1000 African Voices: Advancing inclusive multi-speaker multi-accent speech synthesis
This addresses the problem of limited voice diversity in speech synthesis for African users and applications, representing a novel domain-specific advancement.
The paper tackles the under-representation of African English accents in speech synthesis by developing Afro-TTS, a system that generates speech in 86 African accents with 1000 personas, achieving naturalness and accentedness through speaker interpolation.
Recent advances in speech synthesis have enabled many useful applications like audio directions in Google Maps, screen readers, and automated content generation on platforms like TikTok. However, these systems are mostly dominated by voices sourced from data-rich geographies with personas representative of their source data. Although 3000 of the world's languages are domiciled in Africa, African voices and personas are under-represented in these systems. As speech synthesis becomes increasingly democratized, it is desirable to increase the representation of African English accents. We present Afro-TTS, the first pan-African accented English speech synthesis system able to generate speech in 86 African accents, with 1000 personas representing the rich phonological diversity across the continent for downstream application in Education, Public Health, and Automated Content Creation. Speaker interpolation retains naturalness and accentedness, enabling the creation of new voices.