Voice of a Continent: Mapping Africa's Speech Technology Frontier

TL;DR

This paper maps Africa's speech technology landscape, introduces SimbaBench and Simba models, and analyzes factors affecting performance to promote more inclusive speech technologies for African languages.

Contribution

It provides the first comprehensive benchmark and models for African speech tasks, addressing underrepresentation and guiding future resource development.

Findings

SimbaBench achieves state-of-the-art results across African languages.

Resource availability and language diversity significantly impact model performance.

Dataset quality and domain diversity influence speech technology effectiveness.

Abstract

Africa's rich linguistic diversity remains significantly underrepresented in speech technologies, creating barriers to digital inclusion. To alleviate this challenge, we systematically map the continent's speech space of datasets and technologies, leading to a new comprehensive benchmark SimbaBench for downstream African speech tasks. Using SimbaBench, we introduce the Simba family of models, achieving state-of-the-art performance across multiple African languages and speech tasks. Our benchmark analysis reveals critical patterns in resource availability, while our model evaluation demonstrates how dataset quality, domain diversity, and language family relationships influence performance across languages. Our work highlights the need for expanded speech technology resources that better reflect Africa's linguistic diversity and provides a solid foundation for future research and development efforts toward more inclusive speech technologies.