@inproceedings{edet-etal-2026-adapting,
    title = "Adapting Foundational {ASR} Models to {E}fik: An Empirical Study of an Extremely Low-Resource Tonal Language",
    author = "Edet, Offiong Bassey  and
      Duke, Stephen Orok  and
      Umoh, Enoima Essien  and
      Nyong, Benjamin Okon  and
      Nkpanam, Andrew Asuquo",
    editor = "Hosseini-Kivanani, Nina  and
      Brutti, Alessio  and
      Matassoni, Marco  and
      Dowerah, Sandipana  and
      Liga, Davide  and
      Schommer, Christoph",
    booktitle = "Proceedings of Speech Language Models in Low-Resource Settings: Performance, Evaluation, and Bias Analysis ({SPEAKABLE}) @ {LREC} 2026",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/revision-previews/2026.speakable-1.1/",
    doi = "10.63317/3wmtoxexdady",
    pages = "1--7",
    abstract = "Automatic Speech Recognition (ASR) has significantly transformed human-computer-interaction and natural language processing. However, many African spoken languages, including Efik, remain severely underrepresented in ASR research. This paper investigates the adoption of state-of-the-art foundational ASR models such as XLS-R and Whisper through fine-tuning for Efik, a low-resource tonal language and empirically evaluates their performance. We curate a 3-hour Efik speech dataset and conduct a comparative evaluation using standard ASR metrics. We further augmented the XLS-R CTC model with a 3-gram KenLM language model trained on an Efik text corpus. Experimental results show that XLS-R-300M + KenLM achieves a word error rate (WER) of 10.86{\%} and a character error rate (CER) of 3.16{\%}, substantially outperforming both the baseline XLS-R (WER: 29.2{\%}, CER: 6.4{\%}) and Whisper across noisy and multi-speaker conditions. These findings suggest that lightweight CTC models augmented with language model integration offer a more robust and practical approach for extremely low-resource tonal languages than larger sequence-to-sequence models."
}