5 papers
Tone-Conditioned Curriculum Learning for Low-Resource Bantu Speech Recognition
Kesego Mokgosi, Vukosi Marivate, Sitwala Mundia +3
Southern Bantu languages are spoken by over 80 million people, yet current foundation ASR models still produce zero-shot WER above 100%, which limits practical use in education and…
Evaluating Multimodal LLMs for Inpatient Diagnosis: Real-World Performance, Safety, and Cost Across Ten Frontier Models
Bruce A. Bassett, Amy Rouillard, Sitwala Mundia +8
Background: Large language models (LLMs) are increasingly proposed for diagnostic support, but few evaluations use real-world multimodal inpatient data, particularly in low and mid…
From Handwriting to Structured Data: Benchmarking AI Digitisation of Handwritten Forms
Nicholas Pather, Joshua Fouché, Sitwala Mundia +5
Manual digitisation of structured handwritten documents is slow and costly. We benchmark 17 leading frontier multi-modal large language models and open-source models against a very…
Can LLMs Accurately Score Medical Diagnoses and Clinical Reasoning?
Amy Rouillard, Sitwala Mundia, Linda Camara +8
Evaluating medical AI systems using expert clinician panels is costly and slow, motivating the use of large language models (LLMs) as alternative adjudicators. Here, we evaluate an…
Swivuriso: The South African Next Voices Multilingual Speech Dataset
Vukosi Marivate, Kayode Olaleye, Sitwala Mundia +19
This paper introduces Swivuriso, a 3000-hour multilingual speech dataset developed as part of the African Next Voices project, to support the development and benchmarking of automa…