@inproceedings{iranzo-sanchez-etal-2025-going,
title = "Going Beyond Your Expectations in Latency Metrics for Simultaneous Speech Translation",
author = "Iranzo-S{\'a}nchez, Jorge and
Iranzo-S{\'a}nchez, Javier and
Gim{\'e}nez, Adri{\`a} and
Civera, Jorge",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.937/",
doi = "10.18653/v1/2025.findings-acl.937",
pages = "18205--18228",
ISBN = "979-8-89176-256-5",
abstract = "Current evaluation practices in Simultaneous Speech Translation (SimulST) systems typically involve segmenting the input audio and corresponding translations, calculating quality and latency metrics for each segment, and averaging the results. Although this approach may provide a reliable estimation of translation quality, it can lead to misleading values of latency metrics due to an inherent assumption that average latency values are good enough estimators of SimulST systems' response time. However, our detailed analysis of latency evaluations for state-of-the-art SimulST systems demonstrates that latency distributions are often skewed and subject to extreme variations. As a result, the mean in latency metrics fails to capture these anomalies, potentially masking the lack of robustness in some systems and metrics. In this paper, a thorough analysis of the results of systems submitted to recent editions of the IWSLT simultaneous track is provided to support our hypothesis and alternative ways to report latency metrics are proposed in order to provide a better understanding of SimulST systems' latency."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="iranzo-sanchez-etal-2025-going">
<titleInfo>
<title>Going Beyond Your Expectations in Latency Metrics for Simultaneous Speech Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jorge</namePart>
<namePart type="family">Iranzo-Sánchez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Javier</namePart>
<namePart type="family">Iranzo-Sánchez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adrià</namePart>
<namePart type="family">Giménez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorge</namePart>
<namePart type="family">Civera</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>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Current evaluation practices in Simultaneous Speech Translation (SimulST) systems typically involve segmenting the input audio and corresponding translations, calculating quality and latency metrics for each segment, and averaging the results. Although this approach may provide a reliable estimation of translation quality, it can lead to misleading values of latency metrics due to an inherent assumption that average latency values are good enough estimators of SimulST systems’ response time. However, our detailed analysis of latency evaluations for state-of-the-art SimulST systems demonstrates that latency distributions are often skewed and subject to extreme variations. As a result, the mean in latency metrics fails to capture these anomalies, potentially masking the lack of robustness in some systems and metrics. In this paper, a thorough analysis of the results of systems submitted to recent editions of the IWSLT simultaneous track is provided to support our hypothesis and alternative ways to report latency metrics are proposed in order to provide a better understanding of SimulST systems’ latency.</abstract>
<identifier type="citekey">iranzo-sanchez-etal-2025-going</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.937</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.937/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>18205</start>
<end>18228</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Going Beyond Your Expectations in Latency Metrics for Simultaneous Speech Translation
%A Iranzo-Sánchez, Jorge
%A Iranzo-Sánchez, Javier
%A Giménez, Adrià
%A Civera, Jorge
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F iranzo-sanchez-etal-2025-going
%X Current evaluation practices in Simultaneous Speech Translation (SimulST) systems typically involve segmenting the input audio and corresponding translations, calculating quality and latency metrics for each segment, and averaging the results. Although this approach may provide a reliable estimation of translation quality, it can lead to misleading values of latency metrics due to an inherent assumption that average latency values are good enough estimators of SimulST systems’ response time. However, our detailed analysis of latency evaluations for state-of-the-art SimulST systems demonstrates that latency distributions are often skewed and subject to extreme variations. As a result, the mean in latency metrics fails to capture these anomalies, potentially masking the lack of robustness in some systems and metrics. In this paper, a thorough analysis of the results of systems submitted to recent editions of the IWSLT simultaneous track is provided to support our hypothesis and alternative ways to report latency metrics are proposed in order to provide a better understanding of SimulST systems’ latency.
%R 10.18653/v1/2025.findings-acl.937
%U https://aclanthology.org/2025.findings-acl.937/
%U https://doi.org/10.18653/v1/2025.findings-acl.937
%P 18205-18228
Markdown (Informal)
[Going Beyond Your Expectations in Latency Metrics for Simultaneous Speech Translation](https://aclanthology.org/2025.findings-acl.937/) (Iranzo-Sánchez et al., Findings 2025)
ACL