@inproceedings{shah-etal-2026-tie,
title = "Tie-Calibrated {COMETK}iwi for Speech Translation Quality Estimation: {IWSLT}2026 Metrics Track",
author = "Shah, Mubashir Hussain and
Fatima, Aymen and
Choi, Kiho and
Jang, Daehee",
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-1.36/",
pages = "318--322",
ISBN = "979-8-89176-411-8",
abstract = "We describe our submission to the IWSLT 2026 Speech Translation Metrics shared task, which targets reference-free quality estimation for English-to-German and English-to-Chinese speech translation. Our primary system combines COMETKiwi-22, applied to ASR transcripts, with a lightweight post-processing step called tie calibration: a learned score-bucketing that collapses near-identical scores into exact ties, reducing noisy within-document pairwise ranking errors. On the official development set the method achieves a segment-level Kendall tau-b of 39.4{\%} on average, compared to 34.6{\%} for plain COMETKiwi, 29.2{\%} for SpeechQE, and 24.4{\%} for BLASER 2.0 QE. System-level Soft Pairwise Accuracy is 88.0{\%}, comparable to COMETKiwi (89.4{\%}) and above SpeechQE (86.0{\%}). The method requires no audio, no retraining, and one hyperparameter per target language tuned entirely on the training split."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shah-etal-2026-tie">
<titleInfo>
<title>Tie-Calibrated COMETKiwi for Speech Translation Quality Estimation: IWSLT2026 Metrics Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mubashir</namePart>
<namePart type="given">Hussain</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aymen</namePart>
<namePart type="family">Fatima</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kiho</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daehee</namePart>
<namePart type="family">Jang</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 describe our submission to the IWSLT 2026 Speech Translation Metrics shared task, which targets reference-free quality estimation for English-to-German and English-to-Chinese speech translation. Our primary system combines COMETKiwi-22, applied to ASR transcripts, with a lightweight post-processing step called tie calibration: a learned score-bucketing that collapses near-identical scores into exact ties, reducing noisy within-document pairwise ranking errors. On the official development set the method achieves a segment-level Kendall tau-b of 39.4% on average, compared to 34.6% for plain COMETKiwi, 29.2% for SpeechQE, and 24.4% for BLASER 2.0 QE. System-level Soft Pairwise Accuracy is 88.0%, comparable to COMETKiwi (89.4%) and above SpeechQE (86.0%). The method requires no audio, no retraining, and one hyperparameter per target language tuned entirely on the training split.</abstract>
<identifier type="citekey">shah-etal-2026-tie</identifier>
<location>
<url>https://aclanthology.org/2026.iwslt-1.36/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>318</start>
<end>322</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Tie-Calibrated COMETKiwi for Speech Translation Quality Estimation: IWSLT2026 Metrics Track
%A Shah, Mubashir Hussain
%A Fatima, Aymen
%A Choi, Kiho
%A Jang, Daehee
%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 shah-etal-2026-tie
%X We describe our submission to the IWSLT 2026 Speech Translation Metrics shared task, which targets reference-free quality estimation for English-to-German and English-to-Chinese speech translation. Our primary system combines COMETKiwi-22, applied to ASR transcripts, with a lightweight post-processing step called tie calibration: a learned score-bucketing that collapses near-identical scores into exact ties, reducing noisy within-document pairwise ranking errors. On the official development set the method achieves a segment-level Kendall tau-b of 39.4% on average, compared to 34.6% for plain COMETKiwi, 29.2% for SpeechQE, and 24.4% for BLASER 2.0 QE. System-level Soft Pairwise Accuracy is 88.0%, comparable to COMETKiwi (89.4%) and above SpeechQE (86.0%). The method requires no audio, no retraining, and one hyperparameter per target language tuned entirely on the training split.
%U https://aclanthology.org/2026.iwslt-1.36/
%P 318-322
Markdown (Informal)
[Tie-Calibrated COMETKiwi for Speech Translation Quality Estimation: IWSLT2026 Metrics Track](https://aclanthology.org/2026.iwslt-1.36/) (Shah et al., IWSLT 2026)
ACL