mlsanityData to 14 Oct 2026

On Using SpecAugment for End-to-End Speech Translation

arXiv 1911.08876 ↗First posted 20 Nov 2019cs.CL cs.LG eess.AScited by 19

Not on the map. Why?

Abstract (arXiv)

This work investigates a simple data augmentation technique, SpecAugment, for end-to-end speech translation. SpecAugment is a low-cost implementation method applied directly to the audio input features and it consists of masking blocks of frequency channels, and/or time steps. We apply SpecAugment on end-to-end speech translation tasks and achieve up to +2.2% BLEU on LibriSpeech Audiobooks En->Fr and +1.2% on IWSLT TED-talks En->De by alleviating overfitting to some extent. We also examine the effectiveness of the method in a variety of data scenarios and show that the method also leads to significant improvements in various data conditions irrespective of the amount of training data.

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 9; 2022: 4; 2023: 5; 2024: 0; 2025: 1.

19 papers.

Sort:

By area:

  1. 2022STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translationcited by 57
  2. 2021Cascade versus Direct Speech Translation: Do the Differences Still Make a Difference?cited by 54
  3. 2021Learning Shared Semantic Space for Speech-to-Text Translationcited by 49
  4. 2021RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformercited by 40
  5. 2021Learning When to Translate for Streaming Speechcited by 30
  6. 2021End-to-End Speech Translation with Pre-trained Models and Adapters: UPC at IWSLT 2021cited by 16
  7. 2023Understanding and Bridging the Modality Gap for Speech Translationcited by 15
  8. 2023Recent Advances in Direct Speech-to-text Translationcited by 15
  9. 2021How to Split: the Effect of Word Segmentation on Gender Bias in Speech Translationcited by 11
  10. 2023ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text Translationcited by 9
  11. 2023Tuning Large language model for End-to-end Speech Translationcited by 9
  12. 2021Dealing with training and test segmentation mismatch: FBK@IWSLT2021cited by 6
7 more
  1. 2022Discrete Cross-Modal Alignment Enables Zero-Shot Speech Translationcited by 6
  2. 2022SegAugment: Maximizing the Utility of Speech Translation Data with Segmentation-based Augmentationscited by 6
  3. 2022Does Joint Training Really Help Cascaded Speech Translation?cited by 5
  4. 2023Improving speech translation by fusing speech and textcited by 3
  5. 2021Multilingual Speech Translation with Unified Transformer: Huawei Noah's Ark Lab at IWSLT 2021cited by 1
  6. 2021The IWSLT 2021 BUT Speech Translation Systemscited by 0
  7. 2025AdaST: Dynamically Adapting Encoder States in the Decoder for End-to-End Speech-to-Text Translationcited by 0