@inproceedings{doan-etal-2024-towards,
title = "Towards Zero-Shot Text-To-Speech for {A}rabic Dialects",
author = "Doan, Khai and
Waheed, Abdul and
Abdul-Mageed, Muhammad",
editor = "Habash, Nizar and
Bouamor, Houda and
Eskander, Ramy and
Tomeh, Nadi and
Abu Farha, Ibrahim and
Abdelali, Ahmed and
Touileb, Samia and
Hamed, Injy and
Onaizan, Yaser and
Alhafni, Bashar and
Antoun, Wissam and
Khalifa, Salam and
Haddad, Hatem and
Zitouni, Imed and
AlKhamissi, Badr and
Almatham, Rawan and
Mrini, Khalil",
booktitle = "Proceedings of The Second Arabic Natural Language Processing Conference",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.arabicnlp-1.11",
pages = "123--129",
abstract = "Zero-shot multi-speaker text-to-speech (ZS-TTS) systems have advanced for English, however, it still lags behind due to insufficient resources. We address this gap for Arabic, a language of more than 450 million native speakers, by first adapting a sizeable existing dataset to suit the needs of speech synthesis. Additionally, we employ a set of Arabic dialect identification models to explore the impact of pre-defined dialect labels on improving the ZS-TTS model in a multi-dialect setting. Subsequently, we fine-tune the XTTS model, an open-source architecture. We then evaluate our models on a dataset comprising 31 unseen speakers and an in-house dialectal dataset. Our automated and human evaluation results show convincing performance while capable of generating dialectal speech. Our study highlights significant potential for improvements in this emerging area of research in Arabic.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="doan-etal-2024-towards">
<titleInfo>
<title>Towards Zero-Shot Text-To-Speech for Arabic Dialects</title>
</titleInfo>
<name type="personal">
<namePart type="given">Khai</namePart>
<namePart type="family">Doan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdul</namePart>
<namePart type="family">Waheed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Second Arabic Natural Language Processing Conference</title>
</titleInfo>
<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">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramy</namePart>
<namePart type="family">Eskander</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">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samia</namePart>
<namePart type="family">Touileb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Injy</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bashar</namePart>
<namePart type="family">Alhafni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wissam</namePart>
<namePart type="family">Antoun</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">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">Badr</namePart>
<namePart type="family">AlKhamissi</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>
<name type="personal">
<namePart type="given">Khalil</namePart>
<namePart type="family">Mrini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Zero-shot multi-speaker text-to-speech (ZS-TTS) systems have advanced for English, however, it still lags behind due to insufficient resources. We address this gap for Arabic, a language of more than 450 million native speakers, by first adapting a sizeable existing dataset to suit the needs of speech synthesis. Additionally, we employ a set of Arabic dialect identification models to explore the impact of pre-defined dialect labels on improving the ZS-TTS model in a multi-dialect setting. Subsequently, we fine-tune the XTTS model, an open-source architecture. We then evaluate our models on a dataset comprising 31 unseen speakers and an in-house dialectal dataset. Our automated and human evaluation results show convincing performance while capable of generating dialectal speech. Our study highlights significant potential for improvements in this emerging area of research in Arabic.</abstract>
<identifier type="citekey">doan-etal-2024-towards</identifier>
<location>
<url>https://aclanthology.org/2024.arabicnlp-1.11</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>123</start>
<end>129</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Zero-Shot Text-To-Speech for Arabic Dialects
%A Doan, Khai
%A Waheed, Abdul
%A Abdul-Mageed, Muhammad
%Y Habash, Nizar
%Y Bouamor, Houda
%Y Eskander, Ramy
%Y Tomeh, Nadi
%Y Abu Farha, Ibrahim
%Y Abdelali, Ahmed
%Y Touileb, Samia
%Y Hamed, Injy
%Y Onaizan, Yaser
%Y Alhafni, Bashar
%Y Antoun, Wissam
%Y Khalifa, Salam
%Y Haddad, Hatem
%Y Zitouni, Imed
%Y AlKhamissi, Badr
%Y Almatham, Rawan
%Y Mrini, Khalil
%S Proceedings of The Second Arabic Natural Language Processing Conference
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F doan-etal-2024-towards
%X Zero-shot multi-speaker text-to-speech (ZS-TTS) systems have advanced for English, however, it still lags behind due to insufficient resources. We address this gap for Arabic, a language of more than 450 million native speakers, by first adapting a sizeable existing dataset to suit the needs of speech synthesis. Additionally, we employ a set of Arabic dialect identification models to explore the impact of pre-defined dialect labels on improving the ZS-TTS model in a multi-dialect setting. Subsequently, we fine-tune the XTTS model, an open-source architecture. We then evaluate our models on a dataset comprising 31 unseen speakers and an in-house dialectal dataset. Our automated and human evaluation results show convincing performance while capable of generating dialectal speech. Our study highlights significant potential for improvements in this emerging area of research in Arabic.
%U https://aclanthology.org/2024.arabicnlp-1.11
%P 123-129
Markdown (Informal)
[Towards Zero-Shot Text-To-Speech for Arabic Dialects](https://aclanthology.org/2024.arabicnlp-1.11) (Doan et al., ArabicNLP-WS 2024)
ACL
- Khai Doan, Abdul Waheed, and Muhammad Abdul-Mageed. 2024. Towards Zero-Shot Text-To-Speech for Arabic Dialects. In Proceedings of The Second Arabic Natural Language Processing Conference, pages 123–129, Bangkok, Thailand. Association for Computational Linguistics.