mlsanityData to 13 Oct 2026

Bemba Speech Translation: Exploring a Low-Resource African Language

arXiv 2505.02518 ↗First posted 5 May 2025cs.CL cs.SD eess.AScited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Builds on 16 of its 29 references that are in the map. First posted on arXiv 5 May 2025.

Builds on

16 of 29 references.

References · 16

  1. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,004
  2. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,472
  3. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,793
  4. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,302
  5. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 784
  6. 2021The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translationcited by 556
  7. 2020The Tatoeba Translation Challenge -- Realistic Data Sets for Low Resource and Multilingual MTcited by 127
  8. 2021Survey of Low-Resource Machine Translationcited by 92
  9. 2024SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languagescited by 41
  10. 2023AfriMTE and AfriCOMET: Enhancing COMET to Embrace Under-resourced African Languagescited by 24
  11. 2024Findings of the IWSLT 2024 Evaluation Campaigncited by 19
  12. 2021BembaSpeech: A Speech Recognition Corpus for the Bemba Languagecited by 14
4 more
  1. 2023BIG-C: a Multimodal Multi-Purpose Dataset for Bembacited by 9
  2. 2024Leveraging Synthetic Audio Data for End-to-End Low-Resource Speech Translationcited by 9
  3. 2019Adaptation of Machine Translation Models with Back-translated Data using Transductive Data Selection Methodscited by 8
  4. 2025SpeechT: Findings of the First Mentorship in Speech Translationcited by 1

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026AfriNLLB: Efficient Translation Models for African Languagescited by 2