Elamur Research⌕
☰
home / papers / 2026 / MLLP-VRAIN UPV System for the IWSLT 2026 Simultaneous Speech Translation Task

MLLP-VRAIN UPV System for the IWSLT 2026 Simultaneous Speech Translation Task

Summary

The paper describes the MLLP-VRAIN (Universitat Politècnica de València) submission to the IWSLT 2026 Simultaneous Speech Translation track. The team built a cascaded system for long-form SimulST and entered every language direction and both latency regimes. For En→De, It and Zh they also entered the new context track. The ASR stage is Parakeet, used off the shelf and run in streaming mode with a sliding audio buffer and timestamp-based filtering of repeated output. The MT stage is a quantized Qwen 3.5 LLM. Both stages decide when to emit output through "black-box" policies that need no extra training. The authors test looser variants of Longest Common Prefix, including a new anchor-based Soft LCP (SLCP). For the context track, they add ASR word-boosting and retrieval of pre-translated example sentences. On MCIF En→De, XCOMET-XL rises by +5.82 over their 2025 system, and context adds a further +1.03. The paper also shows that macro-averaged YAAL can understate latency, which matters for evaluating streaming systems fairly.

Key points

  • ASR setup: nvidia/parakeet-tdt-0.6b-v3 was used without finetuning, with NeMo ALSD++ beam search (beam 32). Among LCP, LACP (Levenshtein τ=2) and SLCP, LACP was chosen for ASR. SLCP uses Ratcliff/Obershelp similarity with γ=3 and σ=0.6.
  • MT model choice: Qwen 3.5 was preferred over TranslateGemma, which handled prompt changes and inserted context poorly. The final system uses Qwen 3.5 27B in int4, fitting GPUs with 24GB or less. In preliminary MCIF tests it reached 91.09 XCOMET versus 86.85 for the 2025 UPV system.
  • Context track: domain context enters the ASR through phrase-boosting (with KeyBERT), while the MT retrieves example translations that were prepared offline, using a RAG approach.
  • Final results: YAAL Macro is about 1.9 s / 3.5 s on MCIF directions and 1.5 s / 2.8 s for Cs→En. XCOMET gains over organizer baselines are +13.5/+16.7/+3.0 at low latency and +7.6/+9.0/+2.3 at high latency (De/It/Zh).
  • Latency analysis: faulty inferences with negative delays distort macro-averaged YAAL. A micro average with oracle end offsets closely tracks the measured TrueLatency, and the paper also reports median and p99 latency.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages · Machine translation

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.iwslt-1.24

@inproceedings{iranzosanchez2026mllp,
  title = {{MLLP-VRAIN UPV System for the IWSLT 2026 Simultaneous Speech Translation Task}},
  author = {Iranzo-Sánchez, Jorge and Mas-Mollà, Gerard and Gimenez, Adrià and Saiz, Jorge Civera and Sanchis, Albert and Juan, Alfons},
  booktitle = {Proceedings of the 23rd International Conference on Spoken Language Translation (IWSLT 2026)},
  year = {2026},
  doi = {10.18653/v1/2026.iwslt-1.24},
  url = {https://doi.org/10.18653/v1/2026.iwslt-1.24}
}

