@inproceedings{xing-etal-2026-test,
title = "Test-Time Adaptation of an Offline Multimodal Foundation Model for Simultaneous Speech Translation",
author = "Xing, Yi and
Yu, Manli and
Liu, Pengfei and
Meng, Helen",
editor = "Salesky, Elizabeth and
Anastasopoulos, Antonios and
Negri, Matteo and
Federico, Marcello",
booktitle = "Proceedings of the 23rd International Conference on Spoken Language Translation ({IWSLT} 2026)",
month = jul,
year = "2026",
address = "San Diego, USA (in-person and online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.iwslt-1.27/",
pages = "238--246",
ISBN = "979-8-89176-411-8",
abstract = "End-to-end simultaneous speech-to-text translation (SimulST) systems typically rely on complex architectures and sophisticated training strategies. In contrast, we propose a simple approach that combines conventional pause-based segmentation for streaming audio input with a strong off-the-shelf multimodal foundation model adapted at test-time for translation. To achieve simultaneity, we adopt a variant of the classic wait-k read-write policy to control the interaction between audio input and translation output, and use a multi-turn conversation format with response prefilling and key-value caching for coherent translation and computational efficiency. Experiments on the official development sets of the IWSLT 2026 SimulST shared task show that our system achieves a better quality{--}latency trade-off than the cascaded baseline across all language directions and latency regimes, highlighting the effectiveness of this simple yet powerful approach."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xing-etal-2026-test">
<titleInfo>
<title>Test-Time Adaptation of an Offline Multimodal Foundation Model for Simultaneous Speech Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Xing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manli</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pengfei</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helen</namePart>
<namePart type="family">Meng</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>End-to-end simultaneous speech-to-text translation (SimulST) systems typically rely on complex architectures and sophisticated training strategies. In contrast, we propose a simple approach that combines conventional pause-based segmentation for streaming audio input with a strong off-the-shelf multimodal foundation model adapted at test-time for translation. To achieve simultaneity, we adopt a variant of the classic wait-k read-write policy to control the interaction between audio input and translation output, and use a multi-turn conversation format with response prefilling and key-value caching for coherent translation and computational efficiency. Experiments on the official development sets of the IWSLT 2026 SimulST shared task show that our system achieves a better quality–latency trade-off than the cascaded baseline across all language directions and latency regimes, highlighting the effectiveness of this simple yet powerful approach.</abstract>
<identifier type="citekey">xing-etal-2026-test</identifier>
<location>
<url>https://aclanthology.org/2026.iwslt-1.27/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>238</start>
<end>246</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Test-Time Adaptation of an Offline Multimodal Foundation Model for Simultaneous Speech Translation
%A Xing, Yi
%A Yu, Manli
%A Liu, Pengfei
%A Meng, Helen
%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 xing-etal-2026-test
%X End-to-end simultaneous speech-to-text translation (SimulST) systems typically rely on complex architectures and sophisticated training strategies. In contrast, we propose a simple approach that combines conventional pause-based segmentation for streaming audio input with a strong off-the-shelf multimodal foundation model adapted at test-time for translation. To achieve simultaneity, we adopt a variant of the classic wait-k read-write policy to control the interaction between audio input and translation output, and use a multi-turn conversation format with response prefilling and key-value caching for coherent translation and computational efficiency. Experiments on the official development sets of the IWSLT 2026 SimulST shared task show that our system achieves a better quality–latency trade-off than the cascaded baseline across all language directions and latency regimes, highlighting the effectiveness of this simple yet powerful approach.
%U https://aclanthology.org/2026.iwslt-1.27/
%P 238-246
Markdown (Informal)
[Test-Time Adaptation of an Offline Multimodal Foundation Model for Simultaneous Speech Translation](https://aclanthology.org/2026.iwslt-1.27/) (Xing et al., IWSLT 2026)
ACL