@inproceedings{sarkar-etal-2025-effectively,
    title = "Effectively combining Phi-4 and {NLLB} for Spoken Language Translation: {SPRING} Lab {IITM}{'}s submission to Low Resource Multilingual {I}ndic Track",
    author = "Sarkar, Sankalpa  and
      Kashyap, Samriddhi  and
      Joglekar, Advait  and
      Umesh, Srinivasan",
    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-1.42/",
    pages = "399--404",
    ISBN = "979-8-89176-272-5",
    abstract = "This paper presents the methodologies implemented for Spoken Language Translation for the language pairs Hindi-English, Bengali-English and Tamil-English for the Low Resource Multilingual Indic Track of The International Conference on Spoken Language Translation (IWSLT) for 2025. We adopt a cascaded approach and use a fine-tuned Phi-4 multimodal instruct model for Automatic Speech Recognition(ASR) and a fine-tuned NLLB model for Machine Translation(MT)."
}