Bemba Speech Translation: Exploring a Low-Resource African Language
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916894846484480 |
|---|---|
| author | Farouq, Muhammad Hazim Al Wassie, Aman Kassahun Moslem, Yasmin |
| author_facet | Farouq, Muhammad Hazim Al Wassie, Aman Kassahun Moslem, Yasmin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_02518 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Bemba Speech Translation: Exploring a Low-Resource African Language Farouq, Muhammad Hazim Al Wassie, Aman Kassahun Moslem, Yasmin Computation and Language Sound Audio and Speech Processing 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. |
| title | Bemba Speech Translation: Exploring a Low-Resource African Language |
| topic | Computation and Language Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2505.02518 |