English

Bemba Speech Translation: Exploring a Low-Resource African Language

Computation and Language 2025-08-14 v3 Sound Audio and Speech Processing

Abstract

This paper describes our system submission to the International Conference on Spoken Language Translation (IWSLT 2025), low-resource languages track, namely for Bemba-to-English speech translation. We built cascaded speech translation systems based on Whisper and NLLB-200, and employed data augmentation techniques, such as back-translation. We investigate the effect of using synthetic data and discuss our experimental setup.

Keywords

Cite

@article{arxiv.2505.02518,
  title  = {Bemba Speech Translation: Exploring a Low-Resource African Language},
  author = {Muhammad Hazim Al Farouq and Aman Kassahun Wassie and Yasmin Moslem},
  journal= {arXiv preprint arXiv:2505.02518},
  year   = {2025}
}

Comments

IWSLT 2025

R2 v1 2026-06-28T23:21:17.233Z