MLLP-VRAIN UPV system for the IWSLT 2026 Simultaneous Speech Translation task
This work provides an incremental improvement in simultaneous speech translation for multiple language directions, with a focus on quality-latency trade-offs and context integration.
The MLLP-VRAIN group participated in the IWSLT 2026 Simultaneous Speech Translation task, using Parakeet and Qwen 3.5 models in a cascaded system with adaptive policies. They achieved a +5.82 XCOMET-XL improvement over last year on the MCIF En→De test set, with an additional +1.03 gain from context-aware processing.
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$\rightarrow${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$\rightarrow$De test set shows a substantial quality improvement of +5.82 XCOMET-XL. Our context track processing further improves performance by +1.03.