References

67 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Idris Abdulmumin, Victor Agostinelli, Tanel Alumäe, Antonios Anastasopoulos, Luisa Bentivogli, Ondřej Bojar, Claudia Borg, Fethi Bougares, Roldano Cattoni, Mauro Cettolo, Lizhong Chen, William Chen, Raj Dabre, Yannick Estève, Marcello Federico, Mark Fishel, Marco Gaido, Dávid Javorský, Marek Kaszte… find
  2. David Ifeoluwa Adelani, Victor Agostinelli, Antonios Anastasopoulos, Luisa Bentivogli, Ondřej Bojar, Sebastien Bratières, Marine Carpuat, Roldano Cattoni, Mauro Cettolo, Lizhong Chen, Marcello Federico, Marco Gaido, Mahendra Gupta, HyoJung Han, Ali Hatami, David Javorský, Yejin Jeon, Marek Kaszteln… find
  3. Sweta Agrawal, Chunting Zhou, Mike Lewis, Luke Zettlemoyer, and Marjan Ghazvininejad. 2023. In-context examples selection for machine translation. In Findings of the Association for Computational Linguistics: ACL 2023, pages 8857–8873, Toronto, Canada. Association for Computational Linguistics. find our card
  4. Andrei Andrusenko, Vladimir Bataev, Lilit Grigoryan, Vitaly Lavrukhin, and Boris Ginsburg. 2025. Tur-bobias: Universal asr context-biasing powered by gpu-accelerated phrase-boosting tree. In 2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pages 1–7. find
  5. Naveen Arivazhagan, Colin Cherry, Te I, Wolfgang Macherey, Pallavi Baljekar, and George F. Foster. 2020a. Re-translation strategies for long form, simultaneous, spoken language translation. In 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2020, Barcelona, Spai… find
  6. Naveen Arivazhagan, Colin Cherry, Wolfgang Macherey, and George Foster. 2020b. Re-translation versus streaming for simultaneous translation. In Proceedings of the 17th International Conference on Spoken Language Translation, pages 220–227, Online. Association for Computational Linguistics. find
  7. Max Bain, Jaesung Huh, Tengda Han, and Andrew Zisserman. 2023. Whisperx: Time-accurate speech transcription of long-form audio. In 24th Annual Conference of the International Speech Communication Association, Interspeech 2023, Dublin, Ireland, August 20-24, 2023, pages 4489–4493. find
  8. Shanbo Cheng, Yu Bao, Zhichao Huang, Yu Lu, Ningxin Peng, Lu Xu, Runsheng Yu, Rong Cao, Yujiao Du, Ting Han, Yuxiang Hu, Zeyang Li, Sitong Liu, Shengtao Ma, Shiguang Pan, Jiongchen Xiao, Nuo Xu, Meng Yang, Rong Ye, and 9 others. 2025. Seed liveinterpret 2.0: End-to-end simultaneous speech-to-speech… — [arXiv:2507.17527](https://arxiv.org/abs/2507.17527) find
  9. Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. 2020. Unsupervised cross-lingual representation learning at scale. In Proceedings of the 58th Annual Meeting of the Association fo… find
  10. Marta R. Costa-jussà, James Cross, Onur Çelebi, Maha Elbayad, Kenneth Heafield, Kevin Heffernan, Elahe Kalbassi, Janice Lam, Daniel Licht, Jean Maillard, Anna Y. Sun, Skyler Wang, Guillaume Wenzek, Al Youngblood, Bapi Akula, Loïc Barrault, Gabriel Mejia Gonzalez, Prangthip Hansanti, John Hoffman, an… find
  11. Hiroyuki Deguchi, Yusuke Sakai, Hidetaka Kamigaito, and Taro Watanabe. 2024. mbrs: A library for minimum Bayes risk decoding. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 351–362, Miami, Florida, USA. Association for Computat… find
  12. M. A. del Agua, A. Giménez, N. Serrano, J. Andrés-Ferrer, J. Civera, A. Sanchis, and A. Juan. 2014. The translectures-upv toolkit. In Proc. of VIII Jornadas en Tecnología del Habla and IV Iberian SLTech Workshop (IberSpeech 2014), Las Palmas de Gran Canaria (Spain). find
  13. John DeNero, David Chiang, and Kevin Knight. 2009. Fast consensus decoding over translation forests. In Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP, pages 567–575, Suntec, Singapore.… find
  14. Bryan Eikema and Wilker Aziz. 2022. Sampling-based approximations to minimum Bayes risk decoding for neural machine translation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 10978–10993, Abu Dhabi, United Arab Emirates. Association for Computationa… find
  15. Mara Finkelstein, Isaac Caswell, Tobias Domhan, Jan-Thorsten Peter, Juraj Juraska, Parker Riley, Daniel Deutsch, Geza Kovacs, Cole Dilanni, Colin Cherry, Eleftheria Briakou, Elizabeth Nielsen, Jiaming Luo, Kat Black, Ryan Mullins, Sweta Agrawal, Wenda Xu, Erin Kats, Stephane Jaskiewicz, and 2 others… — [arXiv:2601.09012](https://arxiv.org/abs/2601.09012) find
