{"id":106,"date":"2026-08-07T13:01:40","date_gmt":"2026-08-07T13:01:40","guid":{"rendered":"https:\/\/aiss.mohdluqman.com\/?p=106"},"modified":"2026-09-11T14:00:43","modified_gmt":"2026-09-11T14:00:43","slug":"urhiodsynth","status":"publish","type":"post","link":"https:\/\/aiss.mohdluqman.com\/?p=106","title":{"rendered":"UrHiOdSynth"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\"><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>We present UrHiOdSynth, a three-language parallel S2ST dataset containing approximately 75 hours of speech across Urdu, Hindi, and Odia.<\/li>\n\n\n\n<li>The corpus consists of 10,735 aligned sentence triplets, with an average utterance length of 8.45 seconds.<\/li>\n\n\n\n<li>UrHiOdSynth represents the largest multi-domain resource offering aligned speech and text for S2ST in this language context. <\/li>\n\n\n\n<li>Beyond speech-to-speech translation, the dataset supports tasks such as automatic speech recognition, speech-to-text translation, text-to-speech synthesis, and machine translation. <\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n\n\n\n<div class=\"wp-block-buttons is-content-justification-center is-layout-flex wp-container-core-buttons-is-layout-3e41869c wp-block-buttons-is-layout-flex\">\n<div class=\"wp-block-button is-style-outline is-style-outline--1\"><a class=\"wp-block-button__link has-light-green-cyan-color has-vivid-red-background-color has-text-color has-background has-link-color has-medium-font-size has-custom-font-size wp-element-button\" href=\"https:\/\/huggingface.co\/datasets\/urhinodsynth\/urhinodsynth\/tree\/main\">Dataset<\/a><\/div>\n\n\n\n<div class=\"wp-block-button is-style-outline is-style-outline--2\"><a class=\"wp-block-button__link has-light-green-cyan-color has-vivid-red-background-color has-text-color has-background has-link-color has-medium-font-size has-custom-font-size wp-element-button\" href=\"https:\/\/aclanthology.org\/2026.loreslm-1.50\/\">  Paper <\/a><\/div>\n<\/div>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":8,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[10],"tags":[],"class_list":["post-106","post","type-post","status-publish","format-standard","hentry","category-datasets"],"_links":{"self":[{"href":"https:\/\/aiss.mohdluqman.com\/index.php?rest_route=\/wp\/v2\/posts\/106","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/aiss.mohdluqman.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/aiss.mohdluqman.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/aiss.mohdluqman.com\/index.php?rest_route=\/wp\/v2\/users\/8"}],"replies":[{"embeddable":true,"href":"https:\/\/aiss.mohdluqman.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=106"}],"version-history":[{"count":7,"href":"https:\/\/aiss.mohdluqman.com\/index.php?rest_route=\/wp\/v2\/posts\/106\/revisions"}],"predecessor-version":[{"id":209,"href":"https:\/\/aiss.mohdluqman.com\/index.php?rest_route=\/wp\/v2\/posts\/106\/revisions\/209"}],"wp:attachment":[{"href":"https:\/\/aiss.mohdluqman.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=106"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/aiss.mohdluqman.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=106"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/aiss.mohdluqman.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=106"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}