# Automatic Labelling of Speech Translation Errors

arXiv: https://arxiv.org/abs/2606.06047 · HTML: https://mlsanity.com/paper/2606.06047/

## 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 (most cited first, 13 of 13)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detection](https://mlsanity.com/paper/2310.10482/) (2023)
- [Word Alignment by Fine-tuning Embeddings on Parallel Corpora](https://mlsanity.com/paper/2101.08231/) (2021)
- [Error Span Annotation: A Balanced Approach for Human Evaluation of Machine Translation](https://mlsanity.com/paper/2406.11580/) (2024)
- [Tower+: Bridging Generality and Translation Specialization in Multilingual LLMs](https://mlsanity.com/paper/2506.17080/) (2025)
- [AI-Assisted Human Evaluation of Machine Translation](https://mlsanity.com/paper/2406.12419/) (2024)
- [BLASER: A Text-Free Speech-to-Speech Translation Evaluation Metric](https://mlsanity.com/paper/2212.08486/) (2022)
- [SpeechQE: Estimating the Quality of Direct Speech Translation](https://mlsanity.com/paper/2410.21485/) (2024)
- [MT Metrics Correlate with Human Ratings of Simultaneous Speech Translation](https://mlsanity.com/paper/2211.08633/) (2022)
- [Towards the evaluation of automatic simultaneous speech translation from a communicative perspective](https://mlsanity.com/paper/2103.08364/) (2021)
- [Simultaneous Translation with Offline Speech and LLM Models in CUNI Submission to IWSLT 2025](https://mlsanity.com/paper/2506.17077/) (2025)
- [Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs](https://mlsanity.com/paper/2512.16378/) (2025)
- [How to Evaluate Speech Translation with Source-Aware Neural MT Metrics](https://mlsanity.com/paper/2511.03295/) (2025)

## 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.