{"id":2834,"date":"2025-03-10T18:55:31","date_gmt":"2025-03-10T18:55:31","guid":{"rendered":"http:\/\/airlab.local\/?page_id=2834"},"modified":"2025-03-21T17:11:03","modified_gmt":"2025-03-21T17:11:03","slug":"benchmarking-automatic-speech-recognition-models-for-african-languages","status":"publish","type":"page","link":"https:\/\/air.ug\/?page_id=2834","title":{"rendered":"Project : Benchmarking Automatic Speech Recognition Models for African Languages"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-page\" data-elementor-id=\"2834\" class=\"elementor elementor-2834\">\n\t\t\t\t<div class=\"elementor-element elementor-element-d297aae e-flex e-con-boxed e-con e-parent\" data-id=\"d297aae\" data-element_type=\"container\" data-e-type=\"container\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t<div class=\"elementor-element elementor-element-1c72a05 e-con-full e-flex e-con e-child\" data-id=\"1c72a05\" data-element_type=\"container\" data-e-type=\"container\" data-settings=\"{&quot;background_background&quot;:&quot;classic&quot;}\">\n\t\t<div class=\"elementor-element elementor-element-9ab7503 e-con-full e-flex e-con e-child\" data-id=\"9ab7503\" data-element_type=\"container\" data-e-type=\"container\" data-settings=\"{&quot;background_background&quot;:&quot;classic&quot;}\">\n\t\t\t\t<div class=\"elementor-element elementor-element-a9e4974 elementor-widget elementor-widget-heading\" data-id=\"a9e4974\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Funders<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-825b0ff elementor-widget elementor-widget-text-editor\" data-id=\"825b0ff\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p>Gates Foundation, Clear Global<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-2459449 elementor-widget elementor-widget-heading\" data-id=\"2459449\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Duration<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-ec5eeae elementor-widget elementor-widget-text-editor\" data-id=\"ec5eeae\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p>2024-2025<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-39dbb44 elementor-widget elementor-widget-heading\" data-id=\"39dbb44\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Keywords (Technologies and Domain)<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-619c7ec elementor-widget elementor-widget-text-editor\" data-id=\"619c7ec\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p>Language Technologies, Automatic Speech Recognition<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-abc782c e-con-full e-flex e-con e-child\" data-id=\"abc782c\" data-element_type=\"container\" data-e-type=\"container\">\n\t\t\t\t<div class=\"elementor-element elementor-element-0889ff8 elementor-widget elementor-widget-heading\" data-id=\"0889ff8\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Benchmarking Automatic Speech Recognition Models for African Languages<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-69bc5c2 elementor-widget elementor-widget-text-editor\" data-id=\"69bc5c2\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p>The area of Automatic Speech Recognition (ASR) is of particular importance, as it is crucial to provide voice services (recognition and speaking) to underserved groups. However, it remains unclear how much data needs to be collected to achieve a \u201cgood\u201d Automatic Speech Recognition (ASR) model in low-resource languages. It has been found that the amount of speech data required for ASR model training data has a significant influence on the robustness of ASR systems. Moreover, it is also unclear how much data is required to build domain-specific ASR models. The objective of the research is to develop an evidence base for the amount of speech data required to build a good automatic speech recognition model across priority \u201clow-resource\u201d African languages<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-14914bc e-con-full e-flex e-con e-child\" data-id=\"14914bc\" data-element_type=\"container\" data-e-type=\"container\" data-settings=\"{&quot;background_background&quot;:&quot;classic&quot;}\">\n\t\t<div class=\"elementor-element elementor-element-aa2e99e e-con-full e-flex e-con e-child\" data-id=\"aa2e99e\" data-element_type=\"container\" data-e-type=\"container\" data-settings=\"{&quot;background_background&quot;:&quot;classic&quot;}\">\n\t\t\t\t<div class=\"elementor-element elementor-element-2dcd67d elementor-widget elementor-widget-heading\" data-id=\"2dcd67d\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Outputs (Datasets, publications, models)<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-517005a elementor-widget elementor-widget-text-editor\" data-id=\"517005a\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p><strong>To build<\/strong> a benchmark speech corpus of African languages.<br \/><strong>To develop<\/strong> ASR models for African languages.<br \/><strong>To evaluate<\/strong> the performance of ASR models for African languages.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"<p>Funders Gates Foundation, Clear Global Duration 2024-2025 Keywords (Technologies and Domain) Language Technologies, Automatic Speech Recognition Benchmarking Automatic Speech Recognition Models for African Languages The area of Automatic Speech Recognition (ASR) is of particular importance, as it is crucial to provide voice services (recognition and speaking) to underserved groups. However, it remains unclear how much [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"site-sidebar-layout":"no-sidebar","site-content-layout":"page-builder","ast-site-content-layout":"full-width-container","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":"disabled","ast-breadcrumbs-content":"","ast-featured-img":"disabled","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":"set","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"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-opacity":"","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-opacity":"","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-opacity":"","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-opacity":"","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-opacity":"","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-opacity":"","overlay-gradient":""}},"footnotes":""},"class_list":["post-2834","page","type-page","status-publish","hentry"],"rttpg_featured_image_url":null,"rttpg_author":{"display_name":"airlab","author_link":"https:\/\/air.ug\/?author=1"},"rttpg_comment":0,"rttpg_category":null,"rttpg_excerpt":"Funders Gates Foundation, Clear Global Duration 2024-2025 Keywords (Technologies and Domain) Language Technologies, Automatic Speech Recognition Benchmarking Automatic Speech Recognition Models for African Languages The area of Automatic Speech Recognition (ASR) is of particular importance, as it is crucial to provide voice services (recognition and speaking) to underserved groups. However, it remains unclear how much&hellip;","_links":{"self":[{"href":"https:\/\/air.ug\/index.php?rest_route=\/wp\/v2\/pages\/2834","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/air.ug\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/air.ug\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/air.ug\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/air.ug\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=2834"}],"version-history":[{"count":12,"href":"https:\/\/air.ug\/index.php?rest_route=\/wp\/v2\/pages\/2834\/revisions"}],"predecessor-version":[{"id":3071,"href":"https:\/\/air.ug\/index.php?rest_route=\/wp\/v2\/pages\/2834\/revisions\/3071"}],"wp:attachment":[{"href":"https:\/\/air.ug\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=2834"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}