<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="papi-etal-2022-simultaneous">
    <titleInfo>
        <title>Does Simultaneous Speech Translation need Simultaneous Models?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sara</namePart>
        <namePart type="family">Papi</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">Marco</namePart>
        <namePart type="family">Turchi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yoav</namePart>
            <namePart type="family">Goldberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zornitsa</namePart>
            <namePart type="family">Kozareva</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In simultaneous speech translation (SimulST), finding the best trade-off between high output quality and low latency is a challenging task. To meet the latency constraints posed by different application scenarios, multiple dedicated SimulST models are usually trained and maintained, generating high computational costs. In this paper, also motivated by the increased sensitivity towards sustainable AI, we investigate whether a single model trained offline can serve both offline and simultaneous applications under different latency regimes without additional training or adaptation. Experiments on en-\textgreaterde, es show that, aside from facilitating the adoption of well-established offline architectures and training strategies without affecting latency, offline training achieves similar or better quality compared to the standard SimulST training protocol, also being competitive with the state-of-the-art system.</abstract>
    <identifier type="citekey">papi-etal-2022-simultaneous</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-emnlp.11</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-emnlp.11</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>141</start>
            <end>153</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Does Simultaneous Speech Translation need Simultaneous Models?
%A Papi, Sara
%A Gaido, Marco
%A Negri, Matteo
%A Turchi, Marco
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F papi-etal-2022-simultaneous
%X In simultaneous speech translation (SimulST), finding the best trade-off between high output quality and low latency is a challenging task. To meet the latency constraints posed by different application scenarios, multiple dedicated SimulST models are usually trained and maintained, generating high computational costs. In this paper, also motivated by the increased sensitivity towards sustainable AI, we investigate whether a single model trained offline can serve both offline and simultaneous applications under different latency regimes without additional training or adaptation. Experiments on en-\textgreaterde, es show that, aside from facilitating the adoption of well-established offline architectures and training strategies without affecting latency, offline training achieves similar or better quality compared to the standard SimulST training protocol, also being competitive with the state-of-the-art system.
%R 10.18653/v1/2022.findings-emnlp.11
%U https://aclanthology.org/2022.findings-emnlp.11
%U https://doi.org/10.18653/v1/2022.findings-emnlp.11
%P 141-153

Markdown (Informal)

[Does Simultaneous Speech Translation need Simultaneous Models?](https://aclanthology.org/2022.findings-emnlp.11) (Papi et al., Findings 2022)

• Does Simultaneous Speech Translation need Simultaneous Models? (Papi et al., Findings 2022)

ACL

• Sara Papi, Marco Gaido, Matteo Negri, and Marco Turchi. 2022. Does Simultaneous Speech Translation need Simultaneous Models?. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 141–153, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.