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.
Bemba Speech Translation: Exploring a Low-Resource African Language
A cascaded speech translation system for low-resource languages using Whisper and NLLB-200 employs data augmentation and synthetic data to improve performance.
- Year
- 2025
- Venue
- arXiv 2025
- Authors
- 3
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/2505.02518v3ARXIV-DEFAULT
- TL;DR
- Semantic Scholar