基于黑盒策略的双模型系统，实现长文本实时翻译质量提升。
MLLP-VRAIN UPV system for the IWSLT 2026 Simultaneous Speech Translation task
- 采用自适应黑盒策略构建级联翻译框架
- 在英德语测试集上提升5.82分XCOMET-XL指标
- 新增上下文追踪机制，适合领域定制场景
本文介绍MLLP-VRAIN研究团队在IWSLT 2026同步语音翻译任务中的参与情况。我们利用最新发布的Parakeet与Qwen 3.5模型，通过自适应‘黑盒’策略构建稳健的级联式长文本同步语音翻译系统。探索了策略松弛以优化质量与延迟的权衡。相比去年，今年覆盖全部语言方向。针对英→德、意、中方向，还参与了新设的上下文追踪赛道，结合ASR词增强与离线预译样例的RAG机制引导生成，融入领域上下文信息。最后提供了系统的详细延迟分析。相较于去年，MCIF En→De测试集上质量提升+5.82 XCOMET-XL；上下文处理进一步带来+1.03的性能增益。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。