mlsanityData to 7 Oct 2026

Towards Digital Preservation of Efik: TTS for a Low-Resource African Language

arXiv 2607.04515 ↗First posted 5 Jul 2026cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 14 of its 27 references that are in the map. First posted on arXiv 5 Jul 2026.

Builds on

14 of 27 references.

References · 14

  1. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  2. 2021XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scalecited by 589
  3. 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 555
  4. 2023Scaling Speech Technology to 1,000+ Languagescited by 401
  5. 2021SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processingcited by 177
  6. 2023Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervisioncited by 167
  7. 2020Low-resource Languages: A Review of Past Work and Future Challengescited by 90
  8. 2022BibleTTS: a large, high-fidelity, multilingual, and uniquely African speech corpuscited by 31
  9. 2022Building African Voicescited by 14
  10. 2026WAXAL: A Large-Scale Multilingual African Language Speech Corpuscited by 10
  11. 2025Ibom NLP: A Step Toward Inclusive Natural Language Processing for Nigeria's Minority Languagescited by 6
  12. 2024Building a Luganda Text-to-Speech Model From Crowdsourced Datacited by 1
2 more
  1. 2025Edge-Based Speech Transcription and Synthesis for Kinyarwanda and Swahili Languagescited by 1
  2. 2026Developing an English-Efik Corpus and Machine Translation System for Digitization Inclusioncited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Tone on a Budget: A Reference-Free Metric for Lexical Tone in Massively Multilingual Text-to-Speechcited by 0