@inproceedings{menendez-gomez-2025-text,
    title = "Text-to-speech system for low-resource languages: A case study in {S}hipibo-Konibo (a {P}anoan language from {P}eru)",
    author = "Menendez, Daniel  and
      Gomez, Hector",
    editor = "Mager, Manuel  and
      Ebrahimi, Abteen  and
      Pugh, Robert  and
      Rijhwani, Shruti  and
      Von Der Wense, Katharina  and
      Chiruzzo, Luis  and
      Coto-Solano, Rolando  and
      Oncevay, Arturo",
    booktitle = "Proceedings of the Fifth Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP)",
    month = may,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.americasnlp-1.1/",
    doi = "10.18653/v1/2025.americasnlp-1.1",
    pages = "1--7",
    ISBN = "979-8-89176-236-7",
    abstract = "This paper presents the design and development of a Text-to-Speech (TTS) model for Shipibo-Konibo, a low-resource indigenous language spoken mainly in the Peruvian Amazon. Despite the challenge posed by the scarcity of data, the model was trained with over 4 hours of recordings and 3,025 meticulously collected written sentences. The tests results demon strated an intelligibility rate (IR) exceeding 88{\%} and a mean opinion score (MOS) of 4.01, confirming the quality of the audio generated by the model, which comprises the Tacotron 2 spectrogram predictor and the HiFi-GAN vocoder. Furthermore, the potential of this model to be trained in other indigenous languages spoken in Peru is highlighted, opening a promising avenue for the documentation and revitalization of these languages."
}