<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="machacek-polak-2025-simultaneous">
    <titleInfo>
        <title>Simultaneous Translation with Offline Speech and LLM Models in CUNI Submission to IWSLT 2025</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Dominik</namePart>
        <namePart type="family">Macháček</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Peter</namePart>
        <namePart type="family">Polák</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 Charles University submission to the Simultaneous Speech Translation Task of the IWSLT 2025. We cover all four language pairs with a direct or cascade approach. The backbone of our systems is the offline Whisper speech model, which we use for both translation and transcription in simultaneous mode with the state-of-the-art simultaneous policy AlignAtt. We further improve the performance by prompting to inject in-domain terminology, and we accommodate context. Our cascaded systems further use EuroLLM for unbounded simultaneous translation. Compared to the Organizers’ baseline, our systems improve by 2 BLEU points on Czech to English and 13-22 BLEU points on English to German, Chinese and Japanese on the development sets. Additionally, we also propose a new enhanced measure of speech recognition latency.</abstract>
    <identifier type="citekey">machacek-polak-2025-simultaneous</identifier>
    <identifier type="doi">10.18653/v1/2025.iwslt-1.41</identifier>
    <location>
        <url>https://aclanthology.org/2025.iwslt-1.41/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>389</start>
            <end>398</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Simultaneous Translation with Offline Speech and LLM Models in CUNI Submission to IWSLT 2025
%A Macháček, Dominik
%A Polák, Peter
%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 machacek-polak-2025-simultaneous
%X This paper describes Charles University submission to the Simultaneous Speech Translation Task of the IWSLT 2025. We cover all four language pairs with a direct or cascade approach. The backbone of our systems is the offline Whisper speech model, which we use for both translation and transcription in simultaneous mode with the state-of-the-art simultaneous policy AlignAtt. We further improve the performance by prompting to inject in-domain terminology, and we accommodate context. Our cascaded systems further use EuroLLM for unbounded simultaneous translation. Compared to the Organizers’ baseline, our systems improve by 2 BLEU points on Czech to English and 13-22 BLEU points on English to German, Chinese and Japanese on the development sets. Additionally, we also propose a new enhanced measure of speech recognition latency.
%R 10.18653/v1/2025.iwslt-1.41
%U https://aclanthology.org/2025.iwslt-1.41/
%U https://doi.org/10.18653/v1/2025.iwslt-1.41
%P 389-398

Markdown (Informal)

[Simultaneous Translation with Offline Speech and LLM Models in CUNI Submission to IWSLT 2025](https://aclanthology.org/2025.iwslt-1.41/) (Macháček & Polák, IWSLT 2025)

• Simultaneous Translation with Offline Speech and LLM Models in CUNI Submission to IWSLT 2025 (Macháček & Polák, IWSLT 2025)

ACL

• Dominik Macháček and Peter Polák. 2025. Simultaneous Translation with Offline Speech and LLM Models in CUNI Submission to IWSLT 2025. In Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025), pages 389–398, Vienna, Austria (in-person and online). Association for Computational Linguistics.