# Attention as a Guide for Simultaneous Speech Translation

arXiv: https://arxiv.org/abs/2212.07850 · HTML: https://mlsanity.com/paper/2212.07850/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 56 of its 86 references that are in the map.
- First posted on arXiv 15 Dec 2022.

## Builds on (most cited first, 30 of 56)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [Sequence-Level Knowledge Distillation](https://mlsanity.com/paper/1606.07947/) (2016)
- [Generating Sequences With Recurrent Neural Networks](https://mlsanity.com/paper/1308.0850/) (2013)
- [Listen, Attend and Spell](https://mlsanity.com/paper/1508.01211/) (2015)
- [Revealing the Dark Secrets of BERT](https://mlsanity.com/paper/1908.08593/) (2019)
- [Analyzing the Structure of Attention in a Transformer Language Model](https://mlsanity.com/paper/1906.04284/) (2019)
- [fairseq S2T: Fast Speech-to-Text Modeling with fairseq](https://mlsanity.com/paper/2010.05171/) (2020)
- [SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddings](https://mlsanity.com/paper/2004.08728/) (2020)
- [End-to-End Attention-based Large Vocabulary Speech Recognition](https://mlsanity.com/paper/1508.04395/) (2015)
- [Recent Developments on ESPnet Toolkit Boosted by Conformer](https://mlsanity.com/paper/2010.13956/) (2020)
- [Sequence-to-Sequence Models Can Directly Translate Foreign Speech](https://mlsanity.com/paper/1703.08581/) (2017)
- [Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation](https://mlsanity.com/paper/1612.01744/) (2016)
- [Monotonic Infinite Lookback Attention for Simultaneous Machine Translation](https://mlsanity.com/paper/1906.05218/) (2019)
- [SimulEval: An Evaluation Toolkit for Simultaneous Translation](https://mlsanity.com/paper/2007.16193/) (2020)
- [Monotonic Multihead Attention](https://mlsanity.com/paper/1909.12406/) (2019)
- [Do Attention Heads in BERT Track Syntactic Dependencies?](https://mlsanity.com/paper/1911.12246/) (2019)
- [Online and Linear-Time Attention by Enforcing Monotonic Alignments](https://mlsanity.com/paper/1704.00784/) (2017)
- [SimulMT to SimulST: Adapting Simultaneous Text Translation to End-to-End Simultaneous Speech Translation](https://mlsanity.com/paper/2011.02048/) (2020)
- [Jointly Learning to Align and Translate with Transformer Models](https://mlsanity.com/paper/1909.02074/) (2019)
- [Over-Generation Cannot Be Rewarded: Length-Adaptive Average Lagging for Simultaneous Speech Translation](https://mlsanity.com/paper/2206.05807/) (2022)
- [Squeezeformer: An Efficient Transformer for Automatic Speech Recognition](https://mlsanity.com/paper/2206.00888/) (2022)
- [Low-Latency Sequence-to-Sequence Speech Recognition and Translation by Partial Hypothesis Selection](https://mlsanity.com/paper/2005.11185/) (2020)
- [CTC-based Compression for Direct Speech Translation](https://mlsanity.com/paper/2102.01578/) (2021)

