@inproceedings{siminyu-etal-2022-corpus,
title = "Corpus Development of Kiswahili Speech Recognition Test and Evaluation sets, Preemptively Mitigating Demographic Bias Through Collaboration with Linguists",
author = "Siminyu, Kathleen and
Mohamed Amran, Kibibi and
Ndegwa Karatu, Abdulrahman and
Resani, Mnata and
Makobo Junior, Mwimbi and
Ryakitimbo, Rebecca and
Mwasaru, Britone",
editor = "Moeller, Sarah and
Anastasopoulos, Antonios and
Arppe, Antti and
Chaudhary, Aditi and
Harrigan, Atticus and
Holden, Josh and
Lachler, Jordan and
Palmer, Alexis and
Rijhwani, Shruti and
Schwartz, Lane",
booktitle = "Proceedings of the Fifth Workshop on the Use of Computational Methods in the Study of Endangered Languages",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.computel-1.3",
doi = "10.18653/v1/2022.computel-1.3",
pages = "13--19",
abstract = "Language technologies, particularly speech technologies, are becoming more pervasive for access to digital platforms and resources. This brings to the forefront concerns of their inclusivity, first in terms of language diversity. Additionally, research shows speech recognition to be more accurate for men than for women and more accurate for individuals younger than 30 years of age than those older. In the Global South where languages are low resource, these same issues should be taken into consideration in data collection efforts to not replicate these mistakes. It is also important to note that in varying contexts within the Global South, this work presents additional nuance and potential for bias based on accents, related dialects and variants of a language. This paper documents i) the designing and execution of a Linguists Engagement for purposes of building an inclusive Kiswahili Speech Recognition dataset, representative of the diversity among speakers of the language ii) the unexpected yet key learning in terms of socio-linguistcs which demonstrate the importance of multi-disciplinarity in teams developing datasets and NLP technologies iii) the creation of a test dataset intended to be used for evaluating the performance of Speech Recognition models on demographic groups that are likely to be underrepresented.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="siminyu-etal-2022-corpus">
<titleInfo>
<title>Corpus Development of Kiswahili Speech Recognition Test and Evaluation sets, Preemptively Mitigating Demographic Bias Through Collaboration with Linguists</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kathleen</namePart>
<namePart type="family">Siminyu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kibibi</namePart>
<namePart type="family">Mohamed Amran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdulrahman</namePart>
<namePart type="family">Ndegwa Karatu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mnata</namePart>
<namePart type="family">Resani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mwimbi</namePart>
<namePart type="family">Makobo Junior</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Ryakitimbo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Britone</namePart>
<namePart type="family">Mwasaru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on the Use of Computational Methods in the Study of Endangered Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sarah</namePart>
<namePart type="family">Moeller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonios</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antti</namePart>
<namePart type="family">Arppe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aditi</namePart>
<namePart type="family">Chaudhary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atticus</namePart>
<namePart type="family">Harrigan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josh</namePart>
<namePart type="family">Holden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Lachler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shruti</namePart>
<namePart type="family">Rijhwani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lane</namePart>
<namePart type="family">Schwartz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Language technologies, particularly speech technologies, are becoming more pervasive for access to digital platforms and resources. This brings to the forefront concerns of their inclusivity, first in terms of language diversity. Additionally, research shows speech recognition to be more accurate for men than for women and more accurate for individuals younger than 30 years of age than those older. In the Global South where languages are low resource, these same issues should be taken into consideration in data collection efforts to not replicate these mistakes. It is also important to note that in varying contexts within the Global South, this work presents additional nuance and potential for bias based on accents, related dialects and variants of a language. This paper documents i) the designing and execution of a Linguists Engagement for purposes of building an inclusive Kiswahili Speech Recognition dataset, representative of the diversity among speakers of the language ii) the unexpected yet key learning in terms of socio-linguistcs which demonstrate the importance of multi-disciplinarity in teams developing datasets and NLP technologies iii) the creation of a test dataset intended to be used for evaluating the performance of Speech Recognition models on demographic groups that are likely to be underrepresented.</abstract>
<identifier type="citekey">siminyu-etal-2022-corpus</identifier>
<identifier type="doi">10.18653/v1/2022.computel-1.3</identifier>
<location>
<url>https://aclanthology.org/2022.computel-1.3</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>13</start>
<end>19</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Corpus Development of Kiswahili Speech Recognition Test and Evaluation sets, Preemptively Mitigating Demographic Bias Through Collaboration with Linguists
%A Siminyu, Kathleen
%A Mohamed Amran, Kibibi
%A Ndegwa Karatu, Abdulrahman
%A Resani, Mnata
%A Makobo Junior, Mwimbi
%A Ryakitimbo, Rebecca
%A Mwasaru, Britone
%Y Moeller, Sarah
%Y Anastasopoulos, Antonios
%Y Arppe, Antti
%Y Chaudhary, Aditi
%Y Harrigan, Atticus
%Y Holden, Josh
%Y Lachler, Jordan
%Y Palmer, Alexis
%Y Rijhwani, Shruti
%Y Schwartz, Lane
%S Proceedings of the Fifth Workshop on the Use of Computational Methods in the Study of Endangered Languages
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F siminyu-etal-2022-corpus
%X Language technologies, particularly speech technologies, are becoming more pervasive for access to digital platforms and resources. This brings to the forefront concerns of their inclusivity, first in terms of language diversity. Additionally, research shows speech recognition to be more accurate for men than for women and more accurate for individuals younger than 30 years of age than those older. In the Global South where languages are low resource, these same issues should be taken into consideration in data collection efforts to not replicate these mistakes. It is also important to note that in varying contexts within the Global South, this work presents additional nuance and potential for bias based on accents, related dialects and variants of a language. This paper documents i) the designing and execution of a Linguists Engagement for purposes of building an inclusive Kiswahili Speech Recognition dataset, representative of the diversity among speakers of the language ii) the unexpected yet key learning in terms of socio-linguistcs which demonstrate the importance of multi-disciplinarity in teams developing datasets and NLP technologies iii) the creation of a test dataset intended to be used for evaluating the performance of Speech Recognition models on demographic groups that are likely to be underrepresented.
%R 10.18653/v1/2022.computel-1.3
%U https://aclanthology.org/2022.computel-1.3
%U https://doi.org/10.18653/v1/2022.computel-1.3
%P 13-19
Markdown (Informal)
[Corpus Development of Kiswahili Speech Recognition Test and Evaluation sets, Preemptively Mitigating Demographic Bias Through Collaboration with Linguists](https://aclanthology.org/2022.computel-1.3) (Siminyu et al., ComputEL 2022)
ACL
- Kathleen Siminyu, Kibibi Mohamed Amran, Abdulrahman Ndegwa Karatu, Mnata Resani, Mwimbi Makobo Junior, Rebecca Ryakitimbo, and Britone Mwasaru. 2022. Corpus Development of Kiswahili Speech Recognition Test and Evaluation sets, Preemptively Mitigating Demographic Bias Through Collaboration with Linguists. In Proceedings of the Fifth Workshop on the Use of Computational Methods in the Study of Endangered Languages, pages 13–19, Dublin, Ireland. Association for Computational Linguistics.