Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Bemba Speech Translation: Exploring a Low-Resource African Language

Domain:

natural language processing

Record type:

papermodel
Creator:
FarWasMos
Host:avatar
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. IWSLT 2025

Visit

arxiv.org

Tasks

machine translationspeech processingspeech translation

Languages

Bemba

Tags

Computation and LanguageSoundAudio and Speech Processing

Similar

A Low-Resource Language Translation: French To MooréMendoLeo/african-low-resource-speechContributing to Speech-to-Speech Translation for African Low-Resource Languages : Study of French-Mooré PairImproving End-to-End Speech Translation for the Low Resource Language Fongbe to FrenchNeural Machine Translation for Mooré, a Low-Resource LanguageNaijaS2ST: A Multi-Accent Benchmark for Speech-to-Speech Translation in Low-Resource Nigerian Languages

A Low-Resource Language Translation: French To Mooré

Natural Language Processing (NLP) is an exciting field of artificial intelligence wit

MendoLeo/african-low-resource-speech

World Collection of SOTA NLP papers, tools, datasets, and technologies analysis for Africain languag

Contributing to Speech-to-Speech Translation for African Low-Resource Languages : Study of French-Mooré Pair

Improving End-to-End Speech Translation for the Low Resource Language Fongbe to French

This study addresses the challenges of end-to-end (E2E) Speech-to-Text Translation (STT) for the low

Neural Machine Translation for Mooré, a Low-Resource Language

NaijaS2ST: A Multi-Accent Benchmark for Speech-to-Speech Translation in Low-Resource Nigerian Languages

Speech translation for low-resource languages remains fundamentally limited by the scarcity of high-quality, diverse parallel speech data, a challenge that is especially pronounced in African linguistic contexts. To address this, we introduce NaijaS2ST, a parallel