@inproceedings{singh-etal-2026-iiit,
    title = "{IIIT}-{BGP} {IWSLT} 2026 Systems for Low-resource {ST}",
    author = "Singh, Kaustuk Pratap  and
      ., Dipanshu  and
      Singh, Vedant  and
      Rishu, Kumar",
    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/corrections-2026-06/2026.iwslt-1.31/",
    doi = "10.18653/v1/2026.iwslt-1.31",
    pages = "272--283",
    ISBN = "979-8-89176-411-8",
    abstract = "We present low-resource Bhojpuri-Hindi speech translation systems for the IWSLT 2026 shared task, covering both end-to-end and cascaded settings. Our end-to-end model connects a Bhojpuri-finetuned Wav2Vec2 encoder to a pretrained NLLB-200 decoder via a lightweight interconnection adapter that combines learnable layer aggregation, CNN-based temporal compression, and Transformer refinement, with optional LoRA-based decoder adaptation. For our cascaded system, we finetune Whisper for Bhojpuri ASR and NLLB-200 for Hindi MT, and further apply QE Fusion with COMET-Kiwi to improve translation selection from beam candidates."
}