  16. Markus Freitag, Behrooz Ghorbani, and Patrick Fernandes. 2023. Epsilon sampling rocks: Investigating sampling strategies for minimum Bayes risk decoding for machine translation. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 9198–9209, Singapore. Association for Comp… find
  17. Vaibhava Goel and William J. Byrne. 2000. Minimum bayes-risk automatic speech recognition. Comput. Speech Lang., 14(2):115–135. find
  18. Lilit Grigoryan, Vladimir Bataev, Andrei Andrusenko, Hainan Xu, Vitaly Lavrukhin, and Boris Ginsburg. 2025. Pushing the limits of beam search decoding for transducer-based ASR models. In 26th Annual Conference of the International Speech Communication Association, Interspeech 2025, Rotterdam, The Ne… find
  19. Maarten Grootendorst. 2020. Keybert: Minimal keyword extraction with bert. find
  20. Nuno Miguel Guerreiro, Ricardo Rei, Daan van Stigt, Luísa Coheur, Pierre Colombo, and André F. T. Martins. 2024. xcomet : Transparent machine translation evaluation through fine-grained error detection. Trans. Assoc. Comput. Linguistics, 12:979–995. find our card
  21. Shoutao Guo, Shaolei Zhang, Zhengrui Ma, Min Zhang, and Yang Feng. 2025. Agent-simt: Agent-assisted simultaneous translation with large language models. IEEE Transactions on Audio, Speech and Language Processing, 33:2074–2083. find
  22. John Hewitt, Christopher Manning, and Percy Liang. 2022. Truncation sampling as language model desmoothing. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 3414– 3427, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics. find
  23. Javier Iranzo-Sánchez, Jorge Iranzo-Sánchez, Adrià Giménez, Jorge Civera, and Alfons Juan. 2024. Segmentation-free streaming machine translation. Transactions of the Association for Computational Linguistics, 12:1104–1121. find
  24. Jorge Iranzo-Sánchez, Javier Iranzo-Sánchez, Adrià Giménez, and Jorge Civera. 2025a. Going beyond your expectations in latency metrics for simultaneous speech translation. In Findings of the Association for Computational Linguistics: ACL 2025, pages 18205–18228, Vienna, Austria. Association for Comp… find
  25. Jorge Iranzo-Sánchez, Javier Iranzo-Sanchez, Adrià Giménez Pastor, Jorge Civera Saiz, and Alfons Juan. 2025b. MLLP-VRAIN UPV system for the IWSLT 2025 simultaneous speech translation translation task. In Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025), pa… find
  26. Masoud Jalili Sabet, Philipp Dufter, François Yvon, and Hinrich Schütze. 2020. SimAlign: High quality word alignments without parallel training data using static and contextualized embeddings. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 1627–1643, Online. Associat… find
  27. Yuu Jinnai. 2025. Re-evaluating minimum bayes risk decoding for automatic speech recognition. CoRR, abs/2510.19471. — [arXiv:2510.19471](https://arxiv.org/abs/2510.19471) find
  28. Tom Kocmi, Ekaterina Artemova, Eleftherios Avramidis, Rachel Bawden, Ondřej Bojar, Konstantin Dranch, Anton Dvorkovich, Sergey Dukanov, Mark Fishel, Markus Freitag, Thamme Gowda, Roman Grundkiewicz, Barry Haddow, Marzena Karpinska, Philipp Koehn, Howard Lakougna, Jessica Lundin, Christof Monz, Kent… find our card
  29. Tom Kocmi, Eleftherios Avramidis, Rachel Bawden, Ondřej Bojar, Anton Dvorkovich, Christian Federmann, Mark Fishel, Markus Freitag, Thamme Gowda, Roman Grundkiewicz, Barry Haddow, Marzena Karpinska, Philipp Koehn, Benjamin Marie, Christof Monz, Kenton Murray, Masaaki Nagata, Martin Popel, Maja Popov… find our card
  30. Roman Koshkin, Katsuhito Sudoh, and Satoshi Nakamura. 2024a. LLMs are zero-shot context-aware simultaneous translators. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 1192–1207, Miami, Florida, USA. Association for Computational Linguistics. find
  31. Roman Koshkin, Katsuhito Sudoh, and Satoshi Nakamura. 2024b. TransLLaMa: LLM-based simultaneous translation system. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 461–476, Miami, Florida, USA. Association for Computational Linguistics. find
  32. Shankar Kumar and William Byrne. 2004. Minimum Bayes-risk decoding for statistical machine translation. In Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics: HLT-NAACL 2004, pages 169–176, Boston, Massachusetts, USA… find our card
  33. Daniil Larionov, Mikhail Seleznyov, Vasiliy Viskov, Alexander Panchenko, and Steffen Eger. 2024. xCOMET-lite: Bridging the gap between efficiency and quality in learned MT evaluation metrics. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 21934– 2194… find
