@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://aclanthology.org/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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="menendez-gomez-2025-text">
<titleInfo>
<title>Text-to-speech system for low-resource languages: A case study in Shipibo-Konibo (a Panoan language from Peru)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Menendez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hector</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Manuel</namePart>
<namePart type="family">Mager</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abteen</namePart>
<namePart type="family">Ebrahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Pugh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shruti</namePart>
<namePart type="family">Rijhwani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katharina</namePart>
<namePart type="family">Von Der Wense</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rolando</namePart>
<namePart type="family">Coto-Solano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arturo</namePart>
<namePart type="family">Oncevay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-236-7</identifier>
</relatedItem>
<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.</abstract>
<identifier type="citekey">menendez-gomez-2025-text</identifier>
<identifier type="doi">10.18653/v1/2025.americasnlp-1.1</identifier>
<location>
<url>https://aclanthology.org/2025.americasnlp-1.1/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>1</start>
<end>7</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Text-to-speech system for low-resource languages: A case study in Shipibo-Konibo (a Panoan language from Peru)
%A Menendez, Daniel
%A Gomez, Hector
%Y Mager, Manuel
%Y Ebrahimi, Abteen
%Y Pugh, Robert
%Y Rijhwani, Shruti
%Y Von Der Wense, Katharina
%Y Chiruzzo, Luis
%Y Coto-Solano, Rolando
%Y Oncevay, Arturo
%S Proceedings of the Fifth Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP)
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-236-7
%F menendez-gomez-2025-text
%X 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.
%R 10.18653/v1/2025.americasnlp-1.1
%U https://aclanthology.org/2025.americasnlp-1.1/
%U https://doi.org/10.18653/v1/2025.americasnlp-1.1
%P 1-7
Markdown (Informal)
[Text-to-speech system for low-resource languages: A case study in Shipibo-Konibo (a Panoan language from Peru)](https://aclanthology.org/2025.americasnlp-1.1/) (Menendez & Gomez, AmericasNLP 2025)
ACL