@inproceedings{gupta-etal-2024-parameter,
    title = "Parameter-efficient Adaptation of Multilingual Multimodal Models for Low-resource {ASR}",
    author = "Gupta, Abhishek  and
      Parulekar, Amruta  and
      Chattopadhyay, Sameep  and
      Jyothi, Preethi",
    editor = {S{\"a}lev{\"a}, Jonne  and
      Owodunni, Abraham},
    booktitle = "Proceedings of the Fourth Workshop on Multilingual Representation Learning (MRL 2024)",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.mrl-1.13/",
    doi = "10.18653/v1/2024.mrl-1.13",
    pages = "175--185",
    abstract = "Automatic speech recognition (ASR) for low-resource languages remains a challenge due to the scarcity of labeled training data. Parameter-efficient fine-tuning and text-only adaptation are two popular methods that have been used to address such low-resource settings. In this work, we investigate how these techniques can be effectively combined using a multilingual multimodal model like SeamlessM4T. Multimodal models are able to leverage unlabeled text via text-only adaptation with further parameter-efficient ASR fine-tuning, thus boosting ASR performance. We also show cross-lingual transfer from a high-resource language, achieving up to a relative 17{\%} WER reduction over baseline in an extremely low-resource setting without any labeled speech."
}