@inproceedings{jon-etal-2025-aladan,
    title = "{ALADAN} at {IWSLT}25 Low-resource {A}rabic Dialectal Speech Translation Task",
    author = "Jon, Josef  and
      Ben Kheder, Waad  and
      Beyer, Andre  and
      Barras, Claude  and
      Gauvain, Jean-Luc",
    editor = "Salesky, Elizabeth  and
      Federico, Marcello  and
      Anastasopoulos, Antonis",
    booktitle = "Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria (in-person and online)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/acl25-workshop-ingestion/2025.iwslt-1.24/",
    pages = "252--259",
    ISBN = "979-8-89176-272-5",
    abstract = "We present our IWSLT 2025 submission for the low-resource track on North Levantine Arabic to English speech translation, building on our IWSLT 2024 efforts. We retain last year{'}s cascade ASR architecture that combines a TDNN-F model and a Zipformer for the ASR step. We upgrade the Zipformer to the Zipformer-Large variant (253 M parameters vs. 66 M) to capture richer acoustic representations. For the MT part, to further alleviate data sparsity, we created a crowd-sourced parallel corpus covering five major Arabic dialects (Tunisian, Levantine, Moroccan, Algerian, Egyptian) curated via rigorous qualification and filtering. We show that using crowd-sourced data is feasible in low-resource scenarios as we observe improved automatic evaluation metrics across all dialects. We also experimented with the dataset under a high-resource scenario, where we had access to a large, high-quality Levantine Arabic corpus from LDC. In this setting, adding the crowd-sourced data does not improve the scores on the official validation set anymore. Our final submission scores 20.0 BLEU on the official test set."
}