  34. Xintong Li, Guanlin Li, Lemao Liu, Max Meng, and Shuming Shi. 2019. On the word alignment from neural machine translation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1293–1303, Florence, Italy. Association for Computational Linguistics. find
  35. Zhaolin Li, Yining Liu, Danni Liu, Tuan Nam Nguyen, Enes Yavuz Ugan, Tu Anh Dinh, Carlos Mullov, Alexander Waibel, and Jan Niehues. 2025. KIT’s low-resource speech translation systems for IWSLT2025: System enhancement with synthetic data and model regularization. In Proceedings of the 22nd Internati… find
  36. Danni Liu, Gerasimos Spanakis, and Jan Niehues. 2020a. Low-latency sequence-to-sequence speech recognition and translation by partial hypothesis selection. In 21st Annual Conference of the International Speech Communication Association, Interspeech 2020, Virtual Event, Shanghai, China, October 25-29… find
  37. Danni Liu, Gerasimos Spanakis, and Jan Niehues. 2020b. Low-Latency Sequence-to-Sequence Speech Recognition and Translation by Partial Hypothesis Selection. In Interspeech 2020, pages 3620–3624. find
  38. Jiaxuan Luo, Siqi Ouyang, and Lei Li. 2026. Rasst: Fast cross-modal retrieval-augmented simultaneous speech translation. Preprint, arXiv:2601.22777. — [arXiv:2601.22777](https://arxiv.org/abs/2601.22777) find
  39. Xing Han Lù. 2024. Bm25s: Orders of magnitude faster lexical search via eager sparse scoring. Preprint, arXiv:2407.03618. — [arXiv:2407.03618](https://arxiv.org/abs/2407.03618) find
  40. Mingbo Ma, Liang Huang, Hao Xiong, Renjie Zheng, Kaibo Liu, Baigong Zheng, Chuanqiang Zhang, Zhongjun He, Hairong Liu, Xing Li, Hua Wu, and Haifeng Wang. 2019. STACL: Simultaneous translation with implicit anticipation and controllable latency using prefix-to-prefix framework. In Proceedings of the… find our card
  41. Dominik Macháček, Ondřej Bojar, and Raj Dabre. 2023. MT metrics correlate with human ratings of simultaneous speech translation. In Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023), pages 169–179, Toronto, Canada (in-person and online). Association for C… find
  42. Dominik Macháček and Peter Polák. 2025. Simultaneous translation with offline speech and LLM models in CUNI submission to IWSLT 2025. In Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025), pages 389–398, Vienna, Austria (in-person and online). Association f… find
  43. Zhuoyuan Mao and Yen Yu. 2024. Tuning LLMs with contrastive alignment instructions for machine translation in unseen, low-resource languages. In Proceedings of the Seventh Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2024), pages 1–25, Bangkok, Thailand. Associ… find
  44. Gerard Mas-Mollà, Albert Sanchis, and Alfons Juan. Improving streaming ASR with foundation models using emission policies. Submitted to Interspeech 2026. find
  45. Kenton Murray and David Chiang. 2018. Correcting length bias in neural machine translation. In Proceedings of the Third Conference on Machine Translation: Research Papers, pages 212–223, Brussels, Belgium. Association for Computational Linguistics. find
  46. Sara Papi, Javier Garcia Gilabert, Zachary Hopton, Vilém Zouhar, Carlos Escolano, Gerard I. Gállego, Jorge Iranzo-Sánchez, Ahrii Kim, Dominik Macháček, Patricia Schmidtova, and Maike Züfle. 2025. Hearing to translate: The effectiveness of speech modality integration into llms. Preprint, arXiv:2512.… find
  47. Sara Papi, Maike Züfle, Marco Gaido, Beatrice Savoldi, Danni Liu, Ioannis Douros, Luisa Bentivogli, and Jan Niehues. 2026. MCIF: Multimodal crosslingual instruction-following benchmark from scientific talks. In The Fourteenth International Conference on Learning Representations. find
  48. Peter Polák, Danni Liu, Ngoc-Quan Pham, Jan Niehues, Alexander Waibel, and Ondřej Bojar. 2023. Towards efficient simultaneous speech translation: CUNI-KIT system for simultaneous track at IWSLT 2023. In Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023), pa… find
  49. Peter Polák, Ngoc-Quan Pham, Tuan Nam Nguyen, Danni Liu, Carlos Mullov, Jan Niehues, Ondřej Bojar, and Alexander Waibel. 2022. CUNI-KIT system for simultaneous speech translation task at IWSLT 2022. In Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022), pag… find
  50. Peter Polák, Sara Papi, Luisa Bentivogli, and Ondřej Bojar. 2026. Better late than never: Meta-evaluation of latency metrics for simultaneous speech-to-text translation. Preprint, arXiv:2509.17349. find
