Salvato in:
Dettagli Bibliografici
Autori principali: Iranzo-Sánchez, Jorge, Iranzo-Sánchez, Javier, Giménez, Adrià, Civera, Jorge, Juan, Alfons
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2506.18828
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912445075816448
author Iranzo-Sánchez, Jorge
Iranzo-Sánchez, Javier
Giménez, Adrià
Civera, Jorge
Juan, Alfons
author_facet Iranzo-Sánchez, Jorge
Iranzo-Sánchez, Javier
Giménez, Adrià
Civera, Jorge
Juan, Alfons
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_18828
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MLLP-VRAIN UPV system for the IWSLT 2025 Simultaneous Speech Translation Translation task
Iranzo-Sánchez, Jorge
Iranzo-Sánchez, Javier
Giménez, Adrià
Civera, Jorge
Juan, Alfons
Computation and Language
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.
title MLLP-VRAIN UPV system for the IWSLT 2025 Simultaneous Speech Translation Translation task
topic Computation and Language
url https://arxiv.org/abs/2506.18828