@inproceedings{wang-etal-2025-developing,
    title = "Developing multilingual speech synthesis system for {O}jibwe, Mi{'}kmaq, and Maliseet",
    author = "Wang, Shenran  and
      Yang, Changbing  and
      Parkhill, Michael l  and
      Quinn, Chad  and
      Hammerly, Christopher  and
      Zhu, Jian",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/moar-dois/2025.naacl-short.69/",
    doi = "10.18653/v1/2025.naacl-short.69",
    pages = "817--826",
    ISBN = "979-8-89176-190-2",
    abstract = "We present lightweight flow matching multilingual text-to-speech (TTS) systems for Ojibwe, Mi{'}kmaq, and Maliseet, three Indigenous languages in North America. Our results show that training a multilingual TTS model on three typologically similar languages can improve the performance over monolingual models, especially when data are scarce. Attention-free architectures are highly competitive with self-attention architecture with higher memory efficiency. Our research provides technical development to language revitalization for low-resource languages but also highlights the cultural gap in human evaluation protocols, calling for a more community-centered approach to human evaluation."
}