<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fucci-etal-2025-different">
    <titleInfo>
        <title>Different Speech Translation Models Encode and Translate Speaker Gender Differently</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Dennis</namePart>
        <namePart type="family">Fucci</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Marco</namePart>
        <namePart type="family">Gaido</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Matteo</namePart>
        <namePart type="family">Negri</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Luisa</namePart>
        <namePart type="family">Bentivogli</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Andre</namePart>
        <namePart type="family">Martins</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Giuseppe</namePart>
        <namePart type="family">Attanasio</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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Wanxiang</namePart>
            <namePart type="family">Che</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joyce</namePart>
            <namePart type="family">Nabende</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Shutova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohammad</namePart>
            <namePart type="given">Taher</namePart>
            <namePart type="family">Pilehvar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-252-7</identifier>
    </relatedItem>
    <abstract>Recent studies on interpreting the hidden states of speech models have shown their ability to capture speaker-specific features, including gender. Does this finding also hold for speech translation (ST) models? If so, what are the implications for the speaker’s gender assignment in translation? We address these questions from an interpretability perspective, using probing methods to assess gender encoding across diverse ST models. Results on three language directions (English \rightarrow French/Italian/Spanish) indicate that while traditional encoder-decoder models capture gender information, newer architectures—integrating a speech encoder with a machine translation system via adapters—do not. We also demonstrate that low gender encoding capabilities result in systems’ tendency toward a masculine default, a translation bias that is more pronounced in newer architectures.</abstract>
    <identifier type="citekey">fucci-etal-2025-different</identifier>
    <identifier type="doi">10.18653/v1/2025.acl-short.78</identifier>
    <location>
        <url>https://aclanthology.org/2025.acl-short.78/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>1005</start>
            <end>1019</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Different Speech Translation Models Encode and Translate Speaker Gender Differently
%A Fucci, Dennis
%A Gaido, Marco
%A Negri, Matteo
%A Bentivogli, Luisa
%A Martins, Andre
%A Attanasio, Giuseppe
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-252-7
%F fucci-etal-2025-different
%X Recent studies on interpreting the hidden states of speech models have shown their ability to capture speaker-specific features, including gender. Does this finding also hold for speech translation (ST) models? If so, what are the implications for the speaker’s gender assignment in translation? We address these questions from an interpretability perspective, using probing methods to assess gender encoding across diverse ST models. Results on three language directions (English \rightarrow French/Italian/Spanish) indicate that while traditional encoder-decoder models capture gender information, newer architectures—integrating a speech encoder with a machine translation system via adapters—do not. We also demonstrate that low gender encoding capabilities result in systems’ tendency toward a masculine default, a translation bias that is more pronounced in newer architectures.
%R 10.18653/v1/2025.acl-short.78
%U https://aclanthology.org/2025.acl-short.78/
%U https://doi.org/10.18653/v1/2025.acl-short.78
%P 1005-1019

Markdown (Informal)

[Different Speech Translation Models Encode and Translate Speaker Gender Differently](https://aclanthology.org/2025.acl-short.78/) (Fucci et al., ACL 2025)

• Different Speech Translation Models Encode and Translate Speaker Gender Differently (Fucci et al., ACL 2025)

ACL

• Dennis Fucci, Marco Gaido, Matteo Negri, Luisa Bentivogli, Andre Martins, and Giuseppe Attanasio. 2025. Different Speech Translation Models Encode and Translate Speaker Gender Differently. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 1005–1019, Vienna, Austria. Association for Computational Linguistics.