AI Speech-Recognition Assessment of Oral Reading Fluency in isiXhosa

Early Grade Reading Assessments (EGRA) — one-on-one oral reading tests that flag which children are falling behind — are the standard tool for measuring literacy in low- and middle-income countries, but administering them requires trained human assessors and is rarely done in African languages other than the few with existing speech-recognition support. A research team led by the University of Cape Town, with the University of Pretoria, Western Sydney University, Universidade Federal de Pernambuco and Macquarie University, set out to automate EGRA scoring for isiXhosa, one of South Africa's official languages.
Over an 8-month data-collection effort, the team gathered 14,971 EGRA recordings (more than 19 hours of child speech) from grades 1–4 in South African schools, with support from a Gates Foundation Grand Challenges grant. Three independent human markers first validated the scoring approach against an EGRA expert, reaching 85% agreement; fine-tuned speech-recognition models were then benchmarked against that human-labelled data, reaching roughly 91% diagnostic efficiency.
The published evaluation is unusually candid about limits: the authors note that no single model configuration minimised both false-positive and false-negative error rates simultaneously, meaning any early deployment would trade one kind of misclassification for another. The work remains a research-stage validation rather than a fielded national assessment system.

Read the full analysis: https://gcgh.grandchallenges.org/grant/automating-early-grade-reading-assessments-egra-african-languages-using-voice-recognition-ai