# Don't Discard Fixed-Window Audio Segmentation in Speech-to-Text Translation

arXiv: https://arxiv.org/abs/2210.13363 · HTML: https://mlsanity.com/paper/2210.13363/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 32 references that are in the map.
- First posted on arXiv 24 Oct 2022.

## Builds on (most cited first, 18 of 18)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [The Multilingual TEDx Corpus for Speech Recognition and Translation](https://mlsanity.com/paper/2102.01757/) (2021)
- [Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Task](https://mlsanity.com/paper/2107.05782/) (2021)
- [A General Multi-Task Learning Framework to Leverage Text Data for Speech to Text Tasks](https://mlsanity.com/paper/2010.11338/) (2020)
- [Low-Latency Neural Speech Translation](https://mlsanity.com/paper/1808.00491/) (2018)
- [Re-translation versus Streaming for Simultaneous Translation](https://mlsanity.com/paper/2004.03643/) (2020)
- [SHAS: Approaching optimal Segmentation for End-to-End Speech Translation](https://mlsanity.com/paper/2202.04774/) (2022)
- [Re-Translation Strategies For Long Form, Simultaneous, Spoken Language Translation](https://mlsanity.com/paper/1912.03393/) (2019)
- [Beyond Voice Activity Detection: Hybrid Audio Segmentation for Direct Speech Translation](https://mlsanity.com/paper/2104.11710/) (2021)
- [Efficient yet Competitive Speech Translation: FBK@IWSLT2022](https://mlsanity.com/paper/2205.02629/) (2022)
- [Contextualized Translation of Automatically Segmented Speech](https://mlsanity.com/paper/2008.02270/) (2020)
- [Sentence Boundary Augmentation For Neural Machine Translation Robustness](https://mlsanity.com/paper/2010.11132/) (2020)
- [Dealing with training and test segmentation mismatch: FBK@IWSLT2021](https://mlsanity.com/paper/2106.12607/) (2021)
- [FST: the FAIR Speech Translation System for the IWSLT21 Multilingual Shared Task](https://mlsanity.com/paper/2107.06959/) (2021)
- [On the Impact of Noises in Crowd-Sourced Data for Speech Translation](https://mlsanity.com/paper/2206.13756/) (2022)
- [Simultaneous Translation for Unsegmented Input: A Sliding Window Approach](https://mlsanity.com/paper/2210.09754/) (2022)
- [Presenting Simultaneous Translation in Limited Space](https://mlsanity.com/paper/2009.09016/) (2020)

## Built on by (most cited first, 8 of 8)

- [How "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?](https://mlsanity.com/paper/2412.18495/) (2024)
- [Pitfalls and Outlooks in Using COMET](https://mlsanity.com/paper/2408.15366/) (2024)
- [SegAugment: Maximizing the Utility of Speech Translation Data with Segmentation-based Augmentations](https://mlsanity.com/paper/2212.09699/) (2022)
- [Evaluating the IWSLT2023 Speech Translation Tasks: Human Annotations, Automatic Metrics, and Segmentation](https://mlsanity.com/paper/2406.03881/) (2024)
- [Better Late Than Never: Meta-Evaluation of Latency Metrics for Simultaneous Speech-to-Text Translation](https://mlsanity.com/paper/2509.17349/) (2025)
- [Long-form Simultaneous Speech Translation: Thesis Proposal](https://mlsanity.com/paper/2310.11141/) (2023)
- [Early-Exit and Instant Confidence Translation Quality Estimation](https://mlsanity.com/paper/2502.14429/) (2025)
- [Why We Need Speech to Evaluate Speech Translation](https://mlsanity.com/paper/2605.28227/) (2026)

## Abstract (arXiv)

For real-life applications, it is crucial that end-to-end spoken language translation models perform well on continuous audio, without relying on human-supplied segmentation. For online spoken language translation, where models need to start translating before the full utterance is spoken, most previous work has ignored the segmentation problem. In this paper, we compare various methods for improving models' robustness towards segmentation errors and different segmentation strategies in both offline and online settings and report results on translation quality, flicker and delay. Our findings on five different language pairs show that a simple fixed-window audio segmentation can perform surprisingly well given the right conditions.