@inproceedings{babatunde-etal-2025-beyond,
    title = "Beyond Monolingual Limits: Fine-Tuning Monolingual {ASR} for {Y}oruba-{E}nglish Code-Switching",
    author = "Babatunde, Oreoluwa Boluwatife  and
      Olufemi, Victor Tolulope  and
      Bolarinwa, Emmanuel  and
      Moshood, Kausar Yetunde  and
      Emezue, Chris Chinenye",
    editor = "Winata, Genta Indra  and
      Kar, Sudipta  and
      Zhukova, Marina  and
      Solorio, Thamar  and
      Ai, Xi  and
      Hamed, Injy  and
      Ihsani, Mahardika Krisna Krisna  and
      Wijaya, Derry Tanti  and
      Kuwanto, Garry",
    booktitle = "Proceedings of the 7th Workshop on Computational Approaches to Linguistic Code-Switching",
    month = may,
    year = "2025",
    address = "Albuquerque, New Mexico, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Ingest-2025-COMPUTEL/2025.calcs-1.3/",
    pages = "18--25",
    ISBN = "979-8-89176-053-0",
    abstract = "Code-switching (CS) presents a significant challenge for Automatic Speech Recognition (ASR) systems, particularly in low-resource settings. While multilingual ASR models like OpenAI Whisper Large v3 are designed to handle multiple languages, their high computational demands make them less practical for real-world deployment in resource-constrained environments. In this study, we investigate the effectiveness of fine-tuning both monolingual and multilingual ASR models for Yoruba-English CS speech. Our results show that unadapted monolingual ASR models outperform Whisper Large v3 in a zero-shot setting on CS speech. Fine-tuning significantly reduces WER for both monolingual and multilingual models, with monolingual models achieving over a 20{\%} WER reduction on CS and Yoruba speech while maintaining lower computational costs. However, we observe a trade-off, as fine-tuning leads to some degradation in English recognition, particularly for multilingual models. Our findings highlight that while multilingual models benefit from fine-tuning, monolingual models provide a computationally efficient and competitive alternative for CS-ASR, making them a viable choice for resource-constrained environments."
}