@inproceedings{bar-etal-2025-swiss,
    title = "{S}wiss {G}erman Speech Translation and the Curse of Multidialectality",
    author = {B{\"a}r, Martin  and
      DeMarco, Andrea  and
      Labaka, Gorka},
    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/landing_page/2025.iwslt-1.15/",
    pages = "165--179",
    ISBN = "979-8-89176-272-5",
    abstract = "In many languages, non-standardized varieties make the development of NLP models challenging. This paper explores various fine-tuning techniques and data setups for training Swiss German to Standard German speech-to-text translation models. While fine-tuning on all available Swiss German data yields the best results, ASR pre-training lowers performance by 1.48 BLEU points, and jointly training on Swiss and Standard German data reduces it by 2.29 BLEU. Our dialect transfer experiments suggest that an equivalent of the Curse of Multilinguality (Conneau et al., 2020) exists in dialectal speech processing, as training on multiple dialects jointly tends to decrease single-dialect performance. However, introducing small amounts of dialectal variability can improve the performance for low-resource dialects."
}