{"id":1777,"date":"2026-07-02T11:32:36","date_gmt":"2026-07-02T11:32:36","guid":{"rendered":"https:\/\/euskorpora.eus\/?p=1777"},"modified":"2026-10-05T12:48:45","modified_gmt":"2026-10-05T12:48:45","slug":"basque-speaker-diarization-challenge","status":"publish","type":"post","link":"https:\/\/euskorpora.eus\/en\/evento\/basque-speaker-diarization-challenge\/","title":{"rendered":"Basque Speaker Diarization Challenge"},"content":{"rendered":"<p class=\"isSelectedEnd\"><strong>Euskorpora<\/strong> is pleased to launch the <strong>Basque Speaker Diarization Challenge<\/strong>, an initiative designed to advance research and innovation in speaker diarization for <strong>Basque (Euskara)<\/strong>, a language that remains significantly underrepresented in current speech technology benchmarks.<\/p>\n<p class=\"isSelectedEnd\">Speaker diarization addresses the fundamental question <strong>\u201cWho spoke when?\u201d<\/strong> by automatically detecting speaker turns and grouping speech segments belonging to the same individual. Although remarkable progress has been achieved in recent years for high-resource languages, realistic evaluation benchmarks for low-resource languages such as Basque are still scarce.<\/p>\n<p class=\"isSelectedEnd\">We invite researchers, academic groups, and industry teams to take part in this challenge and contribute to the development of more robust and inclusive speech technologies.<\/p>\n<h2>Challenge Objectives<\/h2>\n<p class=\"isSelectedEnd\">The Basque Speaker Diarization Challenge aims to:<\/p>\n<ul data-spread=\"false\">\n<li>Foster research on speaker diarization for Basque.<\/li>\n<li>Provide a realistic benchmark for low-resource language technologies.<\/li>\n<li>Encourage the development of systems capable of handling complex broadcast scenarios.<\/li>\n<li>Promote collaboration within the speech technology community.<\/li>\n<\/ul>\n<h2>Dataset<\/h2>\n<p class=\"isSelectedEnd\">Participants will have access to a unique corpus of <strong>49 real-world Basque television recordings<\/strong>, comprising approximately <strong>70 hours of audio<\/strong>.<\/p>\n<p class=\"isSelectedEnd\">The dataset includes a wide variety of challenging acoustic conditions:<\/p>\n<ul data-spread=\"false\">\n<li>Television programmes, interviews, debates, and spontaneous conversations.<\/li>\n<li>Overlapping speech.<\/li>\n<li>Background noise and music.<\/li>\n<li>Rapid speaker changes.<\/li>\n<li>Diverse recording environments and acoustic conditions.<\/li>\n<\/ul>\n<p class=\"isSelectedEnd\">The corpus is divided as follows:<\/p>\n<table style=\"height: 132px;\" width=\"810\">\n<tbody>\n<tr>\n<th>Split<\/th>\n<th>Recordings<\/th>\n<th>Duration<\/th>\n<\/tr>\n<tr>\n<td>Training<\/td>\n<td>29<\/td>\n<td>40 h<\/td>\n<\/tr>\n<tr>\n<td>Development<\/td>\n<td>8<\/td>\n<td>10 h<\/td>\n<\/tr>\n<tr>\n<td>Test<\/td>\n<td>12<\/td>\n<td>20 h<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2>Evaluation<\/h2>\n<p class=\"isSelectedEnd\">Submitted systems will be evaluated using internationally recognised speaker diarization metrics:<\/p>\n<ul data-spread=\"false\">\n<li><strong>Diarization Error Rate (DER)<\/strong> \u2013 Official ranking metric.<\/li>\n<li><strong>Jaccard Error Rate (JER)<\/strong> \u2013 Complementary secondary metric.<\/li>\n<\/ul>\n<h2>Important Dates<\/h2>\n<table style=\"height: 301px;\" width=\"845\">\n<thead>\n<tr>\n<th><strong>Phase<\/strong><\/th>\n<th><strong>Date<\/strong><\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Challenge Announcement (Registration Opens)<\/td>\n<td>July 2, 2026<\/td>\n<\/tr>\n<tr>\n<td>Participation Application Deadline (Registration Form &amp; System Proposal)<\/td>\n<td>July 24, 2026<\/td>\n<\/tr>\n<tr>\n<td>Release of Training and Development Sets &amp; Evaluation Repository<\/td>\n<td>July 30, 2026<\/td>\n<\/tr>\n<tr>\n<td>Development Results Submission Deadline<\/td>\n<td>October 16, 2026<\/td>\n<\/tr>\n<tr>\n<td>Release of Test Set<\/td>\n<td>October 21, 2026<\/td>\n<\/tr>\n<tr>\n<td>Test Results