/2024 DESCRIPTIONThe aim of this project is to generate improvements in speech technologies, especially in the Text-to-Speech field, so that people affected by speech disorders could be benefited by the use of this technology. The current Text-to-Speech developed models are built using DNNs&#8230;<\/p>\n","protected":false},"author":3,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_es_post_content":"","_es_post_name":"","_es_post_excerpt":"","_es_post_title":"","_eu_post_content":"","_eu_post_name":"","_eu_post_excerpt":"","_eu_post_title":"","_en_post_content":"<!-- wp:paragraph -->\n<p><strong>Student: <\/strong>Victor Garc\u00eda Romillo<strong><br>Supervisor:<\/strong> Eva Navas Cord\u00f3n e Inma Hern\u00e1ez Rioja<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:paragraph -->\n<p><strong>Viva:<\/strong> 22\/11\/2024<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:paragraph -->\n<p><strong><u>DESCRIPTION<\/u><\/strong><br>The aim of this project is to generate improvements in speech technologies, especially in the Text-to-Speech field, so that people affected by speech disorders could be benefited by the use of this technology. The current Text-to-Speech developed models are built using DNNs and offer high-quality voices, but still have large margin of improvement. The main objectives to be fulfilled are:<\/p>\n<!-- \/wp:paragraph -->\n\n<!-- wp:list -->\n<ul class=\"wp-block-list\"><!-- wp:list-item -->\n<li>Improve the robustness of current systems at synthesis time.<\/li>\n<!-- \/wp:list-item -->\n\n<!-- wp:list-item -->\n<li>Reduce the dependence on huge amounts of data to train the models.<\/li>\n<!-- \/wp:list-item -->\n\n<!-- wp:list-item -->\n<li>Obtain personalized synthetic voices trough improvements over the current systems, especially focusing on personalization from voices with some pathology.<\/li>\n<!-- \/wp:list-item --><\/ul>\n<!-- \/wp:list -->\n\n<!-- wp:embed {\"url\":\"https:\/\/aholab.ehu.eus\/aholab\/download\/victor-garcia-personalized-speech-synthesis-using-deep-learning\/\",\"type\":\"wp-embed\",\"providerNameSlug\":\"aholab\"} -->\n<figure class=\"wp-block-embed is-type-wp-embed is-provider-aholab wp-block-embed-aholab\"><div class=\"wp-block-embed__wrapper\">\nhttps:\/\/aholab.ehu.eus\/aholab\/download\/victor-garcia-personalized-speech-synthesis-using-deep-learning\/\n<\/div><\/figure>\n<!-- \/wp:embed -->","_en_post_name":"personalized-speech-synthesis-using-deep-learning","_en_post_excerpt":"","_en_post_title":"2024, Victor Garc\u00eda: Personalized Speech Synthesis using Deep Learning","edit_language":"en","footnotes":""},"categories":[68],"tags":[],"class_list":["post-3011","post","type-post","status-publish","format-standard","hentry","category-phd-thesis-finished"],"_links":{"self":[{"href":"https:\/\/aholab.ehu.eus\/aholab\/wp-json\/wp\/v2\/posts\/3011","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/aholab.ehu.eus\/aholab\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/aholab.ehu.eus\/aholab\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/aholab.ehu.eus\/aholab\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/aholab.ehu.eus\/aholab\/wp-json\/wp\/v2\/comments?post=3011"}],"version-history":[{"count":5,"href":"https:\/\/aholab.ehu.eus\/aholab\/wp-json\/wp\/v2\/posts\/3011\/revisions"}],"predecessor-version":[{"id":3836,"href":"https:\/\/aholab.ehu.eus\/aholab\/wp-json\/wp\/v2\/posts\/3011\/revisions\/3836"}],"wp:attachment":[{"href":"https:\/\/aholab.ehu.eus\/aholab\/wp-json\/wp\/v2\/media?parent=3011"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/aholab.ehu.eus\/aholab\/wp-json\/wp\/v2\/categories?post=3011"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/aholab.ehu.eus\/aholab\/wp-json\/wp\/v2\/tags?post=3011"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}