mlsanityData to 7 Oct 2026

MLLP-VRAIN UPV system for the IWSLT 2026 Simultaneous Speech Translation task

arXiv 2606.17255 ↗First posted 15 Jun 2026cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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 EnrightarrowDe, 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 EnrightarrowDe test set shows a substantial quality improvement of +5.82 XCOMET-XL. Our context track processing further improves performance by +1.03.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 33 of its 63 references that are in the map. First posted on arXiv 15 Jun 2026.

Builds on

33 of 63 references.

References · 33

  1. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  2. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  3. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  4. 2023WhisperX: Time-Accurate Speech Transcription of Long-Form Audiocited by 320
  5. 2023xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detectioncited by 260
  6. 2022In-context Examples Selection for Machine Translationcited by 172
  7. 2020SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddingscited by 155
  8. 2022Truncation Sampling as Language Model Desmoothingcited by 121
  9. 2018Correcting Length Bias in Neural Machine Translationcited by 119
  10. 2024BM25S: Orders of magnitude faster lexical search via eager sparse scoringcited by 87
  11. 2023Epsilon Sampling Rocks: Investigating Sampling Strategies for Minimum Bayes Risk Decoding for Machine Translationcited by 57
  12. 2025Canary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and ASTcited by 51
21 more
  1. 2020Low-Latency Sequence-to-Sequence Speech Recognition and Translation by Partial Hypothesis Selectioncited by 47
  2. 2025Tower+: Bridging Generality and Translation Specialization in Multilingual LLMscited by 40
  3. 2024TransLLaMa: LLM-based Simultaneous Translation Systemcited by 34
  4. 2022CUNI-KIT System for Simultaneous Speech Translation Task at IWSLT 2022cited by 30
  5. 2019Re-Translation Strategies For Long Form, Simultaneous, Spoken Language Translationcited by 24
  6. 2024Linear-time Minimum Bayes Risk Decoding with Reference Aggregationcited by 21
  7. 2025Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluationcited by 21
  8. 2025MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talkscited by 14
  9. 2024mbrs: A Library for Minimum Bayes Risk Decodingcited by 13
  10. 2024Simultaneous Masking, Not Prompting Optimization: A Paradigm Shift in Fine-tuning LLMs for Simultaneous Translationcited by 11
  11. 2024LLMs Are Zero-Shot Context-Aware Simultaneous Translatorscited by 10
  12. 2022MT Metrics Correlate with Human Ratings of Simultaneous Speech Translationcited by 9
  13. 2024xCOMET-lite: Bridging the Gap Between Efficiency and Quality in Learned MT Evaluation Metricscited by 7
  14. 2025Simultaneous Translation with Offline Speech and LLM Models in CUNI Submission to IWSLT 2025cited by 7
  15. 2025Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMscited by 6
  16. 2025Pushing the Limits of Beam Search Decoding for Transducer-based ASR modelscited by 4
  17. 2025TurboBias: Universal ASR Context-Biasing powered by GPU-accelerated Phrase-Boosting Treecited by 4
  18. 2025Better Late Than Never: Meta-Evaluation of Latency Metrics for Simultaneous Speech-to-Text Translationcited by 4
  19. 2025KIT's Low-resource Speech Translation Systems for IWSLT2025: System Enhancement with Synthetic Data and Model Regularizationcited by 3
  20. 2025MLLP-VRAIN UPV system for the IWSLT 2025 Simultaneous Speech Translation Translation taskcited by 2
  21. 2025Re-evaluating Minimum Bayes Risk Decoding for Automatic Speech Recognitioncited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026AlignAtt4LLM: Fast AlignAtt for Decoder-Only LLMs at IWSLT 2026 Simultaneous Speech Translation Task
  2. 2025HITSZ's End-To-End Speech Translation Systems Combining Sequence-to-Sequence Auto Speech Recognition Model and Indic Large Language Model for IWSLT 2025 in Indic Track
  3. 2022The NPU-ASLP System for The ISCSLP 2022 Magichub Code-Swiching ASR Challenge
  4. 2025SimulMEGA: MoE Routers are Advanced Policy Makers for Simultaneous Speech Translation
  5. 2026Simultaneous Speech-to-Speech Translation Without Aligned Data
  6. 2026Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey
  7. 2025Novel Parasitic Dual-Scale Modeling for Efficient and Accurate Multilingual Speech Translation
  8. 2025MCAT: Scaling Many-to-Many Speech-to-Text Translation with MLLMs to 70 Languages