@inproceedings{otaif-etal-2026-thakaa,
title = "Thakaa at {NADI} 2026 Shared Task: {ROVER} Ensembling and Multi-Representation Fusion for Robust {A}rabic {ASR} and Dialect Identification",
author = "Otaif, Abdulaziz and
Bakhshwain, Hazem and
Aldoobi, Abdulhamid and
Alamr, Meshal and
Aldahlawi, Abdullah",
editor = "Abdul-Mageed, Muhammad and
Elsayed, Tamer and
Bouamor, Houda and
El-Beltagy, Samhaa and
Al-Khalifa, Hend and
Abdelali, Ahmed and
Elmadany, AbdelRahim and
El Mekki, Abdellah and
Darwish, Kareem and
Alkhereyf, Sakhar and
Luqman, Hamzah and
Khalifa, Salam and
Magdy, Samar and
Alyafeai, Zaid and
Hamed, Injy and
Zaghouani, Wajdi and
Zitouni, Imed",
booktitle = "Proceedings of The Fourth {A}rabic Natural Language Processing Conference: Shared Tasks",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.arabicnlp-sharedtasks.11/",
pages = "95--109",
ISBN = "979-8-89176-497-2",
abstract = "We describe Thakaa{'}s systems for NADI 2026 subtasks 1.1 and 1.3 and Task 2, covering noisy country-level Arabic automatic speech recognition (ASR), Tunisian code-switched ASR, and spoken dialect identification. The ASR systems combine heterogeneous connectionist temporal classification (CTC), encoder{--}decoder, and audio-LLM recognizers through ROVER, with country-aware routing for subtask 1.1 and a frame-rate-corrected CTC anchor for subtask 1.3. The dialect identifier fuses Ara-BEST-RQ acoustic scores with lexical evidence extracted from Cohere and Whisper transcripts by a partially fine-tuned MARBERTv2 model. Our official test scores were 50.41{\%} WER on subtask 1.1, 14.53{\%} WER on subtask 1.3, and 56.15{\%} accuracy on Task 2, ranking third, third, and first, respectively. Across the three systems, the largest gains came from explicit control of alignment, temporal resolution, and evidence diversity rather than from model scale alone."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="otaif-etal-2026-thakaa">
<titleInfo>
<title>Thakaa at NADI 2026 Shared Task: ROVER Ensembling and Multi-Representation Fusion for Robust Arabic ASR and Dialect Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdulaziz</namePart>
<namePart type="family">Otaif</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hazem</namePart>
<namePart type="family">Bakhshwain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdulhamid</namePart>
<namePart type="family">Aldoobi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meshal</namePart>
<namePart type="family">Alamr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdullah</namePart>
<namePart type="family">Aldahlawi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Fourth Arabic Natural Language Processing Conference: Shared Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</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">Samhaa</namePart>
<namePart type="family">El-Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">AbdelRahim</namePart>
<namePart type="family">Elmadany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdellah</namePart>
<namePart type="family">El Mekki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakhar</namePart>
<namePart type="family">Alkhereyf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamzah</namePart>
<namePart type="family">Luqman</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">Samar</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zaid</namePart>
<namePart type="family">Alyafeai</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">Wajdi</namePart>
<namePart type="family">Zaghouani</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-497-2</identifier>
</relatedItem>
<abstract>We describe Thakaa’s systems for NADI 2026 subtasks 1.1 and 1.3 and Task 2, covering noisy country-level Arabic automatic speech recognition (ASR), Tunisian code-switched ASR, and spoken dialect identification. The ASR systems combine heterogeneous connectionist temporal classification (CTC), encoder–decoder, and audio-LLM recognizers through ROVER, with country-aware routing for subtask 1.1 and a frame-rate-corrected CTC anchor for subtask 1.3. The dialect identifier fuses Ara-BEST-RQ acoustic scores with lexical evidence extracted from Cohere and Whisper transcripts by a partially fine-tuned MARBERTv2 model. Our official test scores were 50.41% WER on subtask 1.1, 14.53% WER on subtask 1.3, and 56.15% accuracy on Task 2, ranking third, third, and first, respectively. Across the three systems, the largest gains came from explicit control of alignment, temporal resolution, and evidence diversity rather than from model scale alone.</abstract>
<identifier type="citekey">otaif-etal-2026-thakaa</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.11/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>95</start>
<end>109</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Thakaa at NADI 2026 Shared Task: ROVER Ensembling and Multi-Representation Fusion for Robust Arabic ASR and Dialect Identification
%A Otaif, Abdulaziz
%A Bakhshwain, Hazem
%A Aldoobi, Abdulhamid
%A Alamr, Meshal
%A Aldahlawi, Abdullah
%Y Abdul-Mageed, Muhammad
%Y Elsayed, Tamer
%Y Bouamor, Houda
%Y El-Beltagy, Samhaa
%Y Al-Khalifa, Hend
%Y Abdelali, Ahmed
%Y Elmadany, AbdelRahim
%Y El Mekki, Abdellah
%Y Darwish, Kareem
%Y Alkhereyf, Sakhar
%Y Luqman, Hamzah
%Y Khalifa, Salam
%Y Magdy, Samar
%Y Alyafeai, Zaid
%Y Hamed, Injy
%Y Zaghouani, Wajdi
%Y Zitouni, Imed
%S Proceedings of The Fourth Arabic Natural Language Processing Conference: Shared Tasks
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-497-2
%F otaif-etal-2026-thakaa
%X We describe Thakaa’s systems for NADI 2026 subtasks 1.1 and 1.3 and Task 2, covering noisy country-level Arabic automatic speech recognition (ASR), Tunisian code-switched ASR, and spoken dialect identification. The ASR systems combine heterogeneous connectionist temporal classification (CTC), encoder–decoder, and audio-LLM recognizers through ROVER, with country-aware routing for subtask 1.1 and a frame-rate-corrected CTC anchor for subtask 1.3. The dialect identifier fuses Ara-BEST-RQ acoustic scores with lexical evidence extracted from Cohere and Whisper transcripts by a partially fine-tuned MARBERTv2 model. Our official test scores were 50.41% WER on subtask 1.1, 14.53% WER on subtask 1.3, and 56.15% accuracy on Task 2, ranking third, third, and first, respectively. Across the three systems, the largest gains came from explicit control of alignment, temporal resolution, and evidence diversity rather than from model scale alone.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.11/
%P 95-109
Markdown (Informal)
[Thakaa at NADI 2026 Shared Task: ROVER Ensembling and Multi-Representation Fusion for Robust Arabic ASR and Dialect Identification](https://aclanthology.org/2026.arabicnlp-sharedtasks.11/) (Otaif et al., ArabicNLP 2026)
ACL