mlsanityData to 14 Oct 2026

Simultaneous Translation with Offline Speech and LLM Models in CUNI Submission to IWSLT 2025

arXiv 2506.17077 ↗First posted 20 Jun 2025cs.CLcited by 8

Not on the map. Why?

Abstract (arXiv)

This paper describes Charles University submission to the Simultaneous Speech Translation Task of the IWSLT 2025. We cover all four language pairs with a direct or cascade approach. The backbone of our systems is the offline Whisper speech model, which we use for both translation and transcription in simultaneous mode with the state-of-the-art simultaneous policy AlignAtt. We further improve the performance by prompting to inject in-domain terminology, and we accommodate context. Our cascaded systems further use EuroLLM for unbounded simultaneous translation. Compared to the Organizers' baseline, our systems improve by 2 BLEU points on Czech to English and 13-22 BLEU points on English to German, Chinese and Japanese on the development sets. Additionally, we also propose a new enhanced measure of speech recognition latency.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 9 of its 16 references that are in the map. First posted on arXiv 20 Jun 2025.

Builds on

9 of 16 references.

References · 9

  1. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  2. 2020Beyond English-Centric Multilingual Machine Translationcited by 561
  3. 2024EuroLLM: Multilingual Language Models for Europecited by 106
  4. 2023AlignAtt: Using Attention-based Audio-Translation Alignments as a Guide for Simultaneous Speech Translationcited by 35
  5. 2022CUNI-KIT System for Simultaneous Speech Translation Task at IWSLT 2022cited by 30
  6. 2023Turning Whisper into Real-Time Transcription Systemcited by 24
  7. 2024StreamAtt: Direct Streaming Speech-to-Text Translation with Attention-based Audio History Selectioncited by 19
  8. 2024How "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?cited by 17
  9. 2022MT Metrics Correlate with Human Ratings of Simultaneous Speech Translationcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 8.

8 papers.

  1. 2026Streaming Translation and Transcription Through Speech-to-Text Causal Alignmentcited by 1
  2. 2026SimulU: Training-free Policy for Long-form Simultaneous Speech-to-Speech Translationcited by 0
  3. 2026A Pocket Offline Model for Simultaneous Speech Translation as CUNI Submission to IWSLT 2026cited by 0
  4. 2026AlignAtt4LLM: Fast AlignAtt for Decoder-Only LLMs at IWSLT 2026 Simultaneous Speech Translation Taskcited by 0
  5. 2026Automatic Labelling of Speech Translation Errorscited by 0
  6. 2026MLLP-VRAIN UPV system for the IWSLT 2026 Simultaneous Speech Translation taskcited by 0
  7. 2026Decoupling Turn-Taking from Semantics: A Decoupled Data Approach for Finite-State-Machine-Based Full-Duplex Dialoguecited by 0
  8. 2026Estimating Surprisal from the Speech Signalcited by 0