@inproceedings{basilwango-etal-2026-enhancing,
title = "Enhancing Automatic Speech Recognition Models for Maternal and Reproductive Health: Fine-Tuning and Real-World Evaluation in {W}olof",
author = "Basilwango, Ertony and
Beux, Yann Le and
Ankeli, Oche David and
Berdys, Pierre Herve",
editor = "Chimoto, Everlyn Asiko and
Lignos, Constantine and
Muhammad, Shamsuddeen and
Abdulmumin, Idris and
Siro, Clemencia and
Adelani, David Ifeoluwa",
booktitle = "Proceedings of the 7th Workshop on {A}frican Natural Language Processing ({A}frica{NLP} 2026)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.africanlp-main.27/",
pages = "256--263",
ISBN = "979-8-89176-364-7",
abstract = "Automatic Speech Recognition (ASR) systems perform well for high-resource languages, but most African languages, including Wolof, remain underrepresented, particularly in maternal and reproductive healthcare. This work proposes a domain-specific approach to improving Wolof ASR under low-resource conditions, addressing limited annotated data, orthographic variability, and code-switching. We curated a dataset of 750 validated Wolof utterances covering 250 maternal health keywords and applied data augmentation to increase acoustic diversity. Pretrained models, including wav2vec{~}2.0 and Whisper, were benchmarked to select candidates for fine-tuning. Using parameter-efficient Low-Rank Adaptation (LoRA), a Whisper model was adapted to the maternal health domain. Evaluation using Word Error Rate (WER), Character Error Rate (CER), and Keyword Error Rate (KER), which measures medically critical term transcription accuracy, shows substantial gains, reducing WER from 46.5{\%} to 23.2{\%} and KER from 17{\%} to 11{\%}. Community-based evaluation on 1,340 real-world utterances reveals a moderate degradation, with WER increasing by 35{\%}. These results demonstrate that lightweight domain adaptation with small, high-quality data can significantly improve ASR for low-resource healthcare applications.This work introduces one of the first Wolof ASR datasets for healthcare and presents a practical framework for developing reliable speech recognition tools in underrepresented languages, improving access to healthcare information and services."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="basilwango-etal-2026-enhancing">
<titleInfo>
<title>Enhancing Automatic Speech Recognition Models for Maternal and Reproductive Health: Fine-Tuning and Real-World Evaluation in Wolof</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ertony</namePart>
<namePart type="family">Basilwango</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yann</namePart>
<namePart type="given">Le</namePart>
<namePart type="family">Beux</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oche</namePart>
<namePart type="given">David</namePart>
<namePart type="family">Ankeli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="given">Herve</namePart>
<namePart type="family">Berdys</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 7th Workshop on African Natural Language Processing (AfricaNLP 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Everlyn</namePart>
<namePart type="given">Asiko</namePart>
<namePart type="family">Chimoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Constantine</namePart>
<namePart type="family">Lignos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shamsuddeen</namePart>
<namePart type="family">Muhammad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Idris</namePart>
<namePart type="family">Abdulmumin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Clemencia</namePart>
<namePart type="family">Siro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Ifeoluwa</namePart>
<namePart type="family">Adelani</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">979-8-89176-364-7</identifier>
</relatedItem>
<abstract>Automatic Speech Recognition (ASR) systems perform well for high-resource languages, but most African languages, including Wolof, remain underrepresented, particularly in maternal and reproductive healthcare. This work proposes a domain-specific approach to improving Wolof ASR under low-resource conditions, addressing limited annotated data, orthographic variability, and code-switching. We curated a dataset of 750 validated Wolof utterances covering 250 maternal health keywords and applied data augmentation to increase acoustic diversity. Pretrained models, including wav2vec 2.0 and Whisper, were benchmarked to select candidates for fine-tuning. Using parameter-efficient Low-Rank Adaptation (LoRA), a Whisper model was adapted to the maternal health domain. Evaluation using Word Error Rate (WER), Character Error Rate (CER), and Keyword Error Rate (KER), which measures medically critical term transcription accuracy, shows substantial gains, reducing WER from 46.5% to 23.2% and KER from 17% to 11%. Community-based evaluation on 1,340 real-world utterances reveals a moderate degradation, with WER increasing by 35%. These results demonstrate that lightweight domain adaptation with small, high-quality data can significantly improve ASR for low-resource healthcare applications.This work introduces one of the first Wolof ASR datasets for healthcare and presents a practical framework for developing reliable speech recognition tools in underrepresented languages, improving access to healthcare information and services.</abstract>
<identifier type="citekey">basilwango-etal-2026-enhancing</identifier>
<location>
<url>https://aclanthology.org/2026.africanlp-main.27/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>256</start>
<end>263</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Automatic Speech Recognition Models for Maternal and Reproductive Health: Fine-Tuning and Real-World Evaluation in Wolof
%A Basilwango, Ertony
%A Beux, Yann Le
%A Ankeli, Oche David
%A Berdys, Pierre Herve
%Y Chimoto, Everlyn Asiko
%Y Lignos, Constantine
%Y Muhammad, Shamsuddeen
%Y Abdulmumin, Idris
%Y Siro, Clemencia
%Y Adelani, David Ifeoluwa
%S Proceedings of the 7th Workshop on African Natural Language Processing (AfricaNLP 2026)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-364-7
%F basilwango-etal-2026-enhancing
%X Automatic Speech Recognition (ASR) systems perform well for high-resource languages, but most African languages, including Wolof, remain underrepresented, particularly in maternal and reproductive healthcare. This work proposes a domain-specific approach to improving Wolof ASR under low-resource conditions, addressing limited annotated data, orthographic variability, and code-switching. We curated a dataset of 750 validated Wolof utterances covering 250 maternal health keywords and applied data augmentation to increase acoustic diversity. Pretrained models, including wav2vec 2.0 and Whisper, were benchmarked to select candidates for fine-tuning. Using parameter-efficient Low-Rank Adaptation (LoRA), a Whisper model was adapted to the maternal health domain. Evaluation using Word Error Rate (WER), Character Error Rate (CER), and Keyword Error Rate (KER), which measures medically critical term transcription accuracy, shows substantial gains, reducing WER from 46.5% to 23.2% and KER from 17% to 11%. Community-based evaluation on 1,340 real-world utterances reveals a moderate degradation, with WER increasing by 35%. These results demonstrate that lightweight domain adaptation with small, high-quality data can significantly improve ASR for low-resource healthcare applications.This work introduces one of the first Wolof ASR datasets for healthcare and presents a practical framework for developing reliable speech recognition tools in underrepresented languages, improving access to healthcare information and services.
%U https://aclanthology.org/2026.africanlp-main.27/
%P 256-263
Markdown (Informal)
[Enhancing Automatic Speech Recognition Models for Maternal and Reproductive Health: Fine-Tuning and Real-World Evaluation in Wolof](https://aclanthology.org/2026.africanlp-main.27/) (Basilwango et al., AfricaNLP 2026)
ACL