@inproceedings{sood-etal-2025-speech,
    title = "Speech-to-Speech Machine Translation for Dialectal Variations of {H}indi",
    author = "Sood, Sanmay  and
      Rajput, Siddharth  and
      Akhtar, Md Shad",
    editor = "Nakazawa, Toshiaki  and
      Goto, Isao",
    booktitle = "Proceedings of the Twelfth Workshop on Asian Translation (WAT 2025)",
    month = dec,
    year = "2025",
    address = "Mumbai, India",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-ijcnlp-aacl/2025.wat-1.5/",
    pages = "54--65",
    ISBN = "979-8-89176-309-8",
    abstract = "Hindi has many dialects and they are vital to India{'}s cultural and linguistics heritage. However, many of them have been largely overlooked in modern language technological advancements, primarily due to lack proper resources. In this study, we explore speech-to-speech machine translation (S2ST) for four Hindi dialects, i.e., \textit{Awadhi}, \textit{Bhojpuri}, \textit{Braj Bhasha}, and \textit{Magahi}. We adopt a cascaded S2ST pipeline comprising of three stages: Automatic Speech Recognition (ASR), Machine Translation (MT), and Text-to-Speech (TTS). We evaluate many recent large language models (LLMs) for dialect-to-Hindi and dialect-to-English translations in zero-shot, few-shot, and chain-of-thought setups. Our comparative analysis offers insights into the current capabilities and limitations of LLM-based approaches for low-resource dialectal S2ST in Indian context."
}