@inproceedings{ouedraogo-etal-2026-contributing,
title = "Contributing to Speech-to-Speech Translation for {A}frican Low-Resource Languages : Study of {F}rench-Moor{\'e} Pair",
author = "Ouedraogo, Fay{\c{c}}al S. A. and
Ouattara, Maimouna and
Kafando, Rodrique and
Kabore, Abdoul Kader and
Sabane, Aminata and
Bissyand{\'e}, Tegawend{\'e} F.",
editor = "Hettiarachchi, Hansi and
Ranasinghe, Tharindu and
Plum, Alistair and
Rayson, Paul and
Mitkov, Ruslan and
Gaber, Mohamed and
Premasiri, Damith and
Tan, Fiona Anting and
Uyangodage, Lasitha",
booktitle = "Proceedings of the Second Workshop on Language Models for Low-Resource Languages ({L}o{R}es{LM} 2026)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.loreslm-1.54/",
pages = "623--629",
ISBN = "979-8-89176-377-7",
abstract = "Most of African low-resource languages are primarily spoken rather than written and lack large, standardized textual resources. In many communities, low literacy rates and limited access to formal education mean that text-based translation technologies alone are insufficient for effective communication. As a result, speech-to-speech translation systems play a crucial role by enabling direct and natural interaction across languages without requiring reading or writing skills. Such systems are essential for improving access to information, public services, healthcare, and education. The goal of our work is to build powerful transcription and speech synthesis models for Moor{\'e} language. Then, these models have been used to build a cascaded voice translation system between French and Moor{\'e}, since we already got a French-Moor{\'e} machine translation model. We collected Moor{\'e} audio-text pairs, reaching a total audio duration of 150 hours. Then, We fine-tuned Orpheus-3B and XTTS-v2 for speech synthesis and Wav2Vec-Bert-2.0 for transcription task. After fine-tuning and evaluation by 36 Moor{\'e} native speakers, XTTS-v2 achieved a MOS of 4.36 out of 5 compared to 3.47 out of 5 for Orpheus-3B. The UTMOS evaluation resulted in 3.47 out of 5 for XTTS-v2 and 2.80 out of 5 for Orpheus-3B. The A/B tests revealed that the evaluators preferred XTTS-v2 Moor{\'e} audios in 77.8{\%} of cases compared to 22.2{\%} for Orpheus-3B. After fine-tuning on Moor{\'e}, Wav2Vec-Bert-2.0 achieved a WER of 4.24{\%} and a CER of 1.11{\%}. Using these models, we successfully implemented a French-Moor{\'e} Speech-to-Speech Translation system."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ouedraogo-etal-2026-contributing">
<titleInfo>
<title>Contributing to Speech-to-Speech Translation for African Low-Resource Languages : Study of French-Mooré Pair</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fayçal</namePart>
<namePart type="given">S</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Ouedraogo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maimouna</namePart>
<namePart type="family">Ouattara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rodrique</namePart>
<namePart type="family">Kafando</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdoul</namePart>
<namePart type="given">Kader</namePart>
<namePart type="family">Kabore</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aminata</namePart>
<namePart type="family">Sabane</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tegawendé</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Bissyandé</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Language Models for Low-Resource Languages (LoResLM 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hansi</namePart>
<namePart type="family">Hettiarachchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alistair</namePart>
<namePart type="family">Plum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Gaber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damith</namePart>
<namePart type="family">Premasiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fiona</namePart>
<namePart type="given">Anting</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lasitha</namePart>
<namePart type="family">Uyangodage</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-377-7</identifier>
</relatedItem>
