<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="meng-anastasopoulos-2025-gmu">
    <titleInfo>
        <title>GMU Systems for the IWSLT 2025 Low-Resource Speech Translation Shared Task</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Chutong</namePart>
        <namePart type="family">Meng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Antonios</namePart>
        <namePart type="family">Anastasopoulos</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>This paper describes the GMU systems for the IWSLT 2025 low-resource speech translation shared task. We trained systems for all language pairs, except for Levantine Arabic. We fine-tuned SeamlessM4T-v2 for automatic speech recognition (ASR), machine translation (MT), and end-to-end speech translation (E2E ST). The ASR and MT models are also used to form cascaded ST systems. Additionally, we explored various training paradigms for E2E ST fine-tuning, including direct E2E fine-tuning, multi-task training, and parameter initialization using components from fine-tuned ASR and/or MT models. Our results show that (1) direct E2E fine-tuning yields strong results; (2) initializing with a fine-tuned ASR encoder improves ST performance on languages SeamlessM4T-v2 has not been trained on; (3) multi-task training can be slightly helpful.</abstract>
    <identifier type="citekey">meng-anastasopoulos-2025-gmu</identifier>
    <identifier type="doi">10.18653/v1/2025.iwslt-1.29</identifier>
    <location>
        <url>https://aclanthology.org/2025.iwslt-1.29/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>289</start>
            <end>300</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T GMU Systems for the IWSLT 2025 Low-Resource Speech Translation Shared Task
%A Meng, Chutong
%A Anastasopoulos, Antonios
%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 meng-anastasopoulos-2025-gmu
%X This paper describes the GMU systems for the IWSLT 2025 low-resource speech translation shared task. We trained systems for all language pairs, except for Levantine Arabic. We fine-tuned SeamlessM4T-v2 for automatic speech recognition (ASR), machine translation (MT), and end-to-end speech translation (E2E ST). The ASR and MT models are also used to form cascaded ST systems. Additionally, we explored various training paradigms for E2E ST fine-tuning, including direct E2E fine-tuning, multi-task training, and parameter initialization using components from fine-tuned ASR and/or MT models. Our results show that (1) direct E2E fine-tuning yields strong results; (2) initializing with a fine-tuned ASR encoder improves ST performance on languages SeamlessM4T-v2 has not been trained on; (3) multi-task training can be slightly helpful.
%R 10.18653/v1/2025.iwslt-1.29
%U https://aclanthology.org/2025.iwslt-1.29/
%U https://doi.org/10.18653/v1/2025.iwslt-1.29
%P 289-300

Markdown (Informal)

[GMU Systems for the IWSLT 2025 Low-Resource Speech Translation Shared Task](https://aclanthology.org/2025.iwslt-1.29/) (Meng & Anastasopoulos, IWSLT 2025)

• GMU Systems for the IWSLT 2025 Low-Resource Speech Translation Shared Task (Meng & Anastasopoulos, IWSLT 2025)

ACL

• Chutong Meng and Antonios Anastasopoulos. 2025. GMU Systems for the IWSLT 2025 Low-Resource Speech Translation Shared Task. In Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025), pages 289–300, Vienna, Austria (in-person and online). Association for Computational Linguistics.