  51. Maja Popović. 2015. chrF: character n-gram F-score for automatic MT evaluation. In Proceedings of the Tenth Workshop on Statistical Machine Translation, pages 392–395, Lisbon, Portugal. Association for Computational Linguistics. find our card
  52. Maja Popović. 2017. chrF++: words helping character n-grams. In Proceedings of the Second Conference on Machine Translation, pages 612–618, Copenhagen, Denmark. Association for Computational Linguistics. find our card
  53. Matt Post. 2018. A call for clarity in reporting BLEU scores. In Proceedings of the Third Conference on Machine Translation: Research Papers, pages 186– 191, Brussels, Belgium. Association for Computational Linguistics. find our card
  54. Qwen Team. 2026. Qwen3.5: Towards native multimodal agents. find
  55. Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. 2023. Robust speech recognition via large-scale weak supervision. In International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA, pages 28492–28518. find our card
  56. Matthew Raffel, Victor Agostinelli, and Lizhong Chen. 2024. Simultaneous masking, not prompting optimization: A paradigm shift in fine-tuning LLMs for simultaneous translation. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 18302–18314, Miami, Florid… find
  57. Miguel Moura Ramos, Duarte M. Alves, Hippolyte Gisserot-Boukhlef, João Alves, Pedro Henrique Martins, Patrick Fernandes, José Pombal, Nuno M. Guerreiro, Ricardo Rei, Nicolas Boizard, Amin Farajian, Mateusz Klimaszewski, José G. C. de Souza, Barry Haddow, François Yvon, Pierre Colombo, Alexandra Birc… — [arXiv:2602.05879](https://arxiv.org/abs/2602.05879) find
  58. John W Ratcliff, David E Metzener, and 1 others. 1988. Pattern matching: The gestalt approach. Dr. Dobb’s Journal, 13(7):46. find
  59. Ricardo Rei, Nuno Miguel Guerreiro, José Pombal, João Alves, Pedro Teixeirinha, M. Amin Farajian, and André F. T. Martins. 2025. Tower+: Bridging generality and translation specialization in multilingual llms. CoRR, abs/2506.17080. find
  60. Monica Sekoyan, Nithin Rao Koluguri, Nune Tade-vosyan, Piotr Zelasko, Travis Bartley, Nikolay Karpov, Jagadeesh Balam, and Boris Ginsburg. 2025. Canary-1b-v2 & parakeet-tdt-0.6b-v3: Efficient and high-performance models for multilingual asr and ast. Preprint, arXiv:2509.14128. — [arXiv:2509.14128](https://arxiv.org/abs/2509.14128) find
  61. Vaibhav Srivastav, Steven Zheng, Eric Bezzam, Eustache Le Bihan, Nithin Koluguri, Piotr Żelasko, Somshubra Majumdar, Adel Moumen, and Sanchit Gandhi. 2026. Open asr leaderboard: Towards reproducible and transparent multilingual and long-form speech recognition evaluation. Preprint, arXiv:2510.06961… — [arXiv:2510.06961](https://arxiv.org/abs/2510.06961) find
  62. Jannis Vamvas and Rico Sennrich. 2024. Linear-time minimum Bayes risk decoding with reference aggregation. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 790–801, Bangkok, Thailand. Association for Computational Linguistics. find
  63. Francesco Verdini, Pierfrancesco Melucci, Stefano Perna, Francesco Cariaggi, Marco Gaido, Sara Papi, Szymon Mazurek, Marek Kasztelnik, Luisa Bentivogli, Sebastien Bratières, Paolo Merialdo, and Simone Scardapane. 2025. How to Connect Speech Foundation Models and Large Language Models? What Matters a… find
  64. Wenxuan Wang, Yingxin Zhang, Yifan Jin, Binbin Du, and Yuke Li. 2025. NYA’s offline speech translation system for IWSLT 2025. In Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025), pages 206–211, Vienna, Austria (in-person and online). Association for Comput… find
  65. Yilin Yang, Liang Huang, and Mingbo Ma. 2018. Breaking the beam search curse: A study of (re-)scoring methods and stopping criteria for neural machine translation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3054–3059, Brussels, Belgium. Associati… find
  66. Mao Zheng, Zheng Li, Tao Chen, Mingyang Song, and Di Wang. 2025. Hy-mt1.5 technical report. Preprint, arXiv:2512.24092. — [arXiv:2512.24092](https://arxiv.org/abs/2512.24092) find
  67. Vilém Zouhar, Maike Züfle, Beni Egressy, Julius Cheng, Mrinmaya Sachan, and Jan Niehues. 2026. Early-exit and instant confidence translation quality estimation. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pag… find our card

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/papers/sanchez-2026-mllp-vrain-upv-system-iwslt/