@inproceedings{ortega-etal-2026-giving,
title = "Giving Voice to the Constitution: Low-Resource Text-to-Speech for {Q}uechua and {S}panish Using a Bilingual Legal Corpus",
author = "Ortega, John E. and
Zevallos, Rodolfo Joel and
Carraro, Fabr{\'i}cio",
editor = "Afli, Haithem and
Bouamor, Houda and
Zaghouani, Wajdi and
Ghannay, Sahar and
Hossain, Shehenaz",
booktitle = "Proceedings of the 3rd Workshop on Natural Language Processing for Political Sciences ({P}olitical{NLP} 2026)",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.politicalnlp-1.7/",
doi = "10.63317/39457jk69sij",
pages = "64--69",
abstract = "We present a unified pipeline for synthesizing high-quality Quechua and Spanish speech for the Peruvian Constitution using three state-of-the-art text-to-speech (TTS) architectures: XTTS v2, F5-TTS, and DiFlow-TTS. Our models are trained on independent Spanish and Quechua speech datasets with heterogeneous sizes and recording conditions, and leverage bilingual and multilingual TTS capabilities to improve synthesis quality in both languages. By exploiting cross-lingual transfer, our framework mitigates data scarcity in Quechua while preserving naturalness in Spanish. We release trained checkpoints, inference code, and synthesized audio for each constitutional article, providing a reusable resource for speech technologies in indigenous and multilingual contexts. This work contributes to the development of inclusive TTS systems for political and legal content in low-resource settings"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ortega-etal-2026-giving">
<titleInfo>
<title>Giving Voice to the Constitution: Low-Resource Text-to-Speech for Quechua and Spanish Using a Bilingual Legal Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Ortega</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rodolfo</namePart>
<namePart type="given">Joel</namePart>
<namePart type="family">Zevallos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabrício</namePart>
<namePart type="family">Carraro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on Natural Language Processing for Political Sciences (PoliticalNLP 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haithem</namePart>
<namePart type="family">Afli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sahar</namePart>
<namePart type="family">Ghannay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shehenaz</namePart>
<namePart type="family">Hossain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a unified pipeline for synthesizing high-quality Quechua and Spanish speech for the Peruvian Constitution using three state-of-the-art text-to-speech (TTS) architectures: XTTS v2, F5-TTS, and DiFlow-TTS. Our models are trained on independent Spanish and Quechua speech datasets with heterogeneous sizes and recording conditions, and leverage bilingual and multilingual TTS capabilities to improve synthesis quality in both languages. By exploiting cross-lingual transfer, our framework mitigates data scarcity in Quechua while preserving naturalness in Spanish. We release trained checkpoints, inference code, and synthesized audio for each constitutional article, providing a reusable resource for speech technologies in indigenous and multilingual contexts. This work contributes to the development of inclusive TTS systems for political and legal content in low-resource settings</abstract>
<identifier type="citekey">ortega-etal-2026-giving</identifier>
<identifier type="doi">10.63317/39457jk69sij</identifier>
<location>
<url>https://aclanthology.org/2026.politicalnlp-1.7/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>64</start>
<end>69</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Giving Voice to the Constitution: Low-Resource Text-to-Speech for Quechua and Spanish Using a Bilingual Legal Corpus
%A Ortega, John E.
%A Zevallos, Rodolfo Joel
%A Carraro, Fabrício
%Y Afli, Haithem
%Y Bouamor, Houda
%Y Zaghouani, Wajdi
%Y Ghannay, Sahar
%Y Hossain, Shehenaz
%S Proceedings of the 3rd Workshop on Natural Language Processing for Political Sciences (PoliticalNLP 2026)
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F ortega-etal-2026-giving
%X We present a unified pipeline for synthesizing high-quality Quechua and Spanish speech for the Peruvian Constitution using three state-of-the-art text-to-speech (TTS) architectures: XTTS v2, F5-TTS, and DiFlow-TTS. Our models are trained on independent Spanish and Quechua speech datasets with heterogeneous sizes and recording conditions, and leverage bilingual and multilingual TTS capabilities to improve synthesis quality in both languages. By exploiting cross-lingual transfer, our framework mitigates data scarcity in Quechua while preserving naturalness in Spanish. We release trained checkpoints, inference code, and synthesized audio for each constitutional article, providing a reusable resource for speech technologies in indigenous and multilingual contexts. This work contributes to the development of inclusive TTS systems for political and legal content in low-resource settings
%R 10.63317/39457jk69sij
%U https://aclanthology.org/2026.politicalnlp-1.7/
%U https://doi.org/10.63317/39457jk69sij
%P 64-69
Markdown (Informal)
[Giving Voice to the Constitution: Low-Resource Text-to-Speech for Quechua and Spanish Using a Bilingual Legal Corpus](https://aclanthology.org/2026.politicalnlp-1.7/) (Ortega et al., PoliticalNLP 2026)
ACL