{"id":26215,"date":"2024-01-18T11:02:11","date_gmt":"2024-01-18T10:02:11","guid":{"rendered":"https:\/\/lium.univ-lemans.fr\/?p=26215"},"modified":"2024-01-22T11:16:18","modified_gmt":"2024-01-22T10:16:18","slug":"when-neural-speech-technologies-encounter-non-conventional-data-a-discussion-on-speech-recognition-and-speech-synthesis","status":"publish","type":"post","link":"https:\/\/lium.univ-lemans.fr\/en\/when-neural-speech-technologies-encounter-non-conventional-data-a-discussion-on-speech-recognition-and-speech-synthesis\/","title":{"rendered":"When neural speech technologies encounter non-conventional data: A discussion on speech recognition and speech synthesis"},"content":{"rendered":"<div class=\"panel-grid\" id=\"pg-26215-0\" ><div class=\"panel-grid-core\"><div class=\"panel-grid-cell\" id=\"pgc-26215-0-0\" ><div class=\"panel-widget-style\" ><h2 style=\"color: #e5442d;\">Seminar from Aghilas Sini (LIUM) <\/h2>\n<p>&nbsp;<\/p>\n<p><strong>Date:<\/strong> 19\/01\/2024<br \/>\n<strong>Time:<\/strong> 10h15<br \/>\n<strong>Localization:<\/strong> IC2, Boardroom<br \/>\n<strong>Speaker:<\/strong> <a href=\"http:\/\/lium.univ-lemans.fr\/en\/team\/aghilas-sini\/\">Aghilas Sini<\/a><br \/>\n&nbsp;<br \/>\n&nbsp;<\/p>\n<p align=\"center\"><strong> When neural speech technologies encounter non-conventional data: A discussion on speech recognition and speech synthesis.<\/strong><\/p>\n<p>&nbsp;<\/p>\n<p align=\"justify\">Most neural speech technologies are developed using dedicated data recorded under favorable acoustic conditions. This data is instrumental in setting up the underlying models and facilitates a fair and straightforward comparison, enabling the establishment of benchmarks. However, it is intriguing to analyze and quantify the ability of neural speech systems to leverage non-dedicated data and real-world conditions, whether during the learning or inference stages.<\/p>\n<p align=\"justify\">To address these questions and related issues, I will discuss the impact of non-conventional data on state-of-the-art speech technology through two specific practical examples: pronunciation assessment of children&#8217;s speech in a noisy classroom and the development of a fair speech synthesis system for the French language using amateur recording data. I will then explore two speech synthesis techniques, namely voice conversion and voice cloning, to investigate speaker identity and assess data quality.<\/p>\n<p align=\"justify\">Furthermore, I will share ongoing and future work related to multimodal and multilingual data, particularly in the context of deep-fake speech detection and speech-to-speech translation. In conclusion, I will present reflections on the data qualification process, aiming to estimate and anticipate the performance of a given system.<\/p><\/div><\/div><\/div><\/div><div class=\"panel-grid\" id=\"pg-26215-1\" ><div class=\"panel-grid-core\"><div class=\"panel-grid-cell\" id=\"pgc-26215-1-0\" >&nbsp;<\/div><div class=\"panel-grid-cell\" id=\"pgc-26215-1-1\" >&nbsp;<\/div><\/div><\/div>","protected":false},"excerpt":{"rendered":"<p>Seminar from Aghilas Sini (LIUM) &nbsp; Date: 19\/01\/2024 Time: 10h15 Localization: IC2, Boardroom Speaker: Aghilas Sini &nbsp; &nbsp; When neural speech technologies encounter non-conventional data: A discussion on speech recognition and speech synthesis. &nbsp; Most neural speech technologies are developed using dedicated data recorded under favorable acoustic conditions. This data is instrumental in setting up [&hellip;]<\/p>\n<p class=\"more-link style2\"><a href=\"https:\/\/lium.univ-lemans.fr\/en\/when-neural-speech-technologies-encounter-non-conventional-data-a-discussion-on-speech-recognition-and-speech-synthesis\/\"  class=\"themebutton\"><span class=\"more-text\">READ MORE<\/span><span class=\"more-icon\"><i class=\"fa fa-angle-right fa-lg\"><\/i><\/span><\/a><\/p>\n","protected":false},"author":14,"featured_media":13238,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[46,43],"tags":[49],"acf":[],"_links":{"self":[{"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/posts\/26215"}],"collection":[{"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/users\/14"}],"replies":[{"embeddable":true,"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/comments?post=26215"}],"version-history":[{"count":0,"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/posts\/26215\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/media\/13238"}],"wp:attachment":[{"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/media?parent=26215"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/categories?post=26215"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/tags?post=26215"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}