mlsanityData to 7 Oct 2026

Online and Linear-Time Attention by Enforcing Monotonic Alignments

arXiv 1704.00784 ↗First posted 3 Apr 2017cs.LG cs.CLcited by 85

Not on the map. Why?

Abstract (arXiv)

Recurrent neural network models with an attention mechanism have proven to be extremely effective on a wide variety of sequence-to-sequence problems. However, the fact that soft attention mechanisms perform a pass over the entire input sequence when producing each element in the output sequence precludes their use in online settings and results in a quadratic time complexity. Based on the insight that the alignment between input and output sequence elements is monotonic in many problems of interest, we propose an end-to-end differentiable method for learning monotonic alignments which, at test time, enables computing attention online and in linear time. We validate our approach on sentence summarization, machine translation, and online speech recognition problems and achieve results competitive with existing sequence-to-sequence models.

Key facts. Cited by 85 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 26; 2022: 14; 2023: 18; 2024: 11; 2025: 12; 2026: 4.

85 papers.

Sort:

By area:

  1. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  2. 2021A Survey on Neural Speech Synthesiscited by 182
  3. 2024LLaMA-Omni: Seamless Speech Interaction with Large Language Modelscited by 169
  4. 2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 138
  5. 2023End-to-End Speech Recognition: A Surveycited by 127
  6. 2021WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkitcited by 123
  7. 2021Translating Images into Mapscited by 115
  8. 2024DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representationscited by 68
  9. 2021Attention, please! A survey of Neural Attention Models in Deep Learningcited by 50
  10. 2023DreamTuner: Single Image is Enough for Subject-Driven Generationcited by 41
  11. 2022Information-Transport-based Policy for Simultaneous Translationcited by 40
  12. 2024VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignmentcited by 37
38 more
  1. 2024TransLLaMa: LLM-based Simultaneous Translation Systemcited by 34
  2. 2021Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policycited by 32
  3. 2022Attention as a Guide for Simultaneous Speech Translationcited by 32
  4. 2021Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERTcited by 31
  5. 2022Large-Scale Streaming End-to-End Speech Translation with Neural Transducerscited by 31
  6. 2021Sequence-to-Sequence Learning with Latent Neural Grammarscited by 30
  7. 2023RSDiff: Remote Sensing Image Generation from Text Using Diffusion Modelcited by 28
  8. 2023Hidden Markov Transformer for Simultaneous Machine Translationcited by 24
  9. 2025Streaming Sequence-to-Sequence Learning with Delayed Streams Modelingcited by 24
  10. 2025StyleSSP: Sampling StartPoint Enhancement for Training-free Diffusion-based Method for Style Transfercited by 23
  11. 2023End-to-End Simultaneous Speech Translation with Differentiable Segmentationcited by 22
  12. 2022Modeling Dual Read/Write Paths for Simultaneous Machine Translationcited by 21
  13. 2023Hybrid Transducer and Attention based Encoder-Decoder Modeling for Speech-to-Text Taskscited by 20
  14. 2021A Survey on Deep Reinforcement Learning for Audio-Based Applicationscited by 17
  15. 2022Gaussian Multi-head Attention for Simultaneous Machine Translationcited by 17
  16. 2022Reducing Position Bias in Simultaneous Machine Translation with Length-Aware Frameworkcited by 16
  17. 2022Exploring Continuous Integrate-and-Fire for Adaptive Simultaneous Speech Translationcited by 14
  18. 2024Speech ReaLLM -- Real-time Streaming Speech Recognition with Multimodal LLMs by Teaching the Flow of Timecited by 14
  19. 2023Non-autoregressive Streaming Transformer for Simultaneous Translationcited by 12
  20. 2021Alignment Knowledge Distillation for Online Streaming Attention-based Speech Recognitioncited by 11
  21. 2022Inducing and Using Alignments for Transition-based AMR Parsingcited by 11
  22. 2024A Non-autoregressive Generation Framework for End-to-End Simultaneous Speech-to-Speech Translationcited by 10
  23. 2021On-device neural speech synthesiscited by 9
  24. 2021Direct Simultaneous Speech-to-Speech Translation with Variational Monotonic Multihead Attentioncited by 9
  25. 2023Simultaneous Machine Translation with Large Language Modelscited by 9
  26. 2023Efficient Monotonic Multihead Attentioncited by 8
  27. 2021Review of end-to-end speech synthesis technology based on deep learningcited by 6
  28. 2021Multi-mode Transformer Transducer with Stochastic Future Contextcited by 6
  29. 2021Decision Attentive Regularization to Improve Simultaneous Speech Translation Systemscited by 6
  30. 2022Compositional Generalisation with Structured Reordering and Fertility Layerscited by 6
  31. 2023Unified Segment-to-Segment Framework for Simultaneous Sequence Generationcited by 6
  32. 2026FBS: Modeling Native Parallel Reading inside a Transformercited by 6
  33. 2021Thank you for Attention: A survey on Attention-based Artificial Neural Networks for Automatic Speech Recognitioncited by 5
  34. 2021A study of latent monotonic attention variantscited by 5
  35. 2021On Biasing Transformer Attention Towards Monotonicitycited by 5
  36. 2022Anticipation-Free Training for Simultaneous Machine Translationcited by 5
  37. 2023TAPIR: Learning Adaptive Revision for Incremental Natural Language Understanding with a Two-Pass Modelcited by 5
  38. 2022Monotonic segmental attention for automatic speech recognitioncited by 4

50 most cited of 85 All 85 (JSON)