mlsanityData to 14 Oct 2026

Automatic Labelling of Speech Translation Errors

arXiv 2606.06047 ↗First posted 4 Jun 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Errors in speech translations reduce trustworthiness of Speech Translation (ST) systems and can have serious consequences. Yet currently there is no established methodology for evaluating confidence and quality estimation of speech translations. To initiate progress in this direction, we propose Speech Translation Error Labelling (STEL). We create an annotation protocol, a small authentic end-to-end evaluation dataset, and we analyse how existing text-only and speech-processing systems perform the STEL task. Our results show that text-only XCOMET and multimodal LLM Qwen2.5-Omni are able to perform the STEL task in roughly half the precision of humans. We also find that direct speech processing is necessary for the STEL task, and that the current text-only and speech-processing systems are complementary in labelling translation-only vs. speech-processing errors in ST.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 13 of its 26 references that are in the map. First posted on arXiv 4 Jun 2026.

Builds on

13 of 26 references.

References · 13

  1. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  2. 2023xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detectioncited by 265
  3. 2021Word Alignment by Fine-tuning Embeddings on Parallel Corporacited by 186
  4. 2024Error Span Annotation: A Balanced Approach for Human Evaluation of Machine Translationcited by 62
  5. 2025Tower+: Bridging Generality and Translation Specialization in Multilingual LLMscited by 40
  6. 2024AI-Assisted Human Evaluation of Machine Translationcited by 20
  7. 2022BLASER: A Text-Free Speech-to-Speech Translation Evaluation Metriccited by 16
  8. 2024SpeechQE: Estimating the Quality of Direct Speech Translationcited by 10
  9. 2022MT Metrics Correlate with Human Ratings of Simultaneous Speech Translationcited by 9
  10. 2021Towards the evaluation of automatic simultaneous speech translation from a communicative perspectivecited by 8
  11. 2025Simultaneous Translation with Offline Speech and LLM Models in CUNI Submission to IWSLT 2025cited by 8
  12. 2025Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMscited by 7
1 more
  1. 2025How to Evaluate Speech Translation with Source-Aware Neural MT Metricscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026EviSI: An Evidence-Based Evaluation Agent for Simultaneous Interpreting
  2. 2023Recent Advances in Direct Speech-to-text Translation
  3. 2026Rethinking Human-Aligned Evaluation: An Analysis of Semantic Metrics Beyond WER
  4. 2025TranslationCorrect: A Unified Framework for Machine Translation Post-Editing with Predictive Error Assistance
  5. 2022SpeechMatrix: A Large-Scale Mined Corpus of Multilingual Speech-to-Speech Translations
  6. 2026Text Scores Do Not Establish Performance on Lexically Non-Diagnostic Speech Tasks: A Qwen2-Audio Quantization Case Study
  7. 2025The Uneven Impact of Post-Training Quantization in Machine Translation
  8. 2026Breaking the Curse of Multilinguality in Many-to-Many Speech-to-Text Translation via a Resource-Aware Mixture of Speech Encoders