## Built on by (most cited first, 30 of 32)

- [LLaMA-Omni: Seamless Speech Interaction with Large Language Models](https://mlsanity.com/paper/2409.06666/) (2024)
- [AlignAtt: Using Attention-based Audio-Translation Alignments as a Guide for Simultaneous Speech Translation](https://mlsanity.com/paper/2305.11408/) (2023)
- [TransLLaMa: LLM-based Simultaneous Translation System](https://mlsanity.com/paper/2402.04636/) (2024)
- [StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning](https://mlsanity.com/paper/2406.03049/) (2024)
- [StreamAtt: Direct Streaming Speech-to-Text Translation with Attention-based Audio History Selection](https://mlsanity.com/paper/2406.06097/) (2024)
- [How "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?](https://mlsanity.com/paper/2412.18495/) (2024)
- [Towards Achieving Human Parity on End-to-end Simultaneous Speech Translation via LLM Agent](https://mlsanity.com/paper/2407.21646/) (2024)
- [Efficient and Adaptive Simultaneous Speech Translation with Fully Unidirectional Architecture](https://mlsanity.com/paper/2504.11809/) (2025)
- [A Non-autoregressive Generation Framework for End-to-End Simultaneous Speech-to-Speech Translation](https://mlsanity.com/paper/2406.06937/) (2024)
- [End-to-End Speech-to-Text Translation: A Survey](https://mlsanity.com/paper/2312.01053/) (2023)
- [Simul-Whisper: Attention-Guided Streaming Whisper with Truncation Detection](https://mlsanity.com/paper/2406.10052/) (2024)
- [FASST: Fast LLM-based Simultaneous Speech Translation](https://mlsanity.com/paper/2408.09430/) (2024)
- [Direct Models for Simultaneous Translation and Automatic Subtitling: FBK@IWSLT2023](https://mlsanity.com/paper/2309.15554/) (2023)
- [StreamUni: Achieving Streaming Speech Translation with a Unified Large Speech-Language Model](https://mlsanity.com/paper/2507.07803/) (2025)
- [Recent Advances in End-to-End Simultaneous Speech Translation](https://mlsanity.com/paper/2406.00497/) (2024)
- [Label-Synchronous Neural Transducer for E2E Simultaneous Speech Translation](https://mlsanity.com/paper/2406.04541/) (2024)
- [Large Language Models Are Read/Write Policy-Makers for Simultaneous Generation](https://mlsanity.com/paper/2501.00868/) (2025)
- [Overcoming Non-monotonicity in Transducer-based Streaming Generation](https://mlsanity.com/paper/2411.17170/) (2024)
- [Simultaneous Interpretation Corpus Construction by Large Language Models in Distant Language Pair](https://mlsanity.com/paper/2404.12299/) (2024)
- [SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translation](https://mlsanity.com/paper/2504.15509/) (2025)
- [SASST: Leveraging Syntax-Aware Chunking and LLMs for Simultaneous Speech Translation](https://mlsanity.com/paper/2508.07781/) (2025)
- [SimulMEGA: MoE Routers are Advanced Policy Makers for Simultaneous Speech Translation](https://mlsanity.com/paper/2509.01200/) (2025)
- [SBAAM! Eliminating Transcript Dependency in Automatic Subtitling](https://mlsanity.com/paper/2405.10741/) (2024)
- [SimulSeamless: FBK at IWSLT 2024 Simultaneous Speech Translation](https://mlsanity.com/paper/2406.14177/) (2024)
- [Cross-Attention is Half Explanation in Speech-to-Text Models](https://mlsanity.com/paper/2509.18010/) (2025)
- [Streaming Translation and Transcription Through Speech-to-Text Causal Alignment](https://mlsanity.com/paper/2603.11578/) (2026)
- [DOA: Training-Free Decoder-Only Attention Policy for Long-Form Simultaneous Translation with SpeechLLMs](https://mlsanity.com/paper/2605.31432/) (2026)
- [CA*: Addressing Evaluation Pitfalls in Computation-Aware Latency for Simultaneous Speech Translation](https://mlsanity.com/paper/2410.16011/) (2024)
- [Overcoming Latency Bottlenecks in On-Device Speech Translation: A Cascaded Approach with Alignment-Based Streaming MT](https://mlsanity.com/paper/2508.13358/) (2025)
- [Direct Simultaneous Translation Activation for Large Audio-Language Models](https://mlsanity.com/paper/2509.15692/) (2025)

## Abstract (arXiv)

The study of the attention mechanism has sparked interest in many fields, such as language modeling and machine translation. Although its patterns have been exploited to perform different tasks, from neural network understanding to textual alignment, no previous work has analysed the encoder-decoder attention behavior in speech translation (ST) nor used it to improve ST on a specific task. In this paper, we fill this gap by proposing an attention-based policy (EDAtt) for simultaneous ST (SimulST) that is motivated by an analysis of the existing attention relations between audio input and textual output. Its goal is to leverage the encoder-decoder attention scores to guide inference in real time. Results on en->{de, es} show that the EDAtt policy achieves overall better results compared to the SimulST state of the art, especially in terms of computational-aware latency.