@inproceedings{abdelaziz-etal-2026-namaa,
title = "{NAMAA} Community at {NADI} 2026: Mixed-Dialect and Code-Switched {A}rabic {ASR} and Spoken Dialect Identification",
author = "Abdelaziz, Mohamed and
Mohamed Emad Elden, Fatimah and
El Malak, Mousa Ashraf Abd and
Nacar, Omer",
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.7/",
pages = "63--71",
ISBN = "979-8-89176-497-2",
abstract = "Robust Arabic speech processing must accommodate dialectal variation, multilingual code-switching, and distribution shift. We present NAMAA Community{'}s systems for three NADI 2026 speech subtasks: Mixed-Dialect Arabic ASR, Code-Switched Arabic ASR, and 20-way Spoken Arabic Dialect Identification. For Mixed-Dialect ASR, an Arabic-specific Conformer{--}Transformer achieves 0.45 word error rate (WER) on the blind set, outperforming a development-selected normalization and consensus pipeline at 0.49. For Code-Switched ASR, two-stage LoRA adaptation of the Tunisian Whisper-derived FarukSTT checkpoint, with multilingual tokenization and unconstrained decoding, yields 20.38{\%} WER and 8.06{\%} character error rate (CER) on validation and 16.98{\%} blind-test WER. For dialect identification, a four-model ensemble reaches 0.950 development accuracy but 0.31 on the out-of-domain blind set. Label-free class-spread and inter-model agreement diagnostics identify an outlying component; removing it improves blind accuracy to 0.36, and a refined three-model submission reaches 0.38. Across Subtasks 1.2 and 2, development-selected calibration did not reliably transfer to blind data, although the available comparisons do not isolate the causal effect of individual components."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abdelaziz-etal-2026-namaa">
<titleInfo>
<title>NAMAA Community at NADI 2026: Mixed-Dialect and Code-Switched Arabic ASR and Spoken Dialect Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Abdelaziz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fatimah</namePart>
<namePart type="family">Mohamed Emad Elden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mousa</namePart>
<namePart type="given">Ashraf</namePart>
<namePart type="given">Abd</namePart>
<namePart type="family">El Malak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omer</namePart>
<namePart type="family">Nacar</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>Robust Arabic speech processing must accommodate dialectal variation, multilingual code-switching, and distribution shift. We present NAMAA Community’s systems for three NADI 2026 speech subtasks: Mixed-Dialect Arabic ASR, Code-Switched Arabic ASR, and 20-way Spoken Arabic Dialect Identification. For Mixed-Dialect ASR, an Arabic-specific Conformer–Transformer achieves 0.45 word error rate (WER) on the blind set, outperforming a development-selected normalization and consensus pipeline at 0.49. For Code-Switched ASR, two-stage LoRA adaptation of the Tunisian Whisper-derived FarukSTT checkpoint, with multilingual tokenization and unconstrained decoding, yields 20.38% WER and 8.06% character error rate (CER) on validation and 16.98% blind-test WER. For dialect identification, a four-model ensemble reaches 0.950 development accuracy but 0.31 on the out-of-domain blind set. Label-free class-spread and inter-model agreement diagnostics identify an outlying component; removing it improves blind accuracy to 0.36, and a refined three-model submission reaches 0.38. Across Subtasks 1.2 and 2, development-selected calibration did not reliably transfer to blind data, although the available comparisons do not isolate the causal effect of individual components.</abstract>
<identifier type="citekey">abdelaziz-etal-2026-namaa</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.7/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>63</start>
<end>71</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NAMAA Community at NADI 2026: Mixed-Dialect and Code-Switched Arabic ASR and Spoken Dialect Identification
%A Abdelaziz, Mohamed
%A Mohamed Emad Elden, Fatimah
%A El Malak, Mousa Ashraf Abd
%A Nacar, Omer
%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 abdelaziz-etal-2026-namaa
%X Robust Arabic speech processing must accommodate dialectal variation, multilingual code-switching, and distribution shift. We present NAMAA Community’s systems for three NADI 2026 speech subtasks: Mixed-Dialect Arabic ASR, Code-Switched Arabic ASR, and 20-way Spoken Arabic Dialect Identification. For Mixed-Dialect ASR, an Arabic-specific Conformer–Transformer achieves 0.45 word error rate (WER) on the blind set, outperforming a development-selected normalization and consensus pipeline at 0.49. For Code-Switched ASR, two-stage LoRA adaptation of the Tunisian Whisper-derived FarukSTT checkpoint, with multilingual tokenization and unconstrained decoding, yields 20.38% WER and 8.06% character error rate (CER) on validation and 16.98% blind-test WER. For dialect identification, a four-model ensemble reaches 0.950 development accuracy but 0.31 on the out-of-domain blind set. Label-free class-spread and inter-model agreement diagnostics identify an outlying component; removing it improves blind accuracy to 0.36, and a refined three-model submission reaches 0.38. Across Subtasks 1.2 and 2, development-selected calibration did not reliably transfer to blind data, although the available comparisons do not isolate the causal effect of individual components.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.7/
%P 63-71
Markdown (Informal)
[NAMAA Community at NADI 2026: Mixed-Dialect and Code-Switched Arabic ASR and Spoken Dialect Identification](https://aclanthology.org/2026.arabicnlp-sharedtasks.7/) (Abdelaziz et al., ArabicNLP 2026)
ACL