@inproceedings{krahn-fosler-lussier-2026-hydraqe,
title = "{H}ydra{QE}: {OSU}{'}s Submission for the {IWSLT} 2026 Speech Translation Metrics Shared Task",
author = "Krahn, Kevin and
Fosler-Lussier, Eric",
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-1.37/",
pages = "323--331",
ISBN = "979-8-89176-411-8",
abstract = "We present HydraQE, our contribution to the IWSLT 2026 Speech Translation Metrics shared task. HydraQE is an end-to-end, reference-free quality estimation (QE) system for speech translation built on a Qwen3-ASR backbone, which accepts source audio and a translation hypothesis as joint input. Hidden states from all backbone layers are combined via a sparsemax scalar mix, then re-encoded by a bidirectional Transformer for full cross-modal interaction. To address the scarcity of human-annotated speech translation data, three independent prediction heads are trained on complementary supervision signals: human direct assessment (DA) annotations, MetricX-24 pseudo-labels, and xCOMET pseudo-labels. We train on a combination of synthetically corrupted examples and silver pseudo-labeled machine translation outputs, using a curriculum that begins on synthetic and silver data and gradually shifts toward human-annotated examples. HydraQE outperforms cascaded text-based baselines and prior direct speech QE systems, demonstrating that end-to-end speech translation QE is competitive with cascaded approaches."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="krahn-fosler-lussier-2026-hydraqe">
<titleInfo>
<title>HydraQE: OSU’s Submission for the IWSLT 2026 Speech Translation Metrics Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Krahn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Fosler-Lussier</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>We present HydraQE, our contribution to the IWSLT 2026 Speech Translation Metrics shared task. HydraQE is an end-to-end, reference-free quality estimation (QE) system for speech translation built on a Qwen3-ASR backbone, which accepts source audio and a translation hypothesis as joint input. Hidden states from all backbone layers are combined via a sparsemax scalar mix, then re-encoded by a bidirectional Transformer for full cross-modal interaction. To address the scarcity of human-annotated speech translation data, three independent prediction heads are trained on complementary supervision signals: human direct assessment (DA) annotations, MetricX-24 pseudo-labels, and xCOMET pseudo-labels. We train on a combination of synthetically corrupted examples and silver pseudo-labeled machine translation outputs, using a curriculum that begins on synthetic and silver data and gradually shifts toward human-annotated examples. HydraQE outperforms cascaded text-based baselines and prior direct speech QE systems, demonstrating that end-to-end speech translation QE is competitive with cascaded approaches.</abstract>
<identifier type="citekey">krahn-fosler-lussier-2026-hydraqe</identifier>
<location>
<url>https://aclanthology.org/2026.iwslt-1.37/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>323</start>
<end>331</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HydraQE: OSU’s Submission for the IWSLT 2026 Speech Translation Metrics Shared Task
%A Krahn, Kevin
%A Fosler-Lussier, Eric
%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 krahn-fosler-lussier-2026-hydraqe
%X We present HydraQE, our contribution to the IWSLT 2026 Speech Translation Metrics shared task. HydraQE is an end-to-end, reference-free quality estimation (QE) system for speech translation built on a Qwen3-ASR backbone, which accepts source audio and a translation hypothesis as joint input. Hidden states from all backbone layers are combined via a sparsemax scalar mix, then re-encoded by a bidirectional Transformer for full cross-modal interaction. To address the scarcity of human-annotated speech translation data, three independent prediction heads are trained on complementary supervision signals: human direct assessment (DA) annotations, MetricX-24 pseudo-labels, and xCOMET pseudo-labels. We train on a combination of synthetically corrupted examples and silver pseudo-labeled machine translation outputs, using a curriculum that begins on synthetic and silver data and gradually shifts toward human-annotated examples. HydraQE outperforms cascaded text-based baselines and prior direct speech QE systems, demonstrating that end-to-end speech translation QE is competitive with cascaded approaches.
%U https://aclanthology.org/2026.iwslt-1.37/
%P 323-331
Markdown (Informal)
[HydraQE: OSU’s Submission for the IWSLT 2026 Speech Translation Metrics Shared Task](https://aclanthology.org/2026.iwslt-1.37/) (Krahn & Fosler-Lussier, IWSLT 2026)
ACL