The Speech-LLM Takes It All: A Truly Fully End-to-End Spoken Dialog State Tracking Approach

Nizar El Ghazal; Antoine Caubrière; Valentin Vielzeuf

doi:10.63317/5dwmfoqycu6w

The Speech-LLM Takes It All: A Truly Fully End-to-End Spoken Dialog State Tracking Approach

Nizar El Ghazal, Antoine Caubrière, Valentin Vielzeuf

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use ... for bold, ... for italic, ... for underline, <sc>...</sc> for small-caps, <tt>...<tt> for typewriter text, <url>...</url> for URLs, <a href=...> for hyperlinks, and <par/> for paragraph breaks.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the external publication .)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

This paper presents a comparative study of context management strategies for end-to-end Spoken Dialog State Tracking using Speech-LLMs. We systematically evaluate traditional multimodal context (combining text history and spoken current turn), full spoken history, and compressed spoken history approaches. Our experiments on the SpokenWOZ corpus demonstrate that providing the full spoken conversation as input yields the highest performance among models of similar size, significantly surpassing prior methods. Furthermore, we show that attention-pooling-based compression of the spoken history offers a strong trade-off, maintaining competitive accuracy with reduced context size. Detailed analysis confirms that improvements stem from more effective context utilization.

Anthology ID:: 2026.lrec-1.206
Volume:: Proceedings of the Fifteenth Language Resources and Evaluation Conference
Month:: May
Year:: 2026
Address:: Palma de Mallorca, Spain
Editors:: Stelios Piperidis, Núria Bel, Henk van den Heuvel, Nancy Ide, Simon Krek, Antonio Toral
Venue:: LREC
SIG:
Publisher:: ELRA Language Resource Association
Note:
Pages:: 2629–2637
Language:
External URL:: https://lrec.elra.info/lrec2026-main-206
DOI:: 10.63317/5dwmfoqycu6w
Bibkey:
Cite (ACL):: Nizar El Ghazal, Antoine Caubrière, and Valentin Vielzeuf. 2026. The Speech-LLM Takes It All: A Truly Fully End-to-End Spoken Dialog State Tracking Approach. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 2629–2637, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):: The Speech-LLM Takes It All: A Truly Fully End-to-End Spoken Dialog State Tracking Approach (El Ghazal et al., LREC 2026)
Copy Citation:

External Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{el-ghazal-etal-2026-speech,
    title = "The Speech-{LLM} Takes It All: A Truly Fully End-to-End Spoken Dialog State Tracking Approach",
    author = "El Ghazal, Nizar  and
      Caubri{\`e}re, Antoine  and
      Vielzeuf, Valentin",
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://aclanthology.org/2026.lrec-1.206/",
    doi = "10.63317/5dwmfoqycu6w",
    pages = "2629--2637",
    abstract = "This paper presents a comparative study of context management strategies for end-to-end Spoken Dialog State Tracking using Speech-LLMs. We systematically evaluate traditional multimodal context (combining text history and spoken current turn), full spoken history, and compressed spoken history approaches. Our experiments on the SpokenWOZ corpus demonstrate that providing the full spoken conversation as input yields the highest performance among models of similar size, significantly surpassing prior methods. Furthermore, we show that attention-pooling-based compression of the spoken history offers a strong trade-off, maintaining competitive accuracy with reduced context size. Detailed analysis confirms that improvements stem from more effective context utilization."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="el-ghazal-etal-2026-speech">
    <titleInfo>
        <title>The Speech-LLM Takes It All: A Truly Fully End-to-End Spoken Dialog State Tracking Approach</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Nizar</namePart>
        <namePart type="family">El Ghazal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Antoine</namePart>
        <namePart type="family">Caubrière</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Valentin</namePart>
        <namePart type="family">Vielzeuf</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Stelios</namePart>
            <namePart type="family">Piperidis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Núria</namePart>
            <namePart type="family">Bel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Henk</namePart>
            <namePart type="family">van den Heuvel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nancy</namePart>
            <namePart type="family">Ide</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Simon</namePart>
            <namePart type="family">Krek</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Antonio</namePart>
            <namePart type="family">Toral</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>ELRA Language Resource Association</publisher>
            <place>
                <placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper presents a comparative study of context management strategies for end-to-end Spoken Dialog State Tracking using Speech-LLMs. We systematically evaluate traditional multimodal context (combining text history and spoken current turn), full spoken history, and compressed spoken history approaches. Our experiments on the SpokenWOZ corpus demonstrate that providing the full spoken conversation as input yields the highest performance among models of similar size, significantly surpassing prior methods. Furthermore, we show that attention-pooling-based compression of the spoken history offers a strong trade-off, maintaining competitive accuracy with reduced context size. Detailed analysis confirms that improvements stem from more effective context utilization.</abstract>
    <identifier type="citekey">el-ghazal-etal-2026-speech</identifier>
    <identifier type="doi">10.63317/5dwmfoqycu6w</identifier>
    <location>
        <url>https://aclanthology.org/2026.lrec-1.206/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>2629</start>
            <end>2637</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T The Speech-LLM Takes It All: A Truly Fully End-to-End Spoken Dialog State Tracking Approach
%A El Ghazal, Nizar
%A Caubrière, Antoine
%A Vielzeuf, Valentin
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F el-ghazal-etal-2026-speech
%X This paper presents a comparative study of context management strategies for end-to-end Spoken Dialog State Tracking using Speech-LLMs. We systematically evaluate traditional multimodal context (combining text history and spoken current turn), full spoken history, and compressed spoken history approaches. Our experiments on the SpokenWOZ corpus demonstrate that providing the full spoken conversation as input yields the highest performance among models of similar size, significantly surpassing prior methods. Furthermore, we show that attention-pooling-based compression of the spoken history offers a strong trade-off, maintaining competitive accuracy with reduced context size. Detailed analysis confirms that improvements stem from more effective context utilization.
%R 10.63317/5dwmfoqycu6w
%U https://aclanthology.org/2026.lrec-1.206/
%U https://doi.org/10.63317/5dwmfoqycu6w
%P 2629-2637

Download as File

Markdown (Informal)

[The Speech-LLM Takes It All: A Truly Fully End-to-End Spoken Dialog State Tracking Approach](https://aclanthology.org/2026.lrec-1.206/) (El Ghazal et al., LREC 2026)

The Speech-LLM Takes It All: A Truly Fully End-to-End Spoken Dialog State Tracking Approach (El Ghazal et al., LREC 2026)

ACL

Nizar El Ghazal, Antoine Caubrière, and Valentin Vielzeuf. 2026. The Speech-LLM Takes It All: A Truly Fully End-to-End Spoken Dialog State Tracking Approach. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 2629–2637, Palma de Mallorca, Spain. ELRA Language Resource Association.