@inproceedings{keita-etal-2026-salan,
title = "{SALAN}: A Massive {ASR} Dataset for the Languages of {N}iger",
author = "KEITA, Mamadou K and
Homan, Christopher and
Prud{'}hommeaux, Emily and
SAKO, Abdoulaye and
Diallo, Seydou",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.460/",
doi = "10.63317/2ibxrv25uwgo",
pages = "5821--5827",
abstract = "We introduce SALAN, a large-scale speech dataset covering eight of the major indigenous languages of Niger: Zarma, Hausa, Buduma, Gourmantchema, Tubu, Tamasheq, Fulfulde, and Kanuri. The final dataset exceeds 2,000 hours of audio, largely sourced from radio broadcasts and community recordings. We transcribed portions of the audio using the MMS model and conducted manual verification for 110 hours across Zarma and Hausa. We then used active learning to expand annotation to an additional 5 hours of high-uncertainty Zarma segments. To evaluate SALAN{'}s utility for ASR, We fine-tuned both Wav2vec2 XLS-R and Whisper on Zarma subsets and carried out additional pre-training with multilingual unlabeled data. Our best model achieved a word error rate of 25.3{\%} and a character error rate of 6.2{\%}. SALAN and the trained models will be made publicly available for use by researchers and speakers, with the potential to impact over 20 million individuals in Niger and neighboring countries."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="keita-etal-2026-salan">
<titleInfo>
<title>SALAN: A Massive ASR Dataset for the Languages of Niger</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mamadou</namePart>
<namePart type="given">K</namePart>
<namePart type="family">KEITA</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Homan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Prud’hommeaux</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdoulaye</namePart>
<namePart type="family">SAKO</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seydou</namePart>
<namePart type="family">Diallo</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 Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce SALAN, a large-scale speech dataset covering eight of the major indigenous languages of Niger: Zarma, Hausa, Buduma, Gourmantchema, Tubu, Tamasheq, Fulfulde, and Kanuri. The final dataset exceeds 2,000 hours of audio, largely sourced from radio broadcasts and community recordings. We transcribed portions of the audio using the MMS model and conducted manual verification for 110 hours across Zarma and Hausa. We then used active learning to expand annotation to an additional 5 hours of high-uncertainty Zarma segments. To evaluate SALAN’s utility for ASR, We fine-tuned both Wav2vec2 XLS-R and Whisper on Zarma subsets and carried out additional pre-training with multilingual unlabeled data. Our best model achieved a word error rate of 25.3% and a character error rate of 6.2%. SALAN and the trained models will be made publicly available for use by researchers and speakers, with the potential to impact over 20 million individuals in Niger and neighboring countries.</abstract>
<identifier type="citekey">keita-etal-2026-salan</identifier>
<identifier type="doi">10.63317/2ibxrv25uwgo</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.460/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>5821</start>
<end>5827</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SALAN: A Massive ASR Dataset for the Languages of Niger
%A KEITA, Mamadou K.
%A Homan, Christopher
%A Prud’hommeaux, Emily
%A SAKO, Abdoulaye
%A Diallo, Seydou
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F keita-etal-2026-salan
%X We introduce SALAN, a large-scale speech dataset covering eight of the major indigenous languages of Niger: Zarma, Hausa, Buduma, Gourmantchema, Tubu, Tamasheq, Fulfulde, and Kanuri. The final dataset exceeds 2,000 hours of audio, largely sourced from radio broadcasts and community recordings. We transcribed portions of the audio using the MMS model and conducted manual verification for 110 hours across Zarma and Hausa. We then used active learning to expand annotation to an additional 5 hours of high-uncertainty Zarma segments. To evaluate SALAN’s utility for ASR, We fine-tuned both Wav2vec2 XLS-R and Whisper on Zarma subsets and carried out additional pre-training with multilingual unlabeled data. Our best model achieved a word error rate of 25.3% and a character error rate of 6.2%. SALAN and the trained models will be made publicly available for use by researchers and speakers, with the potential to impact over 20 million individuals in Niger and neighboring countries.
%R 10.63317/2ibxrv25uwgo
%U https://aclanthology.org/2026.lrec-1.460/
%U https://doi.org/10.63317/2ibxrv25uwgo
%P 5821-5827
Markdown (Informal)
[SALAN: A Massive ASR Dataset for the Languages of Niger](https://aclanthology.org/2026.lrec-1.460/) (KEITA et al., LREC 2026)
ACL
- Mamadou K KEITA, Christopher Homan, Emily Prud’hommeaux, Abdoulaye SAKO, and Seydou Diallo. 2026. SALAN: A Massive ASR Dataset for the Languages of Niger. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 5821–5827, Palma de Mallorca, Spain. ELRA Language Resource Association.