@inproceedings{mukiibi-etal-2022-makerere,
title = "The Makerere Radio Speech Corpus: A {L}uganda Radio Corpus for Automatic Speech Recognition",
author = "Mukiibi, Jonathan and
Katumba, Andrew and
Nakatumba-Nabende, Joyce and
Hussein, Ali and
Meyer, Joshua",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.208/",
pages = "1945--1954",
abstract = "Building a usable radio monitoring automatic speech recognition (ASR) system is a challenging task for under-resourced languages and yet this is paramount in societies where radio is the main medium of public communication and discussions. Initial efforts by the United Nations in Uganda have proved how understanding the perceptions of rural people who are excluded from social media is important in national planning. However, these efforts are being challenged by the absence of transcribed speech datasets. In this paper, The Makerere Artificial Intelligence research lab releases a Luganda radio speech corpus of 155 hours. To our knowledge, this is the first publicly available radio dataset in sub-Saharan Africa. The paper describes the development of the voice corpus and presents baseline Luganda ASR performance results using Coqui STT toolkit, an open-source speech recognition toolkit."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mukiibi-etal-2022-makerere">
<titleInfo>
<title>The Makerere Radio Speech Corpus: A Luganda Radio Corpus for Automatic Speech Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Mukiibi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Katumba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nakatumba-Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Hussein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joshua</namePart>
<namePart type="family">Meyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Building a usable radio monitoring automatic speech recognition (ASR) system is a challenging task for under-resourced languages and yet this is paramount in societies where radio is the main medium of public communication and discussions. Initial efforts by the United Nations in Uganda have proved how understanding the perceptions of rural people who are excluded from social media is important in national planning. However, these efforts are being challenged by the absence of transcribed speech datasets. In this paper, The Makerere Artificial Intelligence research lab releases a Luganda radio speech corpus of 155 hours. To our knowledge, this is the first publicly available radio dataset in sub-Saharan Africa. The paper describes the development of the voice corpus and presents baseline Luganda ASR performance results using Coqui STT toolkit, an open-source speech recognition toolkit.</abstract>
<identifier type="citekey">mukiibi-etal-2022-makerere</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.208/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>1945</start>
<end>1954</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Makerere Radio Speech Corpus: A Luganda Radio Corpus for Automatic Speech Recognition
%A Mukiibi, Jonathan
%A Katumba, Andrew
%A Nakatumba-Nabende, Joyce
%A Hussein, Ali
%A Meyer, Joshua
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F mukiibi-etal-2022-makerere
%X Building a usable radio monitoring automatic speech recognition (ASR) system is a challenging task for under-resourced languages and yet this is paramount in societies where radio is the main medium of public communication and discussions. Initial efforts by the United Nations in Uganda have proved how understanding the perceptions of rural people who are excluded from social media is important in national planning. However, these efforts are being challenged by the absence of transcribed speech datasets. In this paper, The Makerere Artificial Intelligence research lab releases a Luganda radio speech corpus of 155 hours. To our knowledge, this is the first publicly available radio dataset in sub-Saharan Africa. The paper describes the development of the voice corpus and presents baseline Luganda ASR performance results using Coqui STT toolkit, an open-source speech recognition toolkit.
%U https://aclanthology.org/2022.lrec-1.208/
%P 1945-1954
Markdown (Informal)
[The Makerere Radio Speech Corpus: A Luganda Radio Corpus for Automatic Speech Recognition](https://aclanthology.org/2022.lrec-1.208/) (Mukiibi et al., LREC 2022)
ACL