Submission Deadline<\/td>\n<td>November 11, 2026<\/td>\n<\/tr>\n<tr>\n<td>System Description Paper Submission Deadline<\/td>\n<td>December 11, 2026<\/td>\n<\/tr>\n<tr>\n<td>Results Announcement<\/td>\n<td>TBA<\/td>\n<\/tr>\n<tr>\n<td>Workshop Presentation<\/td>\n<td>TBA<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2>How to Participate<\/h2>\n<p class=\"isSelectedEnd\">To join the challenge, teams must complete the <strong><a href=\"https:\/\/docs.google.com\/forms\/d\/e\/1FAIpQLSd0WTKU3hc9M1Qk6BRdtwIhZErjfH3pRTsXaxlTPRIwV9cYfg\/viewform?usp=publish-editor\">registration form<\/a><\/strong>\u00a0and submit a short description of their proposed approach.<\/p>\n<p class=\"isSelectedEnd\">Detailed participation rules, submission requirements, and evaluation procedures can be found in the <strong><a href=\"https:\/\/euskorpora.eus\/wp-content\/uploads\/2026\/07\/challenge-description-2-1.pdf\">challenge-description <\/a><\/strong>and the <strong><a href=\"https:\/\/euskorpora.eus\/wp-content\/uploads\/2026\/07\/challenge-terms-and-conditions-1.pdf\">official challenge <span data-teams=\"true\">terms and conditions<\/span><\/a>.<\/strong><\/p>\n<h2 class=\"PDq2pG_selectionAnchorContainer\" data-section-id=\"5gnibj\" data-start=\"938\" data-end=\"949\">Funding<\/h2>\n<p data-start=\"951\" data-end=\"1292\">The Basque Speaker Diarization Challenge includes a <strong data-start=\"1003\" data-end=\"1039\">total funding budget of \u20ac210,000<\/strong> to support the development of participating systems. Financial support of <strong data-start=\"1114\" data-end=\"1147\">up to \u20ac70,000 per participant<\/strong> will be awarded to selected participants, in accordance with the challenge evaluation and funding criteria described in the official guidelines.<\/p>\n<h2>Join the Challenge<\/h2>\n<p class=\"isSelectedEnd\">The Basque Speaker Diarization Challenge provides a unique opportunity to evaluate cutting-edge diarization systems on realistic Basque broadcast data and contribute to the advancement of speech technologies for low-resource languages.<\/p>\n<p>We look forward to receiving your submissions and building together a stronger research community around Basque speech technology.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Euskorpora is pleased to launch the Basque Speaker Diarization Challenge, an initiative designed to advance research and innovation in speaker diarization for Basque (Euskara), a language that remains significantly underrepresented in current speech technology benchmarks. Speaker diarization addresses the fundamental question \u201cWho spoke when?\u201d by automatically detecting speaker turns and grouping speech segments belonging to [&hellip;]<\/p>\n","protected":false},"author":2,"featured_media":1792,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[23],"tags":[],"class_list":["post-1777","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-evento"],"_links":{"self":[{"href":"https:\/\/euskorpora.eus\/en\/wp-json\/wp\/v2\/posts\/1777","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/euskorpora.eus\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/euskorpora.eus\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/euskorpora.eus\/en\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/euskorpora.eus\/en\/wp-json\/wp\/v2\/comments?post=1777"}],"version-history":[{"count":8,"href":"https:\/\/euskorpora.eus\/en\/wp-json\/wp\/v2\/posts\/1777\/revisions"}],"predecessor-version":[{"id":1990,"href":"https:\/\/euskorpora.eus\/en\/wp-json\/wp\/v2\/posts\/1777\/revisions\/1990"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/euskorpora.eus\/en\/wp-json\/wp\/v2\/media\/1792"}],"wp:attachment":[{"href":"https:\/\/euskorpora.eus\/en\/wp-json\/wp\/v2\/media?parent=1777"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/euskorpora.eus\/en\/wp-json\/wp\/v2\/categories?post=1777"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/euskorpora.eus\/en\/wp-json\/wp\/v2\/tags?post=1777"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}