@inproceedings{laouirine-etal-2024-tunartts,
title = "{T}un{A}r{TTS}: {T}unisian {A}rabic Text-To-Speech Corpus",
author = "Laouirine, Imen and
Kammoun, Rami and
Bougares, Fethi",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1467",
pages = "16879--16889",
abstract = "Being labeled as a low-resource language, the Tunisian dialect has no existing prior TTS research. In this paper, we present a speech corpus for Tunisian Arabic Text-to-Speech (TunArTTS) to initiate the development of end-to-end TTS systems for the Tunisian dialect. Our Speech corpus is extracted from an online English and Tunisian Arabic dictionary. We were able to extract a mono-speaker speech corpus of +3 hours of a male speaker sampled at 44100 kHz. The corpus is processed and manually diacritized. Furthermore, we develop various TTS systems based on two approaches: training from scratch and transfer learning. Both Tacotron2 and FastSpeech2 were used and evaluated using subjective and objective metrics. The experimental results show that our best results are obtained with the transfer learning from a pre-trained model on the English LJSpeech dataset. This model obtained a mean opinion score (MOS) of 3.88. TunArTTS will be publicly available for research purposes along with the baseline TTS system demo. Keywords: Tunisian Dialect, Text-To-Speech, Low-resource, Transfer Learning, TunArTTS",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="laouirine-etal-2024-tunartts">
<titleInfo>
<title>TunArTTS: Tunisian Arabic Text-To-Speech Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Imen</namePart>
<namePart type="family">Laouirine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rami</namePart>
<namePart type="family">Kammoun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fethi</namePart>
<namePart type="family">Bougares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Being labeled as a low-resource language, the Tunisian dialect has no existing prior TTS research. In this paper, we present a speech corpus for Tunisian Arabic Text-to-Speech (TunArTTS) to initiate the development of end-to-end TTS systems for the Tunisian dialect. Our Speech corpus is extracted from an online English and Tunisian Arabic dictionary. We were able to extract a mono-speaker speech corpus of +3 hours of a male speaker sampled at 44100 kHz. The corpus is processed and manually diacritized. Furthermore, we develop various TTS systems based on two approaches: training from scratch and transfer learning. Both Tacotron2 and FastSpeech2 were used and evaluated using subjective and objective metrics. The experimental results show that our best results are obtained with the transfer learning from a pre-trained model on the English LJSpeech dataset. This model obtained a mean opinion score (MOS) of 3.88. TunArTTS will be publicly available for research purposes along with the baseline TTS system demo. Keywords: Tunisian Dialect, Text-To-Speech, Low-resource, Transfer Learning, TunArTTS</abstract>
<identifier type="citekey">laouirine-etal-2024-tunartts</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1467</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>16879</start>
<end>16889</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TunArTTS: Tunisian Arabic Text-To-Speech Corpus
%A Laouirine, Imen
%A Kammoun, Rami
%A Bougares, Fethi
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F laouirine-etal-2024-tunartts
%X Being labeled as a low-resource language, the Tunisian dialect has no existing prior TTS research. In this paper, we present a speech corpus for Tunisian Arabic Text-to-Speech (TunArTTS) to initiate the development of end-to-end TTS systems for the Tunisian dialect. Our Speech corpus is extracted from an online English and Tunisian Arabic dictionary. We were able to extract a mono-speaker speech corpus of +3 hours of a male speaker sampled at 44100 kHz. The corpus is processed and manually diacritized. Furthermore, we develop various TTS systems based on two approaches: training from scratch and transfer learning. Both Tacotron2 and FastSpeech2 were used and evaluated using subjective and objective metrics. The experimental results show that our best results are obtained with the transfer learning from a pre-trained model on the English LJSpeech dataset. This model obtained a mean opinion score (MOS) of 3.88. TunArTTS will be publicly available for research purposes along with the baseline TTS system demo. Keywords: Tunisian Dialect, Text-To-Speech, Low-resource, Transfer Learning, TunArTTS
%U https://aclanthology.org/2024.lrec-main.1467
%P 16879-16889
Markdown (Informal)
[TunArTTS: Tunisian Arabic Text-To-Speech Corpus](https://aclanthology.org/2024.lrec-main.1467) (Laouirine et al., LREC-COLING 2024)
ACL
- Imen Laouirine, Rami Kammoun, and Fethi Bougares. 2024. TunArTTS: Tunisian Arabic Text-To-Speech Corpus. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 16879–16889, Torino, Italia. ELRA and ICCL.