@inproceedings{samin-etal-2025-investigating,
    title = "Investigating Adapters for Parameter-efficient Low-resource Automatic Speech Recognition",
    author = "Samin, Ahnaf Mozib  and
      Nayak, Shekhar  and
      De Marco, Andrea  and
      Borg, Claudia",
    editor = "Adlakha, Vaibhav  and
      Chronopoulou, Alexandra  and
      Li, Xiang Lorraine  and
      Majumder, Bodhisattwa Prasad  and
      Shi, Freda  and
      Vernikos, Giorgos",
    booktitle = "Proceedings of the 10th Workshop on Representation Learning for NLP (RepL4NLP-2025)",
    month = may,
    year = "2025",
    address = "Albuquerque, NM",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/moar-dois/2025.repl4nlp-1.8/",
    doi = "10.18653/v1/2025.repl4nlp-1.8",
    pages = "100--107",
    ISBN = "979-8-89176-245-9",
    abstract = "Recent years have witnessed the adoption of parameter-efficient adapters in pre-trained language models for natural language processing. Yet, their application in speech processing remains less studied. In this work, we explore the adapters for low-resource speech recognition, introducing a novel technique - ConvAdapt into pre-trained speech models. We investigate various aspects such as data requirements, transfer learning within adapters, and scaling of feed-forward layers in adapters. Our findings reveal that bottleneck adapters offer competitiveness with full fine-tuning with at least 10 hours of data, but they are not as effective in few-shot learning scenarios. Notably, ConvAdapt demonstrates improved performance in such cases. In addition, transfer learning in adapters shows promise, necessitating research in related languages. Furthermore, employing larger speech models for adapter-tuning surpasses fine-tuning with ample data, potentially due to reduced overfitting than fine-tuning."
}