@inproceedings{attanasio-etal-2025-instituto,
    title = "Instituto de Telecomunica{\c{c}}{\~o}es at {IWSLT} 2025: Aligning Small-Scale Speech and Language Models for Speech-to-Text Learning",
    author = "Attanasio, Giuseppe  and
      Sannigrahi, Sonal  and
      Peters, Ben  and
      Filipe Torres Martins, Andr{\'e}",
    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-1.36/",
    pages = "347--353",
    ISBN = "979-8-89176-272-5",
    abstract = "This paper presents Instituto de Telecomunica{\c{c}}{\~o}es{'}s submission to the IWSLT 2025 Shared Task on Instruction Following Speech Processing. We submit results for the Short Track, i.e., speech recognition, translation, and spoken question answering. Our model is a unified speech-to-text model that integrates a pretrained continuous speech encoder and text decoder through a first phase of modality alignment and a second phase of instruction fine-tuning. Crucially, we focus on using small-scale language model backbones ({\ensuremath{<}} 2B) and restrict to high-quality, CC-BY data along with synthetic data generation to supplement existing resources."
}