<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jon-etal-2025-aladan">
    <titleInfo>
        <title>ALADAN at IWSLT25 Low-resource Arabic Dialectal Speech Translation Task</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Josef</namePart>
        <namePart type="family">Jon</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Waad</namePart>
        <namePart type="family">Ben Kheder</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Andre</namePart>
        <namePart type="family">Beyer</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Claude</namePart>
        <namePart type="family">Barras</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jean-Luc</namePart>
        <namePart type="family">Gauvain</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Elizabeth</namePart>
            <namePart type="family">Salesky</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marcello</namePart>
            <namePart type="family">Federico</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Antonis</namePart>
            <namePart type="family">Anastasopoulos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria (in-person and online)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-272-5</identifier>
    </relatedItem>
    <abstract>We present our IWSLT 2025 submission for the low-resource track on North Levantine Arabic to English speech translation, building on our IWSLT 2024 efforts. We retain last year’s cascade ASR architecture that combines a TDNN-F model and a Zipformer for the ASR step. We upgrade the Zipformer to the Zipformer-Large variant (253 M parameters vs. 66 M) to capture richer acoustic representations. For the MT part, to further alleviate data sparsity, we created a crowd-sourced parallel corpus covering five major Arabic dialects (Tunisian, Levantine, Moroccan, Algerian, Egyptian) curated via rigorous qualification and filtering. We show that using crowd-sourced data is feasible in low-resource scenarios as we observe improved automatic evaluation metrics across all dialects. We also experimented with the dataset under a high-resource scenario, where we had access to a large, high-quality Levantine Arabic corpus from LDC. In this setting, adding the crowd-sourced data does not improve the scores on the official validation set anymore. Our final submission scores 20.0 BLEU on the official test set.</abstract>
    <identifier type="citekey">jon-etal-2025-aladan</identifier>
    <identifier type="doi">10.18653/v1/2025.iwslt-1.24</identifier>
    <location>
        <url>https://aclanthology.org/2025.iwslt-1.24/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>252</start>
            <end>259</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T ALADAN at IWSLT25 Low-resource Arabic Dialectal Speech Translation Task
%A Jon, Josef
%A Ben Kheder, Waad
%A Beyer, Andre
%A Barras, Claude
%A Gauvain, Jean-Luc
%Y Salesky, Elizabeth
%Y Federico, Marcello
%Y Anastasopoulos, Antonis
%S Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria (in-person and online)
%@ 979-8-89176-272-5
%F jon-etal-2025-aladan
%X We present our IWSLT 2025 submission for the low-resource track on North Levantine Arabic to English speech translation, building on our IWSLT 2024 efforts. We retain last year’s cascade ASR architecture that combines a TDNN-F model and a Zipformer for the ASR step. We upgrade the Zipformer to the Zipformer-Large variant (253 M parameters vs. 66 M) to capture richer acoustic representations. For the MT part, to further alleviate data sparsity, we created a crowd-sourced parallel corpus covering five major Arabic dialects (Tunisian, Levantine, Moroccan, Algerian, Egyptian) curated via rigorous qualification and filtering. We show that using crowd-sourced data is feasible in low-resource scenarios as we observe improved automatic evaluation metrics across all dialects. We also experimented with the dataset under a high-resource scenario, where we had access to a large, high-quality Levantine Arabic corpus from LDC. In this setting, adding the crowd-sourced data does not improve the scores on the official validation set anymore. Our final submission scores 20.0 BLEU on the official test set.
%R 10.18653/v1/2025.iwslt-1.24
%U https://aclanthology.org/2025.iwslt-1.24/
%U https://doi.org/10.18653/v1/2025.iwslt-1.24
%P 252-259

Markdown (Informal)

[ALADAN at IWSLT25 Low-resource Arabic Dialectal Speech Translation Task](https://aclanthology.org/2025.iwslt-1.24/) (Jon et al., IWSLT 2025)

• ALADAN at IWSLT25 Low-resource Arabic Dialectal Speech Translation Task (Jon et al., IWSLT 2025)

ACL

• Josef Jon, Waad Ben Kheder, Andre Beyer, Claude Barras, and Jean-Luc Gauvain. 2025. ALADAN at IWSLT25 Low-resource Arabic Dialectal Speech Translation Task. In Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025), pages 252–259, Vienna, Austria (in-person and online). Association for Computational Linguistics.