mlsanityData to 14 Oct 2026

End-to-End Speech Translation with Knowledge Distillation

arXiv 1904.08075 ↗First posted 17 Apr 2019cs.CLcited by 58

Not on the map. Why?

Abstract (arXiv)

End-to-end speech translation (ST), which directly translates from source language speech into target language text, has attracted intensive attentions in recent years. Compared to conventional pipeline systems, end-to-end ST models have advantages of lower latency, smaller model size and less error propagation. However, the combination of speech recognition and text translation in one model is more difficult than each of these two tasks. In this paper, we propose a knowledge distillation approach to improve ST model by transferring the knowledge from text translation model. Specifically, we first train a text translation model, regarded as a teacher model, and then ST model is trained to learn output probabilities from teacher model through knowledge distillation. Experiments on English- French Augmented LibriSpeech and English-Chinese TED corpus show that end-to-end ST is possible to implement on both similar and dissimilar language pairs. In addition, with the instruction of teacher model, end-to-end ST model can gain significant improvements by over 3.5 BLEU points.

Key facts. Cited by 58 papers in the map (data through 14 Oct 2026). First posted on arXiv 17 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 19; 2022: 15; 2023: 16; 2024: 3; 2025: 4; 2026: 1.

58 papers.

Sort:

By area:

  1. 2022UnitY: Two-pass Direct Speech-to-speech Translation with Discrete Unitscited by 60
  2. 2022STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translationcited by 57
  3. 2021Cascade versus Direct Speech Translation: Do the Differences Still Make a Difference?cited by 54
  4. 2021Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Taskcited by 54
  5. 2021Learning Shared Semantic Space for Speech-to-Text Translationcited by 49
  6. 2021Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained Models into Speech Translation Encoderscited by 48
  7. 2021Fused Acoustic and Text Encoding for Multimodal Bilingual Pretraining and Speech Translationcited by 47
  8. 2021RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformercited by 40
  9. 2022Large-Scale Streaming End-to-End Speech Translation with Neural Transducerscited by 31
  10. 2021Learning When to Translate for Streaming Speechcited by 30
  11. 2021Source and Target Bidirectional Knowledge Distillation for End-to-end Speech Translationcited by 28
  12. 2022Revisiting End-to-End Speech-to-Text Translation From Scratchcited by 26
38 more
  1. 2022Under the Morphosyntactic Lens: A Multifaceted Evaluation of Gender Bias in Speech Translationcited by 23
  2. 2023CMOT: Cross-modal Mixup via Optimal Transport for Speech Translationcited by 22
  3. 2022Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translationcited by 20
  4. 2022GigaST: A 10,000-hour Pseudo Speech Translation Corpuscited by 20
  5. 2023DUB: Discrete Unit Back-translation for Speech Translationcited by 18
  6. 2021Beyond Voice Activity Detection: Hybrid Audio Segmentation for Direct Speech Translationcited by 17
  7. 2021Regularizing End-to-End Speech Translation with Triangular Decomposition Agreementcited by 16
  8. 2023Understanding and Bridging the Modality Gap for Speech Translationcited by 15
  9. 2023Recent Advances in Direct Speech-to-text Translationcited by 15
  10. 2023MixSpeech: Cross-Modality Self-Learning with Audio-Visual Stream Mixup for Visual Speech Translation and Recognitioncited by 14
  11. 2021The USTC-NELSLIP Systems for Simultaneous Speech Translation Task at IWSLT 2021cited by 13
  12. 2022Leveraging Pseudo-labeled Data to Improve Direct Speech-to-Speech Translationcited by 12
  13. 2022Non-Parametric Domain Adaptation for End-to-End Speech Translationcited by 12
  14. 2021Is "moby dick" a Whale or a Bird? Named Entities and Terminology in Speech Translationcited by 11
  15. 2021Non-autoregressive End-to-end Speech Translation with Parallel Autoregressive Rescoringcited by 9
  16. 2021Fast-MD: Fast Multi-Decoder End-to-End Speech Translation with Non-Autoregressive Hidden Intermediatescited by 9
  17. 2022Improving End-to-end Speech Translation by Leveraging Auxiliary Speech and Text Datacited by 9
  18. 2023ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text Translationcited by 9
  19. 2023Tuning Large language model for End-to-end Speech Translationcited by 9
  20. 2023End-to-End Speech-to-Text Translation: A Surveycited by 9
  21. 2021Kosp2e: Korean Speech to English Translation Corpuscited by 7
  22. 2022Distilling a Pretrained Language Model to a Multilingual ASR Modelcited by 7
  23. 2023Improving Speech Translation by Cross-Modal Multi-Grained Contrastive Learningcited by 7
  24. 2021Dealing with training and test segmentation mismatch: FBK@IWSLT2021cited by 6
  25. 2021Decision Attentive Regularization to Improve Simultaneous Speech Translation Systemscited by 6
  26. 2022Discrete Cross-Modal Alignment Enables Zero-Shot Speech Translationcited by 6
  27. 2022SegAugment: Maximizing the Utility of Speech Translation Data with Segmentation-based Augmentationscited by 6
  28. 2023An Empirical Study of Consistency Regularization for End-to-End Speech-to-Text Translationcited by 6
  29. 2023Decouple Non-parametric Knowledge Distillation For End-to-end Speech Translationcited by 3
  30. 2023Improving speech translation by fusing speech and textcited by 3
  31. 2024Representation Purification for End-to-End Speech Translationcited by 3
  32. 2021AlloST: Low-resource Speech Translation without Source Transcriptioncited by 2
  33. 2023Multi-Teacher Knowledge Distillation For Text Image Machine Translationcited by 2
  34. 2024Streaming Sequence Transduction through Dynamic Compressioncited by 2
  35. 2025Matryoshka Model Learning for Improved Elastic Student Modelscited by 2
  36. 2021Multilingual Speech Translation with Unified Transformer: Huawei Noah's Ark Lab at IWSLT 2021cited by 1
  37. 2022Efficient Speech Translation with Pre-trained Modelscited by 1
  38. 2023Speech Translation with Foundation Models and Optimal Transport: UPC at IWSLT23cited by 1

50 most cited of 58 All 58 (JSON)