mlsanityData to 14 Oct 2026

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

arXiv 2210.13363 ↗First posted 24 Oct 2022cs.CLcited by 8

Not on the map. Why?

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.

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

18 of 32 references.

References · 18

  1. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  2. 2020COMET: A Neural Framework for MT Evaluationcited by 1,033
  3. 2021The Multilingual TEDx Corpus for Speech Recognition and Translationcited by 101
  4. 2021Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Taskcited by 54
  5. 2020A General Multi-Task Learning Framework to Leverage Text Data for Speech to Text Taskscited by 51
  6. 2018Low-Latency Neural Speech Translationcited by 37
  7. 2020Re-translation versus Streaming for Simultaneous Translationcited by 31
  8. 2022SHAS: Approaching optimal Segmentation for End-to-End Speech Translationcited by 26
  9. 2019Re-Translation Strategies For Long Form, Simultaneous, Spoken Language Translationcited by 25
  10. 2021Beyond Voice Activity Detection: Hybrid Audio Segmentation for Direct Speech Translationcited by 17
  11. 2022Efficient yet Competitive Speech Translation: FBK@IWSLT2022cited by 14
  12. 2020Contextualized Translation of Automatically Segmented Speechcited by 12
6 more
  1. 2020Sentence Boundary Augmentation For Neural Machine Translation Robustnesscited by 10
  2. 2021Dealing with training and test segmentation mismatch: FBK@IWSLT2021cited by 6
  3. 2021FST: the FAIR Speech Translation System for the IWSLT21 Multilingual Shared Taskcited by 6
  4. 2022On the Impact of Noises in Crowd-Sourced Data for Speech Translationcited by 6
  5. 2022Simultaneous Translation for Unsegmented Input: A Sliding Window Approachcited by 6
  6. 2020Presenting Simultaneous Translation in Limited Spacecited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 3; 2025: 2; 2026: 1.

8 papers.

  1. 2024How "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?cited by 17
  2. 2024Pitfalls and Outlooks in Using COMETcited by 10
  3. 2022SegAugment: Maximizing the Utility of Speech Translation Data with Segmentation-based Augmentationscited by 6
  4. 2024Evaluating the IWSLT2023 Speech Translation Tasks: Human Annotations, Automatic Metrics, and Segmentationcited by 5
  5. 2025Better Late Than Never: Meta-Evaluation of Latency Metrics for Simultaneous Speech-to-Text Translationcited by 4
  6. 2023Long-form Simultaneous Speech Translation: Thesis Proposalcited by 3
  7. 2025Early-Exit and Instant Confidence Translation Quality Estimationcited by 2
  8. 2026Why We Need Speech to Evaluate Speech Translationcited by 1