<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bentes-safka-2026-pinch">
    <titleInfo>
        <title>Pinch-AST: Robust Cascaded Speech Translation System for the IWSLT 2026 Simultaneous Speech Translation Task</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Carlos</namePart>
        <namePart type="family">Bentes</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Christian</namePart>
        <namePart type="family">Safka</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 23rd International Conference on Spoken Language Translation (IWSLT 2026)</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">Antonios</namePart>
            <namePart type="family">Anastasopoulos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Matteo</namePart>
            <namePart type="family">Negri</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>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, USA (in-person and online)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-411-8</identifier>
    </relatedItem>
    <abstract>We describe Pinch-AST, our submission to the IWSLT 2026 Simultaneous Speech-to-Text Translation shared task, covering all four official directions (En → De, En → It, En → Zh, Cs → En) under both low- and high- latency regimes. Pinch-AST is a cascaded system pairing off-the-shelf speech models with a translation backbone adapted per language pair via LoRA on ASR-noise-augmented parallel data. The streaming policy is a character-level longest-common-prefix re-translation strategy, and the full pipeline runs on a single H100 80 GB GPU within the real-time budget. Evaluated on the IWSLT 2026 development set, Pinch-AST achieves competitive quality–latency trade-offs across all four language pairs in both latency regimes.</abstract>
    <identifier type="citekey">bentes-safka-2026-pinch</identifier>
    <location>
        <url>https://aclanthology.org/2026.iwslt-1.30/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>268</start>
            <end>271</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Pinch-AST: Robust Cascaded Speech Translation System for the IWSLT 2026 Simultaneous Speech Translation Task
%A Bentes, Carlos
%A Safka, Christian
%Y Salesky, Elizabeth
%Y Anastasopoulos, Antonios
%Y Negri, Matteo
%Y Federico, Marcello
%S Proceedings of the 23rd International Conference on Spoken Language Translation (IWSLT 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, USA (in-person and online)
%@ 979-8-89176-411-8
%F bentes-safka-2026-pinch
%X We describe Pinch-AST, our submission to the IWSLT 2026 Simultaneous Speech-to-Text Translation shared task, covering all four official directions (En → De, En → It, En → Zh, Cs → En) under both low- and high- latency regimes. Pinch-AST is a cascaded system pairing off-the-shelf speech models with a translation backbone adapted per language pair via LoRA on ASR-noise-augmented parallel data. The streaming policy is a character-level longest-common-prefix re-translation strategy, and the full pipeline runs on a single H100 80 GB GPU within the real-time budget. Evaluated on the IWSLT 2026 development set, Pinch-AST achieves competitive quality–latency trade-offs across all four language pairs in both latency regimes.
%U https://aclanthology.org/2026.iwslt-1.30/
%P 268-271

Markdown (Informal)

[Pinch-AST: Robust Cascaded Speech Translation System for the IWSLT 2026 Simultaneous Speech Translation Task](https://aclanthology.org/2026.iwslt-1.30/) (Bentes & Safka, IWSLT 2026)

• Pinch-AST: Robust Cascaded Speech Translation System for the IWSLT 2026 Simultaneous Speech Translation Task (Bentes & Safka, IWSLT 2026)

ACL

• Carlos Bentes and Christian Safka. 2026. Pinch-AST: Robust Cascaded Speech Translation System for the IWSLT 2026 Simultaneous Speech Translation Task. In Proceedings of the 23rd International Conference on Spoken Language Translation (IWSLT 2026), pages 268–271, San Diego, USA (in-person and online). Association for Computational Linguistics.