@inproceedings{toyin-etal-2023-artst,
title = "{A}r{TST}: {A}rabic Text and Speech Transformer",
author = "Toyin, Hawau and
Djanibekov, Amirbek and
Kulkarni, Ajinkya and
Aldarmaki, Hanan",
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-1.5",
doi = "10.18653/v1/2023.arabicnlp-1.5",
pages = "41--51",
abstract = "We present ArTST, a pre-trained Arabic text and speech transformer for supporting open-source speech technologies for the Arabic language. The model architecture follows the unified-modal framework, SpeechT5, that was recently released for English, and is focused on Modern Standard Arabic (MSA), with plans to extend the model for dialectal and code-switched Arabic in future editions. We pre-trained the model from scratch on MSA speech and text data, and fine-tuned it for the following tasks: Automatic Speech Recognition (ASR), Text-To-Speech synthesis (TTS), and spoken dialect identification. In our experiments comparing ArTST with SpeechT5, as well as with previously reported results in these tasks, ArTST performs on a par with or exceeding the current state-of-the-art in all three tasks. Moreover, we find that our pre-training is conducive for generalization, which is particularly evident in the low-resource TTS task. The pre-trained model as well as the fine-tuned ASR and TTS models are released for research use.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="toyin-etal-2023-artst">
<titleInfo>
<title>ArTST: Arabic Text and Speech Transformer</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hawau</namePart>
<namePart type="family">Toyin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amirbek</namePart>
<namePart type="family">Djanibekov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ajinkya</namePart>
<namePart type="family">Kulkarni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanan</namePart>
<namePart type="family">Aldarmaki</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>We present ArTST, a pre-trained Arabic text and speech transformer for supporting open-source speech technologies for the Arabic language. The model architecture follows the unified-modal framework, SpeechT5, that was recently released for English, and is focused on Modern Standard Arabic (MSA), with plans to extend the model for dialectal and code-switched Arabic in future editions. We pre-trained the model from scratch on MSA speech and text data, and fine-tuned it for the following tasks: Automatic Speech Recognition (ASR), Text-To-Speech synthesis (TTS), and spoken dialect identification. In our experiments comparing ArTST with SpeechT5, as well as with previously reported results in these tasks, ArTST performs on a par with or exceeding the current state-of-the-art in all three tasks. Moreover, we find that our pre-training is conducive for generalization, which is particularly evident in the low-resource TTS task. The pre-trained model as well as the fine-tuned ASR and TTS models are released for research use.</abstract>
<identifier type="citekey">toyin-etal-2023-artst</identifier>
<identifier type="doi">10.18653/v1/2023.arabicnlp-1.5</identifier>
<location>
<url>https://aclanthology.org/2023.arabicnlp-1.5</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>41</start>
<end>51</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ArTST: Arabic Text and Speech Transformer
%A Toyin, Hawau
%A Djanibekov, Amirbek
%A Kulkarni, Ajinkya
%A Aldarmaki, Hanan
%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 toyin-etal-2023-artst
%X We present ArTST, a pre-trained Arabic text and speech transformer for supporting open-source speech technologies for the Arabic language. The model architecture follows the unified-modal framework, SpeechT5, that was recently released for English, and is focused on Modern Standard Arabic (MSA), with plans to extend the model for dialectal and code-switched Arabic in future editions. We pre-trained the model from scratch on MSA speech and text data, and fine-tuned it for the following tasks: Automatic Speech Recognition (ASR), Text-To-Speech synthesis (TTS), and spoken dialect identification. In our experiments comparing ArTST with SpeechT5, as well as with previously reported results in these tasks, ArTST performs on a par with or exceeding the current state-of-the-art in all three tasks. Moreover, we find that our pre-training is conducive for generalization, which is particularly evident in the low-resource TTS task. The pre-trained model as well as the fine-tuned ASR and TTS models are released for research use.
%R 10.18653/v1/2023.arabicnlp-1.5
%U https://aclanthology.org/2023.arabicnlp-1.5
%U https://doi.org/10.18653/v1/2023.arabicnlp-1.5
%P 41-51
Markdown (Informal)
[ArTST: Arabic Text and Speech Transformer](https://aclanthology.org/2023.arabicnlp-1.5) (Toyin et al., ArabicNLP-WS 2023)
ACL
- Hawau Toyin, Amirbek Djanibekov, Ajinkya Kulkarni, and Hanan Aldarmaki. 2023. ArTST: Arabic Text and Speech Transformer. In Proceedings of ArabicNLP 2023, pages 41–51, Singapore (Hybrid). Association for Computational Linguistics.