# Towards Achieving Human Parity on End-to-end Simultaneous Speech Translation via LLM Agent

arXiv: https://arxiv.org/abs/2407.21646 · HTML: https://mlsanity.com/paper/2407.21646/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 53 of its 82 references that are in the map.
- First posted on arXiv 31 Jul 2024.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 53)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [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)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://mlsanity.com/paper/2202.03555/) (2022)
- [Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models](https://mlsanity.com/paper/2311.07919/) (2023)
- [FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech](https://mlsanity.com/paper/2205.12446/) (2022)
- [Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages](https://mlsanity.com/paper/2303.01037/) (2023)
- [Wav2CLIP: Learning Robust Audio Representations From CLIP](https://mlsanity.com/paper/2110.11499/) (2021)
- [Seamless: Multilingual Expressive and Streaming Speech Translation](https://mlsanity.com/paper/2312.05187/) (2023)
- [Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis](https://mlsanity.com/paper/2304.04675/) (2023)
- [Learning to Translate in Real-time with Neural Machine Translation](https://mlsanity.com/paper/1610.00388/) (2016)
- [Document-Level Machine Translation with Large Language Models](https://mlsanity.com/paper/2304.02210/) (2023)
- [Can neural machine translation do simultaneous translation?](https://mlsanity.com/paper/1606.02012/) (2016)
- [SimulMT to SimulST: Adapting Simultaneous Text Translation to End-to-End Simultaneous Speech Translation](https://mlsanity.com/paper/2011.02048/) (2020)
- [CoVoST 2 and Massively Multilingual Speech-to-Text Translation](https://mlsanity.com/paper/2007.10310/) (2020)
- [Scientific Credibility of Machine Translation Research: A Meta-Evaluation of 769 Papers](https://mlsanity.com/paper/2106.15195/) (2021)
- [CoVoST: A Diverse Multilingual Speech-To-Text Translation Corpus](https://mlsanity.com/paper/2002.01320/) (2020)
- [Over-Generation Cannot Be Rewarded: Length-Adaptive Average Lagging for Simultaneous Speech Translation](https://mlsanity.com/paper/2206.05807/) (2022)
- [Eliciting the Translation Ability of Large Language Models via Multilingual Finetuning with Translation Instructions](https://mlsanity.com/paper/2305.15083/) (2023)

## Built on by (most cited first, 14 of 14)

- [LLM Agents for Education: Advances and Applications](https://mlsanity.com/paper/2503.11733/) (2025)
- [SeqPO-SiMT: Sequential Policy Optimization for Simultaneous Machine Translation](https://mlsanity.com/paper/2505.20622/) (2025)
- [Seed LiveInterpret 2.0: End-to-end Simultaneous Speech-to-speech Translation with Your Voice](https://mlsanity.com/paper/2507.17527/) (2025)
- [StreamUni: Achieving Streaming Speech Translation with a Unified Large Speech-Language Model](https://mlsanity.com/paper/2507.07803/) (2025)
- [LLMs Can Achieve High-quality Simultaneous Machine Translation as Efficiently as Offline](https://mlsanity.com/paper/2504.09570/) (2025)
- [Spatial Speech Translation: Translating Across Space With Binaural Hearables](https://mlsanity.com/paper/2504.18715/) (2025)
- [From Tens of Hours to Tens of Thousands: Scaling Back-Translation for Speech Recognition](https://mlsanity.com/paper/2505.16972/) (2025)
- [PHRASED: Phrase Dictionary Biasing for Speech Translation](https://mlsanity.com/paper/2506.09175/) (2025)
- [Hierarchical Policy Optimization for Simultaneous Translation of Unbounded Speech](https://mlsanity.com/paper/2604.21045/) (2026)
- [Toward Machine Interpreting: Lessons from Human Interpreting Studies](https://mlsanity.com/paper/2508.07964/) (2025)
- [SimulSense: Sense-Driven Interpreting for Efficient Simultaneous Speech Translation](https://mlsanity.com/paper/2509.21932/) (2025)
- [Regularized Entropy Information Adaptation with Temporal-Awareness Networks for Simultaneous Speech Translation](https://mlsanity.com/paper/2604.09916/) (2026)
- [Bridging the Usability Gap: Lessons from Interpreting Studies for Machine Interpreting Design](https://mlsanity.com/paper/2606.16009/) (2026)
- [EviSI: An Evidence-Based Evaluation Agent for Simultaneous Interpreting](https://mlsanity.com/paper/2609.08171/) (2026)

## Abstract (arXiv)

In this paper, we present Cross Language Agent -- Simultaneous Interpretation, CLASI, a high-quality and human-like Simultaneous Speech Translation (SiST) System. Inspired by professional human interpreters, we utilize a novel data-driven read-write strategy to balance the translation quality and latency. To address the challenge of translating in-domain terminologies, CLASI employs a multi-modal retrieving module to obtain relevant information to augment the translation. Supported by LLMs, our approach can generate error-tolerated translation by considering the input audio, historical context, and retrieved information. Experimental results show that our system outperforms other systems by significant margins. Aligned with professional human interpreters, we evaluate CLASI with a better human evaluation metric, valid information proportion (VIP), which measures the amount of information that can be successfully conveyed to the listeners. In the real-world scenarios, where the speeches are often disfluent, informal, and unclear, CLASI achieves VIP of 81.3% and 78.0% for Chinese-to-English and English-to-Chinese translation directions, respectively. In contrast, state-of-the-art commercial or open-source systems only achieve 35.4% and 41.6%. On the extremely hard dataset, where other systems achieve under 13% VIP, CLASI can still achieve 70% VIP.