Towards Digital Preservation of Efik: TTS for a Low-Resource African Language
Abstract
Efik, a tonal language spoken by about 3 million second language speakers and 1.5 million native speakers in Southeastern Nigeria, remains underrepresented in speech synthesis research. We present the first documented end-to-end text-to-speech study for Efik, introducing a curated single speaker corpus of 2,632 utterances totaling three hours and a comparative evaluation of four neural models (VITS, MMS-TTS, SpeechT5, and Orpheus-TTS) under low resource conditions. Native speakers evaluated the systems using MOS, Nat-MOS, and A-MOS. MMS-TTS achieved the highest MOS of 3.80 +/- 0.63 and produced more stable long form speech, though tonal errors persisted. Other models showed greater tonal and prosodic inconsistencies. These results provide a reproducible baseline and highlight the need for larger corpora and tone aware modeling for tonal African languages.
Cite
@article{arxiv.2607.04515,
title = {Towards Digital Preservation of Efik: TTS for a Low-Resource African Language},
author = {Offiong Bassey Edet and Emmanuel Oyo-Ita and Archibong Okon Archibong and David Effanga Bassey and Mbuotidem Sunday Awak},
journal= {arXiv preprint arXiv:2607.04515},
year = {2026}
}
Comments
6 pages, 2 figures. Accepted to Interspeech 2026