@inproceedings{palomino-2026-selected,
    title = "Selected-Layer Codec Compression for Compact Speech Translation Models: An {IWSLT} 2026 {E}nglish-to-{C}hinese Submission",
    author = "Palomino, Alonso",
    editor = "Salesky, Elizabeth  and
      Anastasopoulos, Antonios  and
      Negri, Matteo  and
      Federico, Marcello",
    booktitle = "Proceedings of the 23rd International Conference on Spoken Language Translation ({IWSLT} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, USA (in-person and online)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/bulk-corrections-2026-07-02/2026.iwslt-1.4/",
    doi = "10.18653/v1/2026.iwslt-1.4",
    pages = "40--46",
    ISBN = "979-8-89176-411-8",
    abstract = "This paper describes a selected-layer codec compression approach submitted to the IWSLT 2026 Model Compression Shared Task for constrained English-to-Chinese speech translation. The approach is compared against standard quantization, global codec compression, and a pruning-plus-codec variant. The results indicate that translation quality after compression depends strongly on where compression is applied. In these experiments, selected-layer compression preserves translation quality better than uniform global compression, with one variant achieving the highest COMET score among compressed systems and another providing the strongest overall quality-compression trade-off among the custom codec methods. These results suggest that simple layer-aware post-hoc compression is a viable approach for model compression in constrained English-to-Chinese speech translation."
}