@inproceedings{al-wazrah-etal-2026-ksaa,
title = "{KSAA}-2026 Shared Task on {A}rabic Speech Dictation with Automatic Diacritization",
author = "Al Wazrah, Asma Ali and
Alshammari, Waad and
Almatham, Rawan and
Al-rasheed, Raghad and
Altamimi, Afrah Abdulaziz and
Marew, Rufael and
Alqahtani, Sawsan and
Aldarmaki, Hanan and
Alharbi, Abdullah I. and
Alshehri, Abdulrahman Saeed and
Assar, Mohamed and
Almazrua, Amal and
Alosaimy, Abdulrahman",
editor = "Al-Khalifa, Hend and
El-Haj, Mo and
Ezzini, Saad",
booktitle = "The 7th Workshop on Open-Source {A}rabic Corpora and Processing Tools ({OSACT}7) with 5 Shared Tasks",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.osact-1.28/",
doi = "10.63317/33hmmyfpg7mx",
pages = "220--224",
abstract = "This paper presents the KSAA-2026 Shared Task on Arabic Speech Dictation with Automatic Diacritization, addressing a persistent challenge in Arabic NLP. The task focuses on transforming speech transcripts into fully diacritized Arabic text by leveraging both the speech signal and its undiacritized transcript. Unlike conventional ASR tasks that focus on transcription, this task integrates acoustic and textual information to improve diacritization accuracy. The shared task consists of two subtasks: (1) Data Contribution, where participants recorded and reviewed speech data through the VoiceWall platform, resulting in 2,160 recordings, and (2) Diacritization, where 5 teams developed systems that generate fully diacritized text from speech and undiacritized transcripts. The dataset includes approximately 5 hours of Modern Standard Arabic (MSA) and multi-dialectal speech with fully diacritized references. Experimental results show that several participant systems outperform the provided baselines, and that incorporating speech information and fine-tuning improves performance compared to text-only approaches. KSAA-2026 shared task establishes a benchmark for multimodal Arabic diacritization and supports the development of robust systems for applications in education, accessibility, and speech-driven text generation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="al-wazrah-etal-2026-ksaa">
<titleInfo>
<title>KSAA-2026 Shared Task on Arabic Speech Dictation with Automatic Diacritization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Asma</namePart>
<namePart type="given">Ali</namePart>
<namePart type="family">Al Wazrah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Waad</namePart>
<namePart type="family">Alshammari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rawan</namePart>
<namePart type="family">Almatham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raghad</namePart>
<namePart type="family">Al-rasheed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Afrah</namePart>
<namePart type="given">Abdulaziz</namePart>
<namePart type="family">Altamimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rufael</namePart>
<namePart type="family">Marew</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">Hanan</namePart>
<namePart type="family">Aldarmaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdullah</namePart>
<namePart type="given">I</namePart>
<namePart type="family">Alharbi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdulrahman</namePart>
<namePart type="given">Saeed</namePart>
<namePart type="family">Alshehri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Assar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amal</namePart>
<namePart type="family">Almazrua</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdulrahman</namePart>
<namePart type="family">Alosaimy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mo</namePart>
<namePart type="family">El-Haj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saad</namePart>
<namePart type="family">Ezzini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents the KSAA-2026 Shared Task on Arabic Speech Dictation with Automatic Diacritization, addressing a persistent challenge in Arabic NLP. The task focuses on transforming speech transcripts into fully diacritized Arabic text by leveraging both the speech signal and its undiacritized transcript. Unlike conventional ASR tasks that focus on transcription, this task integrates acoustic and textual information to improve diacritization accuracy. The shared task consists of two subtasks: (1) Data Contribution, where participants recorded and reviewed speech data through the VoiceWall platform, resulting in 2,160 recordings, and (2) Diacritization, where 5 teams developed systems that generate fully diacritized text from speech and undiacritized transcripts. The dataset includes approximately 5 hours of Modern Standard Arabic (MSA) and multi-dialectal speech with fully diacritized references. Experimental results show that several participant systems outperform the provided baselines, and that incorporating speech information and fine-tuning improves performance compared to text-only approaches. KSAA-2026 shared task establishes a benchmark for multimodal Arabic diacritization and supports the development of robust systems for applications in education, accessibility, and speech-driven text generation.</abstract>
<identifier type="citekey">al-wazrah-etal-2026-ksaa</identifier>
<identifier type="doi">10.63317/33hmmyfpg7mx</identifier>
<location>
<url>https://aclanthology.org/2026.osact-1.28/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>220</start>
<end>224</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KSAA-2026 Shared Task on Arabic Speech Dictation with Automatic Diacritization
%A Al Wazrah, Asma Ali
%A Alshammari, Waad
%A Almatham, Rawan
%A Al-rasheed, Raghad
%A Altamimi, Afrah Abdulaziz
%A Marew, Rufael
%A Alqahtani, Sawsan
%A Aldarmaki, Hanan
%A Alharbi, Abdullah I.
%A Alshehri, Abdulrahman Saeed
%A Assar, Mohamed
%A Almazrua, Amal
%A Alosaimy, Abdulrahman
%Y Al-Khalifa, Hend
%Y El-Haj, Mo
%Y Ezzini, Saad
%S The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks
%D 2026
%8 May
%I Association for Computational Linguistics
%C Palma, Mallorca (Spain)
%F al-wazrah-etal-2026-ksaa
%X This paper presents the KSAA-2026 Shared Task on Arabic Speech Dictation with Automatic Diacritization, addressing a persistent challenge in Arabic NLP. The task focuses on transforming speech transcripts into fully diacritized Arabic text by leveraging both the speech signal and its undiacritized transcript. Unlike conventional ASR tasks that focus on transcription, this task integrates acoustic and textual information to improve diacritization accuracy. The shared task consists of two subtasks: (1) Data Contribution, where participants recorded and reviewed speech data through the VoiceWall platform, resulting in 2,160 recordings, and (2) Diacritization, where 5 teams developed systems that generate fully diacritized text from speech and undiacritized transcripts. The dataset includes approximately 5 hours of Modern Standard Arabic (MSA) and multi-dialectal speech with fully diacritized references. Experimental results show that several participant systems outperform the provided baselines, and that incorporating speech information and fine-tuning improves performance compared to text-only approaches. KSAA-2026 shared task establishes a benchmark for multimodal Arabic diacritization and supports the development of robust systems for applications in education, accessibility, and speech-driven text generation.
%R 10.63317/33hmmyfpg7mx
%U https://aclanthology.org/2026.osact-1.28/
%U https://doi.org/10.63317/33hmmyfpg7mx
%P 220-224
Markdown (Informal)
[KSAA-2026 Shared Task on Arabic Speech Dictation with Automatic Diacritization](https://aclanthology.org/2026.osact-1.28/) (Al Wazrah et al., OSACT 2026)
ACL
- Asma Ali Al Wazrah, Waad Alshammari, Rawan Almatham, Raghad Al-rasheed, Afrah Abdulaziz Altamimi, Rufael Marew, Sawsan Alqahtani, Hanan Aldarmaki, Abdullah I. Alharbi, Abdulrahman Saeed Alshehri, Mohamed Assar, Amal Almazrua, and Abdulrahman Alosaimy. 2026. KSAA-2026 Shared Task on Arabic Speech Dictation with Automatic Diacritization. In The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks, pages 220–224, Palma, Mallorca (Spain). Association for Computational Linguistics.