MLLP-VRAIN UPV System for the IWSLT 2026 Simultaneous Speech Translation Task

Jorge Iranzo-Sánchez, Gerard Mas-Mollà, Adrià Gimenez, Jorge Civera Saiz, Albert Sanchis, Alfons Juan


Abstract
This work describes the participation of the MLLP-VRAIN research group in the shared task of the IWSLT 2026 Simultaneous Speech Translation track. Our submission utilizes the recently released Parakeet and Qwen 3.5 models to create a robust, cascaded solution for long-form SimulST through the use of adaptive black-box policies. We explore relaxations of these policies to achieve better quality-latency trade-offs. Compared to last year, we participate on all language directions. In addition to this, for the En→De, It, Zh directions we also participate in this year’s new context track employing a combination of ASR word-boosting and a RAG mechanism of offline pre-translated exemplars to guide generation and enrich our system with domain-specific context. Finally, we provide a detailed latency analysis of our system. Compared to last year, results on the MCIF En→De test set shows a substantial quality improvement of +5.82 XCOMET-XL. Our context track processing further improves performance by +1.03.
Anthology ID:
2026.iwslt-1.24
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:
212–226
Language:
URL:
https://aclanthology.org/2026.iwslt-1.24/
DOI:
Bibkey:
Cite (ACL):
Jorge Iranzo-Sánchez, Gerard Mas-Mollà, Adrià Gimenez, Jorge Civera Saiz, Albert Sanchis, and Alfons Juan. 2026. MLLP-VRAIN UPV System for the IWSLT 2026 Simultaneous Speech Translation Task. In Proceedings of the 23rd International Conference on Spoken Language Translation (IWSLT 2026), pages 212–226, San Diego, USA (in-person and online). Association for Computational Linguistics.
Cite (Informal):
MLLP-VRAIN UPV System for the IWSLT 2026 Simultaneous Speech Translation Task (Iranzo-Sánchez et al., IWSLT 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.iwslt-1.24.pdf