mlsanityData to 7 Oct 2026

Investigating the Reordering Capability in CTC-based Non-Autoregressive End-to-End Speech Translation

arXiv 2105.04840 ↗First posted 11 May 2021cs.CLcited by 23

Not on the map. Why?

Abstract (arXiv)

We study the possibilities of building a non-autoregressive speech-to-text translation model using connectionist temporal classification (CTC), and use CTC-based automatic speech recognition as an auxiliary task to improve the performance. CTC's success on translation is counter-intuitive due to its monotonicity assumption, so we analyze its reordering capability. Kendall's tau distance is introduced as the quantitative metric, and gradient-based visualization provides an intuitive way to take a closer look into the model. Our analysis shows that transformer encoders have the ability to change the word order and points out the future research direction that worth being explored more on non-autoregressive speech translation.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 22 of its 32 references that are in the map. First posted on arXiv 11 May 2021.

Builds on

22 of 32 references.

References · 22

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  3. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  4. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  5. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 554
  6. 2017Non-Autoregressive Neural Machine Translationcited by 457
  7. 2019Levenshtein Transformercited by 197
  8. 2018Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinementcited by 194
  9. 2020SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddingscited by 155
  10. 2019Insertion Transformer: Flexible Sequence Generation via Insertion Operationscited by 123
  11. 2017Sequence-to-Sequence Models Can Directly Translate Foreign Speechcited by 121
  12. 2016Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translationcited by 113
10 more
  1. 2020Non-Autoregressive Machine Translation with Latent Alignmentscited by 96
  2. 2020Speech Translation and the End-to-End Promise: Taking Stock of Where We Arecited by 77
  3. 2018End-to-End Non-Autoregressive Neural Machine Translation with Connectionist Temporal Classificationcited by 72
  4. 2018End-to-End Automatic Speech Translation of Audiobookscited by 65
  5. 2020Imputer: Sequence Modelling via Imputation and Dynamic Programmingcited by 65
  6. 2018Tied Multitask Learning for Neural Speech Translationcited by 54
  7. 2019Guiding Non-Autoregressive Neural Machine Translation Decoding with Reordering Informationcited by 37
  8. 2019Attention-Passing Models for Robust and Data-Efficient End-to-End Speech Translationcited by 30
  9. 2020Orthros: Non-autoregressive End-to-end Speech Translation with Dual-decodercited by 17
  10. 2020Worse WER, but Better BLEU? Leveraging Word Embedding as Intermediate in Multitask End-to-End Speech Translationcited by 12

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 6; 2023: 6; 2024: 6; 2025: 2.

23 papers.

Sort:

  1. 2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 138
  2. 2022A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyondcited by 64
  3. 2024OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identificationcited by 34
  4. 2022Revisiting End-to-End Speech-to-Text Translation From Scratchcited by 26
  5. 2022CTC Alignments Improve Autoregressive Translationcited by 25
  6. 2023Hybrid Transducer and Attention based Encoder-Decoder Modeling for Speech-to-Text Taskscited by 20
  7. 2023Recent Advances in Direct Speech-to-text Translationcited by 15
  8. 2022Bayes risk CTC: Controllable CTC alignment in Sequence-to-Sequence taskscited by 12
  9. 2024LLaST: Improved End-to-end Speech Translation System Leveraged by Large Language Modelscited by 12
  10. 2022Blockwise Streaming Transformer for Spoken Language Understanding and Simultaneous Speech Translationcited by 11
  11. 2021Non-autoregressive End-to-end Speech Translation with Parallel Autoregressive Rescoringcited by 9
  12. 2021Fast-MD: Fast Multi-Decoder End-to-End Speech Translation with Non-Autoregressive Hidden Intermediatescited by 9
11 more
  1. 2023CTC-based Non-autoregressive Speech Translationcited by 9
  2. 2022Anticipation-Free Training for Simultaneous Machine Translationcited by 5
  3. 2024Label-Synchronous Neural Transducer for E2E Simultaneous Speech Translationcited by 5
  4. 2024Disentangling Speakers in Multi-Talker Speech Recognition with Speaker-Aware CTCcited by 4
  5. 2024Overcoming Non-monotonicity in Transducer-based Streaming Generationcited by 4
  6. 2023Strategies for improving low resource speech to text translation relying on pre-trained ASR modelscited by 3
  7. 2023Decoupled Structure for Improved Adaptability of End-to-End Modelscited by 3
  8. 2023Efficient CTC Regularization via Coarse Labels for End-to-End Speech Translationcited by 1
  9. 2024SBAAM! Eliminating Transcript Dependency in Automatic Subtitlingcited by 1
  10. 2025Aligner-Encoders: Self-Attention Transformers Can Be Self-Transducerscited by 1
  11. 2025A Differentiable Alignment Framework for Sequence-to-Sequence Modeling via Optimal Transportcited by 0