@inproceedings{djanibekov-aldarmaki-2025-sparqle,
    title = "{S}par{QL}e: Speech Queries to Text Translation Through {LLM}s",
    author = "Djanibekov, Amirbek  and
      Aldarmaki, Hanan",
    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-1.6/",
    pages = "76--83",
    ISBN = "979-8-89176-272-5",
    abstract = "With the growing influence of Large Language Models (LLMs), there is increasing interest in integrating speech representations with them to enable more seamless multi-modal processing and speech understanding. This study introduces a novel approach that combines self-supervised speech representations with instruction-tuned LLMs for speech-to-text translation. The proposed approach leverages a modality adapter to align extracted speech features with instruction-tuned LLMs using English speech data. Our experiments demonstrate that this method effectively preserves the semantic content of the input speech and serves as an effective bridge between self-supervised speech models and instruction-tuned LLMs, offering a promising approach for various speech understanding applications."
}