# MLLP-VRAIN UPV system for the IWSLT 2025 Simultaneous Speech Translation Translation task

arXiv: https://arxiv.org/abs/2506.18828 · HTML: https://mlsanity.com/paper/2506.18828/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 26 references that are in the map.
- First posted on arXiv 23 Jun 2025.

## Builds on (most cited first, 17 of 17)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [8-bit Optimizers via Block-wise Quantization](https://mlsanity.com/paper/2110.02861/) (2021)
- [MADLAD-400: A Multilingual And Document-Level Large Audited Dataset](https://mlsanity.com/paper/2309.04662/) (2023)
- [DoRA: Enhancing Parameter-Efficient Fine-Tuning with Dynamic Rank Distribution](https://mlsanity.com/paper/2405.17357/) (2024)
- [Low-Latency Neural Speech Translation](https://mlsanity.com/paper/1808.00491/) (2018)
- [AlignAtt: Using Attention-based Audio-Translation Alignments as a Guide for Simultaneous Speech Translation](https://mlsanity.com/paper/2305.11408/) (2023)
- [Turning Whisper into Real-Time Transcription System](https://mlsanity.com/paper/2307.14743/) (2023)
- [Does Simultaneous Speech Translation need Simultaneous Models?](https://mlsanity.com/paper/2204.03783/) (2022)
- [StreamAtt: Direct Streaming Speech-to-Text Translation with Attention-based Audio History Selection](https://mlsanity.com/paper/2406.06097/) (2024)
- [From Simultaneous to Streaming Machine Translation by Leveraging Streaming History](https://mlsanity.com/paper/2203.02459/) (2022)
- [Simultaneous Machine Translation with Large Language Models](https://mlsanity.com/paper/2309.06706/) (2023)
- [InfiniSST: Simultaneous Translation of Unbounded Speech with Large Language Model](https://mlsanity.com/paper/2503.02969/) (2025)
- [Simultaneous Translation for Unsegmented Input: A Sliding Window Approach](https://mlsanity.com/paper/2210.09754/) (2022)
- [Recovering document annotations for sentence-level bitext](https://mlsanity.com/paper/2406.03869/) (2024)
- [Does Joint Training Really Help Cascaded Speech Translation?](https://mlsanity.com/paper/2210.13700/) (2022)
- [Word Order in English-Japanese Simultaneous Interpretation: Analyses and Evaluation using Chunk-wise Monotonic Translation](https://mlsanity.com/paper/2406.08940/) (2024)

## Built on by (most cited first, 2 of 2)

- [Streaming Translation and Transcription Through Speech-to-Text Causal Alignment](https://mlsanity.com/paper/2603.11578/) (2026)
- [MLLP-VRAIN UPV system for the IWSLT 2026 Simultaneous Speech Translation task](https://mlsanity.com/paper/2606.17255/) (2026)

## Abstract (arXiv)

This work describes the participation of the MLLP-VRAIN research group in the shared task of the IWSLT 2025 Simultaneous Speech Translation track. Our submission addresses the unique challenges of real-time translation of long-form speech by developing a modular cascade system that adapts strong pre-trained models to streaming scenarios. We combine Whisper Large-V3-Turbo for ASR with the multilingual NLLB-3.3B model for MT, implementing lightweight adaptation techniques rather than training new end-to-end models from scratch. Our approach employs document-level adaptation with prefix training to enhance the MT model's ability to handle incomplete inputs, while incorporating adaptive emission policies including a wait-k strategy and RALCP for managing the translation stream. Specialized buffer management techniques and segmentation strategies ensure coherent translations across long audio sequences. Experimental results on the ACL60/60 dataset demonstrate that our system achieves a favorable balance between translation quality and latency, with a BLEU score of 31.96 and non-computational-aware StreamLAAL latency of 2.94 seconds. Our final model achieves a preliminary score on the official test set (IWSLT25Instruct) of 29.8 BLEU. Our work demonstrates that carefully adapted pre-trained components can create effective simultaneous translation systems for long-form content without requiring extensive in-domain parallel data or specialized end-to-end training.