Tie-Calibrated COMETKiwi for Speech Translation Quality Estimation: IWSLT2026 Metrics Track

Mubashir Hussain Shah, Aymen Fatima, Kiho Choi, Daehee Jang


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.
Anthology ID:
2026.iwslt-1.36
Volume:
Proceedings of the 23rd International Conference on Spoken Language Translation (IWSLT 2026)
Month:
July
Year:
2026
Address:
San Diego, USA (in-person and online)
Editors:
Elizabeth Salesky, Antonios Anastasopoulos, Matteo Negri, Marcello Federico
Venues:
IWSLT | WS
SIG:
SIGSLT
Publisher:
Association for Computational Linguistics
Note:
Pages:
318–322
Language:
URL:
https://aclanthology.org/2026.iwslt-1.36/
DOI:
Bibkey:
Cite (ACL):
Mubashir Hussain Shah, Aymen Fatima, Kiho Choi, and Daehee Jang. 2026. Tie-Calibrated COMETKiwi for Speech Translation Quality Estimation: IWSLT2026 Metrics Track. In Proceedings of the 23rd International Conference on Spoken Language Translation (IWSLT 2026), pages 318–322, San Diego, USA (in-person and online). Association for Computational Linguistics.
Cite (Informal):
Tie-Calibrated COMETKiwi for Speech Translation Quality Estimation: IWSLT2026 Metrics Track (Shah et al., IWSLT 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.iwslt-1.36.pdf