@inproceedings{shatnawi-etal-2024-data,
title = "Data Augmentation for Speech-Based Diacritic Restoration",
author = "Shatnawi, Sara and
Alqahtani, Sawsan and
Shehata, Shady and
Aldarmaki, Hanan",
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-1.15",
pages = "160--169",
abstract = "This paper describes a data augmentation technique for boosting the performance of speech-based diacritic restoration. Our experiments demonstrate the utility of this appraoch, resulting in improved generalization of all models across different test sets. In addition, we describe the first multi-modal diacritic restoration model, utilizing both speech and text as input modalities. This type of model can be used to diacritize speech transcripts. Unlike previous work that relies on an external ASR model, the proposed model is far more compact and efficient. While the multi-modal framework does not surpass the ASR-based model for this task, it offers a promising approach for improving the efficiency of speech-based diacritization, with a potential for improvement using data augmentation and other methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shatnawi-etal-2024-data">
<titleInfo>
<title>Data Augmentation for Speech-Based Diacritic Restoration</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Shatnawi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sawsan</namePart>
<namePart type="family">Alqahtani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shady</namePart>
<namePart type="family">Shehata</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>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>This paper describes a data augmentation technique for boosting the performance of speech-based diacritic restoration. Our experiments demonstrate the utility of this appraoch, resulting in improved generalization of all models across different test sets. In addition, we describe the first multi-modal diacritic restoration model, utilizing both speech and text as input modalities. This type of model can be used to diacritize speech transcripts. Unlike previous work that relies on an external ASR model, the proposed model is far more compact and efficient. While the multi-modal framework does not surpass the ASR-based model for this task, it offers a promising approach for improving the efficiency of speech-based diacritization, with a potential for improvement using data augmentation and other methods.</abstract>
<identifier type="citekey">shatnawi-etal-2024-data</identifier>
<location>
<url>https://aclanthology.org/2024.arabicnlp-1.15</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>160</start>
<end>169</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Data Augmentation for Speech-Based Diacritic Restoration
%A Shatnawi, Sara
%A Alqahtani, Sawsan
%A Shehata, Shady
%A Aldarmaki, Hanan
%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 shatnawi-etal-2024-data
%X This paper describes a data augmentation technique for boosting the performance of speech-based diacritic restoration. Our experiments demonstrate the utility of this appraoch, resulting in improved generalization of all models across different test sets. In addition, we describe the first multi-modal diacritic restoration model, utilizing both speech and text as input modalities. This type of model can be used to diacritize speech transcripts. Unlike previous work that relies on an external ASR model, the proposed model is far more compact and efficient. While the multi-modal framework does not surpass the ASR-based model for this task, it offers a promising approach for improving the efficiency of speech-based diacritization, with a potential for improvement using data augmentation and other methods.
%U https://aclanthology.org/2024.arabicnlp-1.15
%P 160-169
Markdown (Informal)
[Data Augmentation for Speech-Based Diacritic Restoration](https://aclanthology.org/2024.arabicnlp-1.15) (Shatnawi et al., ArabicNLP-WS 2024)
ACL
- Sara Shatnawi, Sawsan Alqahtani, Shady Shehata, and Hanan Aldarmaki. 2024. Data Augmentation for Speech-Based Diacritic Restoration. In Proceedings of The Second Arabic Natural Language Processing Conference, pages 160–169, Bangkok, Thailand. Association for Computational Linguistics.