# Average Token Delay: A Latency Metric for Simultaneous Translation

arXiv: https://arxiv.org/abs/2211.13173 · HTML: https://mlsanity.com/paper/2211.13173/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 12 references that are in the map.
- First posted on arXiv 22 Nov 2022.

## Builds on (most cited first, 7 of 7)

- [Monotonic Infinite Lookback Attention for Simultaneous Machine Translation](https://mlsanity.com/paper/1906.05218/) (2019)
- [Learning to Translate in Real-time with Neural Machine Translation](https://mlsanity.com/paper/1610.00388/) (2016)
- [SimulEval: An Evaluation Toolkit for Simultaneous Translation](https://mlsanity.com/paper/2007.16193/) (2020)
- [Can neural machine translation do simultaneous translation?](https://mlsanity.com/paper/1606.02012/) (2016)
- [Over-Generation Cannot Be Rewarded: Length-Adaptive Average Lagging for Simultaneous Speech Translation](https://mlsanity.com/paper/2206.05807/) (2022)
- [Stream-level Latency Evaluation for Simultaneous Machine Translation](https://mlsanity.com/paper/2104.08817/) (2021)
- [Simultaneous Neural Machine Translation with Constituent Label Prediction](https://mlsanity.com/paper/2110.13480/) (2021)

## Built on by (most cited first, 15 of 15)

- [StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning](https://mlsanity.com/paper/2406.03049/) (2024)
- [How "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?](https://mlsanity.com/paper/2412.18495/) (2024)
- [Tagged End-to-End Simultaneous Speech Translation Training using Simultaneous Interpretation Data](https://mlsanity.com/paper/2306.08582/) (2023)
- [Direct Models for Simultaneous Translation and Automatic Subtitling: FBK@IWSLT2023](https://mlsanity.com/paper/2309.15554/) (2023)
- [Recent Advances in End-to-End Simultaneous Speech Translation](https://mlsanity.com/paper/2406.00497/) (2024)
- [Better Late Than Never: Meta-Evaluation of Latency Metrics for Simultaneous Speech-to-Text Translation](https://mlsanity.com/paper/2509.17349/) (2025)
- [Simultaneous Interpretation Corpus Construction by Large Language Models in Distant Language Pair](https://mlsanity.com/paper/2404.12299/) (2024)
- [SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translation](https://mlsanity.com/paper/2504.15509/) (2025)
- [Average Token Delay: A Duration-aware Latency Metric for Simultaneous Translation](https://mlsanity.com/paper/2311.14353/) (2023)
- [Chunk Based Speech Pre-training with High Resolution Finite Scalar Quantization](https://mlsanity.com/paper/2509.15579/) (2025)
- [SimulSeamless: FBK at IWSLT 2024 Simultaneous Speech Translation](https://mlsanity.com/paper/2406.14177/) (2024)
- [Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategies](https://mlsanity.com/paper/2601.11002/) (2026)
- [CA*: Addressing Evaluation Pitfalls in Computation-Aware Latency for Simultaneous Speech Translation](https://mlsanity.com/paper/2410.16011/) (2024)
- [Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategies](https://mlsanity.com/paper/2509.21801/) (2025)
- [Rubric-Aligned Disentangled Evaluation of Human Simultaneous Interpreting](https://mlsanity.com/paper/2609.11131/) (2026)

## Abstract (arXiv)

Simultaneous translation is a task in which translation begins before the speaker has finished speaking. In its evaluation, we have to consider the latency of the translation in addition to the quality. The latency is preferably as small as possible for users to comprehend what the speaker says with a small delay. Existing latency metrics focus on when the translation starts but do not consider adequately when the translation ends. This means such metrics do not penalize the latency caused by a long translation output, which actually delays users' comprehension. In this work, we propose a novel latency evaluation metric called Average Token Delay (ATD) that focuses on the end timings of partial translations in simultaneous translation. We discuss the advantage of ATD using simulated examples and also investigate the differences between ATD and Average Lagging with simultaneous translation experiments.