<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fucci-etal-2026-spes">
    <titleInfo>
        <title>SPES: Spectrogram Perturbation for Explainable Speech-to-Text Generation</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">Beatrice</namePart>
        <namePart type="family">Savoldi</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">Mauro</namePart>
        <namePart type="family">Cettolo</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>
    <originInfo>
        <dateIssued>2026</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>Spurred by the demand for interpretable models, research on explainable AI for language technologies has experienced significant growth, with feature attribution methods emerging as a cornerstone of this progress. While prior work in NLP explored such methods for classification tasks and textual applications, explainability intersecting generation and speech is lagging, with existing techniques failing to account for the autoregressive nature of state-of-the-art models and to provide finegrained, phonetically meaningful explanations. We address this gap by introducing Spectrogram Perturbation for Explainable Speech-to-text Generation (SPES), a feature attribution technique applicable to sequence generation tasks with autoregressive models. SPES provides explanations for each predicted token based on both the input spectrogram and the previously generated tokens. Extensive evaluation on speech recognition and translation demonstrates that SPES generates explanations that are faithful and plausible to humans.</abstract>
    <identifier type="citekey">fucci-etal-2026-spes</identifier>
    <identifier type="doi">10.1162/tacl.a.684</identifier>
    <location>
        <url>https://aclanthology.org/2026.tacl-1.35/</url>
    </location>
    <part>
        <date>2026</date>
        <detail type="volume"><number>14</number></detail>
        <extent unit="page">
            <start>772</start>
            <end>801</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T SPES: Spectrogram Perturbation for Explainable Speech-to-Text Generation
%A Fucci, Dennis
%A Gaido, Marco
%A Savoldi, Beatrice
%A Negri, Matteo
%A Cettolo, Mauro
%A Bentivogli, Luisa
%J Transactions of the Association for Computational Linguistics
%D 2026
%V 14
%I MIT Press
%C Cambridge, MA
%F fucci-etal-2026-spes
%X Spurred by the demand for interpretable models, research on explainable AI for language technologies has experienced significant growth, with feature attribution methods emerging as a cornerstone of this progress. While prior work in NLP explored such methods for classification tasks and textual applications, explainability intersecting generation and speech is lagging, with existing techniques failing to account for the autoregressive nature of state-of-the-art models and to provide finegrained, phonetically meaningful explanations. We address this gap by introducing Spectrogram Perturbation for Explainable Speech-to-text Generation (SPES), a feature attribution technique applicable to sequence generation tasks with autoregressive models. SPES provides explanations for each predicted token based on both the input spectrogram and the previously generated tokens. Extensive evaluation on speech recognition and translation demonstrates that SPES generates explanations that are faithful and plausible to humans.
%R 10.1162/tacl.a.684
%U https://aclanthology.org/2026.tacl-1.35/
%U https://doi.org/10.1162/tacl.a.684
%P 772-801

Markdown (Informal)

[SPES: Spectrogram Perturbation for Explainable Speech-to-Text Generation](https://aclanthology.org/2026.tacl-1.35/) (Fucci et al., TACL 2026)

• SPES: Spectrogram Perturbation for Explainable Speech-to-Text Generation (Fucci et al., TACL 2026)

ACL

• Dennis Fucci, Marco Gaido, Beatrice Savoldi, Matteo Negri, Mauro Cettolo, and Luisa Bentivogli. 2026. SPES: Spectrogram Perturbation for Explainable Speech-to-Text Generation. Transactions of the Association for Computational Linguistics, 14:772–801.