@inproceedings{dossou-emezue-2021-okwugbe,
title = "{O}kwu{G}b{\'e}: End-to-End Speech Recognition for {F}on and {I}gbo",
author = "Dossou, Bonaventure F. P. and
Emezue, Chris Chinenye",
booktitle = "Proceedings of the Fifth Workshop on Widening Natural Language Processing",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.winlp-1.1",
pages = "1--4",
abstract = "Language is a fundamental component of human communication. African low-resourced languages have recently been a major subject of research in machine translation, and other text-based areas of NLP. However, there is still very little comparable research in speech recognition for African languages. OkwuGb{\'e} is a step towards building speech recognition systems for African low-resourced languages. Using Fon and Igbo as our case study, we build two end-to-end deep neural network-based speech recognition models. We present a state-of-the-art automatic speech recognition (ASR) model for Fon, and a benchmark ASR model result for Igbo. Our findings serve both as a guide for future NLP research for Fon and Igbo in particular, and the creation of speech recognition models for other African low-resourced languages in general. The Fon and Igbo models source code have been made publicly available. Moreover, Okwugbe, a python library has been created to make easier the process of ASR model building and training.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dossou-emezue-2021-okwugbe">
<titleInfo>
<title>OkwuGbé: End-to-End Speech Recognition for Fon and Igbo</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonaventure</namePart>
<namePart type="given">F</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Dossou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="given">Chinenye</namePart>
<namePart type="family">Emezue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Widening Natural Language Processing</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Language is a fundamental component of human communication. African low-resourced languages have recently been a major subject of research in machine translation, and other text-based areas of NLP. However, there is still very little comparable research in speech recognition for African languages. OkwuGbé is a step towards building speech recognition systems for African low-resourced languages. Using Fon and Igbo as our case study, we build two end-to-end deep neural network-based speech recognition models. We present a state-of-the-art automatic speech recognition (ASR) model for Fon, and a benchmark ASR model result for Igbo. Our findings serve both as a guide for future NLP research for Fon and Igbo in particular, and the creation of speech recognition models for other African low-resourced languages in general. The Fon and Igbo models source code have been made publicly available. Moreover, Okwugbe, a python library has been created to make easier the process of ASR model building and training.</abstract>
<identifier type="citekey">dossou-emezue-2021-okwugbe</identifier>
<location>
<url>https://aclanthology.org/2021.winlp-1.1</url>
</location>
<part>
<date>2021-nov</date>
<extent unit="page">
<start>1</start>
<end>4</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T OkwuGbé: End-to-End Speech Recognition for Fon and Igbo
%A Dossou, Bonaventure F. P.
%A Emezue, Chris Chinenye
%S Proceedings of the Fifth Workshop on Widening Natural Language Processing
%D 2021
%8 nov
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F dossou-emezue-2021-okwugbe
%X Language is a fundamental component of human communication. African low-resourced languages have recently been a major subject of research in machine translation, and other text-based areas of NLP. However, there is still very little comparable research in speech recognition for African languages. OkwuGbé is a step towards building speech recognition systems for African low-resourced languages. Using Fon and Igbo as our case study, we build two end-to-end deep neural network-based speech recognition models. We present a state-of-the-art automatic speech recognition (ASR) model for Fon, and a benchmark ASR model result for Igbo. Our findings serve both as a guide for future NLP research for Fon and Igbo in particular, and the creation of speech recognition models for other African low-resourced languages in general. The Fon and Igbo models source code have been made publicly available. Moreover, Okwugbe, a python library has been created to make easier the process of ASR model building and training.
%U https://aclanthology.org/2021.winlp-1.1
%P 1-4
Markdown (Informal)
[OkwuGbé: End-to-End Speech Recognition for Fon and Igbo](https://aclanthology.org/2021.winlp-1.1) (Dossou & Emezue, WiNLP 2021)
ACL
- Bonaventure F. P. Dossou and Chris Chinenye Emezue. 2021. OkwuGbé: End-to-End Speech Recognition for Fon and Igbo. In Proceedings of the Fifth Workshop on Widening Natural Language Processing, pages 1–4, Punta Cana, Dominican Republic. Association for Computational Linguistics.