mlsanityData to 7 Oct 2026

Efficient Monotonic Multihead Attention

arXiv 2312.04515 ↗First posted 7 Dec 2023cs.CLcited by 8

Not on the map. Why?

Abstract (arXiv)

We introduce the Efficient Monotonic Multihead Attention (EMMA), a state-of-the-art simultaneous translation model with numerically-stable and unbiased monotonic alignment estimation. In addition, we present improved training and inference strategies, including simultaneous fine-tuning from an offline translation model and reduction of monotonic alignment variance. The experimental results demonstrate that the proposed model attains state-of-the-art performance in simultaneous speech-to-text translation on the Spanish and English translation task.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 19 of its 24 references that are in the map. First posted on arXiv 7 Dec 2023.

Builds on

19 of 24 references.

References · 19

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  3. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  4. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,028
  5. 2017Sequence-to-Sequence Models Can Directly Translate Foreign Speechcited by 121
  6. 2016Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translationcited by 113
  7. 2019Monotonic Infinite Lookback Attention for Simultaneous Machine Translationcited by 103
  8. 2016Learning to Translate in Real-time with Neural Machine Translationcited by 97
  9. 2020SimulEval: An Evaluation Toolkit for Simultaneous Translationcited by 94
  10. 2019Monotonic Multihead Attentioncited by 91
  11. 2016Can neural machine translation do simultaneous translation?cited by 85
  12. 2017Online and Linear-Time Attention by Enforcing Monotonic Alignmentscited by 85
7 more
  1. 2017Monotonic Chunkwise Attentioncited by 82
  2. 2020ESPnet-ST: All-in-One Speech Translation Toolkitcited by 82
  3. 2020SimulMT to SimulST: Adapting Simultaneous Text Translation to End-to-End Simultaneous Speech Translationcited by 80
  4. 2018End-to-End Automatic Speech Translation of Audiobookscited by 65
  5. 2022UnitY: Two-pass Direct Speech-to-speech Translation with Discrete Unitscited by 60
  6. 2018Incremental Decoding and Training Methods for Simultaneous Translation in Neural Machine Translationcited by 51
  7. 2018Low-Resource Speech-to-Text Translationcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 2; 2026: 2.

8 papers.

  1. 2024BESTOW: Efficient and Streamable Speech Language Model with the Best of Two Worlds in GPT and T5cited by 18
  2. 2024How "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?cited by 17
  3. 2024Speech ReaLLM -- Real-time Streaming Speech Recognition with Multimodal LLMs by Teaching the Flow of Timecited by 14
  4. 2024Navigating the Minefield of MT Beam Search in Cascaded Streaming Speech Translationcited by 3
  5. 2025SimulMEGA: MoE Routers are Advanced Policy Makers for Simultaneous Speech Translationcited by 2
  6. 2025Overcoming Latency Bottlenecks in On-Device Speech Translation: A Cascaded Approach with Alignment-Based Streaming MTcited by 0
  7. 2026Regularized Entropy Information Adaptation with Temporal-Awareness Networks for Simultaneous Speech Translationcited by 0
  8. 2026Attention-Based Adaptive Policies for Simultaneous Speech-to-Text Translationcited by 0