Accepted
1000 African Voices: Advancing inclusive multi-speaker multi-accent speech synthesis
- 25th Interspeech Conference, Interspeech 2024
Abstract
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 Tik-tok. However, these systems are mostly dominated by voices sourced from data-rich geographies with personas rep- resentative 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 be- comes 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 75 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 interpola- tion retains naturalness and accentedness, enabling the creation of new voices.