@inproceedings{lin-etal-2025-channel,
    title = "A Channel-Aware Anomaly-Guided Data Augmentation Framework for the {FSR}-2025 {H}akka Speech Recognition Challenge",
    author = "Lin, Siang-Ting  and
      Hao, Arthur  and
      Hua, Chiun-Yu  and
      Huang, Kuan-Tang  and
      Chen, Berlin",
    editor = "Chang, Kai-Wei  and
      Lu, Ke-Han  and
      Yang, Chih-Kai  and
      Tam, Zhi-Rui  and
      Chang, Wen-Yu  and
      Wang, Chung-Che",
    booktitle = "Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025)",
    month = nov,
    year = "2025",
    address = "National Taiwan University, Taipei City, Taiwan",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/dashboard/2025.rocling-main.60/",
    pages = "499--503",
    ISBN = "979-8-89176-379-1",
    abstract = "The Formosa Speech Recognition Challenge 2025 (FSR-2025) focuses on Taiwanese Hakka, a low-resource language with limited data diversity and channel coverage. To address this challenge, we propose a channel-aware, data-centric framework that leverages multilingual foundation models to mitigate mismatches between field recordings and training data. Our method integrates unsupervised anomaly detection and channel-conditioned augmentation to enhance data representativeness before ASR fine-tuning, aiming to explore the potential for improving robustness in low-resource Hakka speech recognition."
}