<abstract>Most of African low-resource languages are primarily spoken rather than written and lack large, standardized textual resources. In many communities, low literacy rates and limited access to formal education mean that text-based translation technologies alone are insufficient for effective communication. As a result, speech-to-speech translation systems play a crucial role by enabling direct and natural interaction across languages without requiring reading or writing skills. Such systems are essential for improving access to information, public services, healthcare, and education. The goal of our work is to build powerful transcription and speech synthesis models for Mooré language. Then, these models have been used to build a cascaded voice translation system between French and Mooré, since we already got a French-Mooré machine translation model. We collected Mooré audio-text pairs, reaching a total audio duration of 150 hours. Then, We fine-tuned Orpheus-3B and XTTS-v2 for speech synthesis and Wav2Vec-Bert-2.0 for transcription task. After fine-tuning and evaluation by 36 Mooré native speakers, XTTS-v2 achieved a MOS of 4.36 out of 5 compared to 3.47 out of 5 for Orpheus-3B. The UTMOS evaluation resulted in 3.47 out of 5 for XTTS-v2 and 2.80 out of 5 for Orpheus-3B. The A/B tests revealed that the evaluators preferred XTTS-v2 Mooré audios in 77.8% of cases compared to 22.2% for Orpheus-3B. After fine-tuning on Mooré, Wav2Vec-Bert-2.0 achieved a WER of 4.24% and a CER of 1.11%. Using these models, we successfully implemented a French-Mooré Speech-to-Speech Translation system.</abstract>
<identifier type="citekey">ouedraogo-etal-2026-contributing</identifier>
<location>
<url>https://aclanthology.org/2026.loreslm-1.54/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>623</start>
<end>629</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Contributing to Speech-to-Speech Translation for African Low-Resource Languages : Study of French-Mooré Pair
%A Ouedraogo, Fayçal S. A.
%A Ouattara, Maimouna
%A Kafando, Rodrique
%A Kabore, Abdoul Kader
%A Sabane, Aminata
%A Bissyandé, Tegawendé F.
%Y Hettiarachchi, Hansi
%Y Ranasinghe, Tharindu
%Y Plum, Alistair
%Y Rayson, Paul
%Y Mitkov, Ruslan
%Y Gaber, Mohamed
%Y Premasiri, Damith
%Y Tan, Fiona Anting
%Y Uyangodage, Lasitha
%S Proceedings of the Second Workshop on Language Models for Low-Resource Languages (LoResLM 2026)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-377-7
%F ouedraogo-etal-2026-contributing
%X Most of African low-resource languages are primarily spoken rather than written and lack large, standardized textual resources. In many communities, low literacy rates and limited access to formal education mean that text-based translation technologies alone are insufficient for effective communication. As a result, speech-to-speech translation systems play a crucial role by enabling direct and natural interaction across languages without requiring reading or writing skills. Such systems are essential for improving access to information, public services, healthcare, and education. The goal of our work is to build powerful transcription and speech synthesis models for Mooré language. Then, these models have been used to build a cascaded voice translation system between French and Mooré, since we already got a French-Mooré machine translation model. We collected Mooré audio-text pairs, reaching a total audio duration of 150 hours. Then, We fine-tuned Orpheus-3B and XTTS-v2 for speech synthesis and Wav2Vec-Bert-2.0 for transcription task. After fine-tuning and evaluation by 36 Mooré native speakers, XTTS-v2 achieved a MOS of 4.36 out of 5 compared to 3.47 out of 5 for Orpheus-3B. The UTMOS evaluation resulted in 3.47 out of 5 for XTTS-v2 and 2.80 out of 5 for Orpheus-3B. The A/B tests revealed that the evaluators preferred XTTS-v2 Mooré audios in 77.8% of cases compared to 22.2% for Orpheus-3B. After fine-tuning on Mooré, Wav2Vec-Bert-2.0 achieved a WER of 4.24% and a CER of 1.11%. Using these models, we successfully implemented a French-Mooré Speech-to-Speech Translation system.
%U https://aclanthology.org/2026.loreslm-1.54/
%P 623-629
Markdown (Informal)
[Contributing to Speech-to-Speech Translation for African Low-Resource Languages : Study of French-Mooré Pair](https://aclanthology.org/2026.loreslm-1.54/) (Ouedraogo et al., LoResLM 2026)
ACL