@inproceedings{mgonzo-etal-2026-learning,
title = "Learning from Scarcity: Building and Benchmarking Speech Technology for {S}ukuma.",
author = "Mgonzo, Macton and
Oketch, Kezia and
Etori, Naome A and
Mang'eni, Winnie and
Nyaki, Elizabeth Fabian and
Mollel, Michael Samwel",
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-1.25/",
pages = "288--296",
ISBN = "979-8-89176-377-7",
abstract = "Automatic Speech Recognition (ASR) systems are gaining increasing attention in both academia and industry. Despite having remarkable performance in high-resource languages, their efficacy is less pronounced in low-resource settings. We present the first ASR system for Sukuma, one of the most severely under-resourced Tanzanian languages, and provide an open-source Sukuma speech corpus comprising 7.47 hours of carefully transcribed audio. The data, sourced primarily from Bible readings, was rigorously annotated to ensure phonetic and orthographic consistency, making it the most linguistically reliable resource currently available for the Sukuma language. To establish baselines, we train lightweight ASR and Text-to-Speech (TTS) models that demonstrate the feasibility of building end-to-end speech systems for this underrepresented language. This work addresses the challenges of developing language and communication tools for speakers of less-represented languages, particularly the scarcity of representative datasets and benchmarks, and highlights future research directions for linguistically challenging languages, such as Sukuma. We make our data and code publicly available to facilitate reproducibility and further research."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mgonzo-etal-2026-learning">
<titleInfo>
<title>Learning from Scarcity: Building and Benchmarking Speech Technology for Sukuma.</title>
</titleInfo>
<name type="personal">
<namePart type="given">Macton</namePart>
<namePart type="family">Mgonzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kezia</namePart>
<namePart type="family">Oketch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naome</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Etori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Winnie</namePart>
<namePart type="family">Mang’eni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="given">Fabian</namePart>
<namePart type="family">Nyaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="given">Samwel</namePart>
<namePart type="family">Mollel</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>Automatic Speech Recognition (ASR) systems are gaining increasing attention in both academia and industry. Despite having remarkable performance in high-resource languages, their efficacy is less pronounced in low-resource settings. We present the first ASR system for Sukuma, one of the most severely under-resourced Tanzanian languages, and provide an open-source Sukuma speech corpus comprising 7.47 hours of carefully transcribed audio. The data, sourced primarily from Bible readings, was rigorously annotated to ensure phonetic and orthographic consistency, making it the most linguistically reliable resource currently available for the Sukuma language. To establish baselines, we train lightweight ASR and Text-to-Speech (TTS) models that demonstrate the feasibility of building end-to-end speech systems for this underrepresented language. This work addresses the challenges of developing language and communication tools for speakers of less-represented languages, particularly the scarcity of representative datasets and benchmarks, and highlights future research directions for linguistically challenging languages, such as Sukuma. We make our data and code publicly available to facilitate reproducibility and further research.</abstract>
<identifier type="citekey">mgonzo-etal-2026-learning</identifier>
<location>
<url>https://aclanthology.org/2026.loreslm-1.25/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>288</start>
<end>296</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning from Scarcity: Building and Benchmarking Speech Technology for Sukuma.
%A Mgonzo, Macton
%A Oketch, Kezia
%A Etori, Naome A.
%A Mang’eni, Winnie
%A Nyaki, Elizabeth Fabian
%A Mollel, Michael Samwel
%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 mgonzo-etal-2026-learning
%X Automatic Speech Recognition (ASR) systems are gaining increasing attention in both academia and industry. Despite having remarkable performance in high-resource languages, their efficacy is less pronounced in low-resource settings. We present the first ASR system for Sukuma, one of the most severely under-resourced Tanzanian languages, and provide an open-source Sukuma speech corpus comprising 7.47 hours of carefully transcribed audio. The data, sourced primarily from Bible readings, was rigorously annotated to ensure phonetic and orthographic consistency, making it the most linguistically reliable resource currently available for the Sukuma language. To establish baselines, we train lightweight ASR and Text-to-Speech (TTS) models that demonstrate the feasibility of building end-to-end speech systems for this underrepresented language. This work addresses the challenges of developing language and communication tools for speakers of less-represented languages, particularly the scarcity of representative datasets and benchmarks, and highlights future research directions for linguistically challenging languages, such as Sukuma. We make our data and code publicly available to facilitate reproducibility and further research.
%U https://aclanthology.org/2026.loreslm-1.25/
%P 288-296
Markdown (Informal)
[Learning from Scarcity: Building and Benchmarking Speech Technology for Sukuma.](https://aclanthology.org/2026.loreslm-1.25/) (Mgonzo et al., LoResLM 2026)
ACL