@inproceedings{gaido-etal-2026-simulstream,
title = "Simulstream: Open-Source Toolkit for Evaluation and Demonstration of Streaming Speech-to-Text Translation Systems",
author = "Gaido, Marco and
Papi, Sara and
Cettolo, Mauro and
Negri, Matteo and
Bentivogli, Luisa",
editor = "Agrawal, Sweta and
Abad, Alberto",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-demos.8/",
pages = "87--97",
ISBN = "979-8-89176-461-3",
abstract = "Streaming Speech-to-Text Translation (StreamST) requires producing translations concurrently with incoming speech under strict latency constraints, demanding models that balance low latency with high translation quality. Despite rapid progress, evaluation remains fragmented across existing frameworks, which make different assumptions about how systems operate{---}for example, whether they process continuous speech or short pre-segmented audio, and whether they support output revision (retranslation) or not (incremental) during decoding. As a result, comparing systems fairly and consistently across studies remains challenging. SimulEval, the most widely used framework, reflects these limitations: it supports only incremental decoding, assumes short segmented inputs, and lacks a native support for system demonstrations. More broadly, existing alternatives address only subsets of evaluation and deployment needs, leaving no unified solution for benchmarking and interactive demonstration. To address this gap, we introduce simulstream, the first open-source framework for StreamST evaluation and demonstration. It supports both incremental and re-translation decoding on long-form speech, provides fine-grained logging for quality and latency evaluation, and includes an interactive web interface for real-time visualization and comparison."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gaido-etal-2026-simulstream">
<titleInfo>
<title>Simulstream: Open-Source Toolkit for Evaluation and Demonstration of Streaming Speech-to-Text Translation Systems</title>
</titleInfo>
<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">Sara</namePart>
<namePart type="family">Papi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mauro</namePart>
<namePart type="family">Cettolo</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">Luisa</namePart>
<namePart type="family">Bentivogli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sweta</namePart>
<namePart type="family">Agrawal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Abad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-461-3</identifier>
</relatedItem>
<abstract>Streaming Speech-to-Text Translation (StreamST) requires producing translations concurrently with incoming speech under strict latency constraints, demanding models that balance low latency with high translation quality. Despite rapid progress, evaluation remains fragmented across existing frameworks, which make different assumptions about how systems operate—for example, whether they process continuous speech or short pre-segmented audio, and whether they support output revision (retranslation) or not (incremental) during decoding. As a result, comparing systems fairly and consistently across studies remains challenging. SimulEval, the most widely used framework, reflects these limitations: it supports only incremental decoding, assumes short segmented inputs, and lacks a native support for system demonstrations. More broadly, existing alternatives address only subsets of evaluation and deployment needs, leaving no unified solution for benchmarking and interactive demonstration. To address this gap, we introduce simulstream, the first open-source framework for StreamST evaluation and demonstration. It supports both incremental and re-translation decoding on long-form speech, provides fine-grained logging for quality and latency evaluation, and includes an interactive web interface for real-time visualization and comparison.</abstract>
<identifier type="citekey">gaido-etal-2026-simulstream</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-demos.8/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>87</start>
<end>97</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Simulstream: Open-Source Toolkit for Evaluation and Demonstration of Streaming Speech-to-Text Translation Systems
%A Gaido, Marco
%A Papi, Sara
%A Cettolo, Mauro
%A Negri, Matteo
%A Bentivogli, Luisa
%Y Agrawal, Sweta
%Y Abad, Alberto
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-461-3
%F gaido-etal-2026-simulstream
%X Streaming Speech-to-Text Translation (StreamST) requires producing translations concurrently with incoming speech under strict latency constraints, demanding models that balance low latency with high translation quality. Despite rapid progress, evaluation remains fragmented across existing frameworks, which make different assumptions about how systems operate—for example, whether they process continuous speech or short pre-segmented audio, and whether they support output revision (retranslation) or not (incremental) during decoding. As a result, comparing systems fairly and consistently across studies remains challenging. SimulEval, the most widely used framework, reflects these limitations: it supports only incremental decoding, assumes short segmented inputs, and lacks a native support for system demonstrations. More broadly, existing alternatives address only subsets of evaluation and deployment needs, leaving no unified solution for benchmarking and interactive demonstration. To address this gap, we introduce simulstream, the first open-source framework for StreamST evaluation and demonstration. It supports both incremental and re-translation decoding on long-form speech, provides fine-grained logging for quality and latency evaluation, and includes an interactive web interface for real-time visualization and comparison.
%U https://aclanthology.org/2026.emnlp-demos.8/
%P 87-97
Markdown (Informal)
[Simulstream: Open-Source Toolkit for Evaluation and Demonstration of Streaming Speech-to-Text Translation Systems](https://aclanthology.org/2026.emnlp-demos.8/) (Gaido et al., EMNLP 2026)
ACL