@inproceedings{alkanhal-etal-2023-aswat,
title = "Aswat: {A}rabic Audio Dataset for Automatic Speech Recognition Using Speech-Representation Learning",
author = "Alkanhal, Lamya and
Alessa, Abeer and
Almahmoud, Elaf and
Alaqil, Rana",
editor = "Sawaf, Hassan and
El-Beltagy, Samhaa and
Zaghouani, Wajdi and
Magdy, Walid and
Abdelali, Ahmed and
Tomeh, Nadi and
Abu Farha, Ibrahim and
Habash, Nizar and
Khalifa, Salam and
Keleg, Amr and
Haddad, Hatem and
Zitouni, Imed and
Mrini, Khalil and
Almatham, Rawan",
booktitle = "Proceedings of ArabicNLP 2023",
month = dec,
year = "2023",
address = "Singapore (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.arabicnlp-1.10",
doi = "10.18653/v1/2023.arabicnlp-1.10",
pages = "120--127",
abstract = "Recent advancements in self-supervised speech-representation learning for automatic speech recognition (ASR) approaches have significantly improved the results on many benchmarks with low-cost data labeling. In this paper, we train two self-supervised frameworks for ASR, namely wav2vec, and data2vec, in which we conduct multiple experiments and analyze their results. Furthermore, we introduce Aswat dataset, which covers multiple genres and features speakers with vocal variety. Aswat contains 732 hours of clean Arabic speech that can be used in the pretraining task for learning latent speech representations, which results in achieving a lower word error rate (WER) in Arabic ASR. We report the baseline results and achieve state-of-the-art WERs of 11.7{\%} and 10.3{\%} on Common Voice (CV) and the second round of Multi-Genre Broadcast (MGB-2) respectively, as a result of including our dataset Aswat.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alkanhal-etal-2023-aswat">
<titleInfo>
<title>Aswat: Arabic Audio Dataset for Automatic Speech Recognition Using Speech-Representation Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lamya</namePart>
<namePart type="family">Alkanhal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abeer</namePart>
<namePart type="family">Alessa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elaf</namePart>
<namePart type="family">Almahmoud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rana</namePart>
<namePart type="family">Alaqil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of ArabicNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hassan</namePart>
<namePart type="family">Sawaf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samhaa</namePart>
<namePart type="family">El-Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walid</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadi</namePart>
<namePart type="family">Tomeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ibrahim</namePart>
<namePart type="family">Abu Farha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amr</namePart>
<namePart type="family">Keleg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hatem</namePart>
<namePart type="family">Haddad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalil</namePart>
<namePart type="family">Mrini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rawan</namePart>
<namePart type="family">Almatham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent advancements in self-supervised speech-representation learning for automatic speech recognition (ASR) approaches have significantly improved the results on many benchmarks with low-cost data labeling. In this paper, we train two self-supervised frameworks for ASR, namely wav2vec, and data2vec, in which we conduct multiple experiments and analyze their results. Furthermore, we introduce Aswat dataset, which covers multiple genres and features speakers with vocal variety. Aswat contains 732 hours of clean Arabic speech that can be used in the pretraining task for learning latent speech representations, which results in achieving a lower word error rate (WER) in Arabic ASR. We report the baseline results and achieve state-of-the-art WERs of 11.7% and 10.3% on Common Voice (CV) and the second round of Multi-Genre Broadcast (MGB-2) respectively, as a result of including our dataset Aswat.</abstract>
<identifier type="citekey">alkanhal-etal-2023-aswat</identifier>
<identifier type="doi">10.18653/v1/2023.arabicnlp-1.10</identifier>
<location>
<url>https://aclanthology.org/2023.arabicnlp-1.10</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>120</start>
<end>127</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Aswat: Arabic Audio Dataset for Automatic Speech Recognition Using Speech-Representation Learning
%A Alkanhal, Lamya
%A Alessa, Abeer
%A Almahmoud, Elaf
%A Alaqil, Rana
%Y Sawaf, Hassan
%Y El-Beltagy, Samhaa
%Y Zaghouani, Wajdi
%Y Magdy, Walid
%Y Abdelali, Ahmed
%Y Tomeh, Nadi
%Y Abu Farha, Ibrahim
%Y Habash, Nizar
%Y Khalifa, Salam
%Y Keleg, Amr
%Y Haddad, Hatem
%Y Zitouni, Imed
%Y Mrini, Khalil
%Y Almatham, Rawan
%S Proceedings of ArabicNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore (Hybrid)
%F alkanhal-etal-2023-aswat
%X Recent advancements in self-supervised speech-representation learning for automatic speech recognition (ASR) approaches have significantly improved the results on many benchmarks with low-cost data labeling. In this paper, we train two self-supervised frameworks for ASR, namely wav2vec, and data2vec, in which we conduct multiple experiments and analyze their results. Furthermore, we introduce Aswat dataset, which covers multiple genres and features speakers with vocal variety. Aswat contains 732 hours of clean Arabic speech that can be used in the pretraining task for learning latent speech representations, which results in achieving a lower word error rate (WER) in Arabic ASR. We report the baseline results and achieve state-of-the-art WERs of 11.7% and 10.3% on Common Voice (CV) and the second round of Multi-Genre Broadcast (MGB-2) respectively, as a result of including our dataset Aswat.
%R 10.18653/v1/2023.arabicnlp-1.10
%U https://aclanthology.org/2023.arabicnlp-1.10
%U https://doi.org/10.18653/v1/2023.arabicnlp-1.10
%P 120-127
Markdown (Informal)
[Aswat: Arabic Audio Dataset for Automatic Speech Recognition Using Speech-Representation Learning](https://aclanthology.org/2023.arabicnlp-1.10) (Alkanhal et al., ArabicNLP-WS 2023)
ACL