Soul-AILab/SoulX-Duplug-Eval

---
license: apache-2.0
language:
- en
- zh
---

<div align="center">
<h1>
SoulX-Duplug
</h1>
<p>
Official code for enabling full-duplex speech interaction with<br>
<b><em>SoulX-Duplug: Plug-and-Play Streaming State Prediction Module for Realtime Full-Duplex Speech Conversation</em></b>
</p>
<p>
<img src="SoulX-Duplug-logo.png" alt="SoulX-Duplug Logo" style="width: 200px; height: 200px;">
</p>
<p>
</p>
<a href="https://soulx-duplug.sjtuxlance.com/"><img src="https://img.shields.io/badge/🌐%20Online-Demo-blue" alt="Online Demo"></a>
<a href="https://arxiv.org/abs/2603.14877"><img src="https://img.shields.io/badge/arXiv-2603.14877-B31B1B?logo=arxiv&logoColor=white.svg" alt="arXiv"></a>
<a href="https://github.com/Soul-AILab/SoulX-Duplug"><img src='https://img.shields.io/badge/Github-Page-yellow?logo=github&logoColor=white.svg' alt="Github"></a>
<a href="https://github.com/Soul-AILab/SoulX-Duplug"><img src="https://img.shields.io/badge/License-Apache%202.0-green.svg" alt="Apache-2.0"></a>
</div>

## ✨ Overview
SoulX-Duplug is a **plug-and-play streaming semantic VAD model** designed for real-time full-duplex speech conversation. Through text-guided streaming state prediction, SoulX-Duplug enables low-latency, semantic-aware streaming dialogue management. In addition to the core model, we also **open-source a [dialogue system](https://github.com/Soul-AILab/SoulX-Duplug/tree/dialogue-system) build on top of SoulX-Duplug**, which demonstrates the practicality of our model in real-world applications.

To facilitate benchmarking and research in this area, we also release **[SoulX-Duplug-Eval](https://huggingface.co/datasets/Soul-AILab/SoulX-Duplug-Eval)**, a complementary evaluation set for benchmarking full-duplex spoken dialogue systems.

## 🧪 SoulX-Duplug-Eval

- [Easy-Turn-Testset-en.zip](https://huggingface.co/datasets/Soul-AILab/SoulX-Duplug-Eval/blob/main/Easy-Turn-Testset-en.zip) contains the English counterpart of the original [Easy Turn testset](https://huggingface.co/datasets/ASLP-lab/Easy-Turn-Testset). It focuses on duplex state prediction and contains two categories: *Complete* and *Incomplete*. The *Complete* category consists of 318 semantically complete utterances. The *Incomplete* category contains 299 semantically incomplete samples.
- [Full-Duplex-Bench-zh.zip](https://huggingface.co/datasets/Soul-AILab/SoulX-Duplug-Eval/blob/main/Full-Duplex-Bench-zh.zip) is a Chinese counterpart to [Full-Duplex-Bench](https://github.com/DanielLin94144/Full-Duplex-Bench). The dataset covers four representative interaction scenarios: *Turn Taking* (155 samples), *Pause Handling* (239 samples), *User Backchannel* (199 samples), and *User Interruption* (161 samples). The testsets follow the same format as Full-Duplex-Bench and can be directly evaluated using the official evaluation pipeline.

## 🔖 Citation
If you find this work useful in your research, please consider citing:

```bibtex
@misc{yan2026soulxduplug,
title={SoulX-Duplug: Plug-and-Play Streaming State Prediction Module for Realtime Full-Duplex Speech Conversation},
author={Ruiqi Yan and Wenxi Chen and Zhanxun Liu and Ziyang Ma and Haopeng Lin and Hanlin Wen and Hanke Xie and Jun Wu and Yuzhe Liang and Yuxiang Zhao and Pengchao Feng and Jiale Qian and Hao Meng and Yuhang Dai and Shunshun Yin and Ming Tao and Lei Xie and Kai Yu and Xinsheng Wang and Xie Chen},
year={2026},
eprint={2603.14877},
archivePrefix={arXiv},
primaryClass={eess.AS},
url={https://arxiv.org/abs/2603.14877},
}
```

## 📜 License
This project is licensed under the [Apache 2.0 License](https://github.com/Soul-AILab/SoulX-Duplug/blob/main/LICENSE).

## 🙏 Acknowledgment
We greatly thank [Easy Turn](https://github.com/ASLP-lab/Easy-Turn) and [Full-Duplex-Bench](https://github.com/DanielLin94144/Full-Duplex-Bench) for their contributions.

---
许可证：Apache-2.0
语言：
- 英语
- 汉语
---

<div align="center">
<h1>
SoulX-Duplug
</h1>
<p>
本项目为实现全双工语音交互的官方代码，对应研究论文为《SoulX-Duplug：面向实时全双工语音对话的即插即用流式状态预测模块》
</p>
<p>
<img src="SoulX-Duplug-logo.png" alt="SoulX-Duplug 标识" style="width: 200px; height: 200px;">
</p>
<p>
</p>
<a href="https://soulx-duplug.sjtuxlance.com/"><img src="https://img.shields.io/badge/🌐%20Online-Demo-blue" alt="在线演示"></a>
<a href="https://arxiv.org/abs/2603.14877"><img src="https://img.shields.io/badge/arXiv-2603.14877-B31B1B?logo=arxiv&logoColor=white.svg" alt="arXiv"></a>
<a href="https://github.com/Soul-AILab/SoulX-Duplug"><img src='https://img.shields.io/badge/Github-Page-yellow?logo=github&logoColor=white.svg' alt="GitHub 仓库"></a>
<a href="https://github.com/Soul-AILab/SoulX-Duplug"><img src="https://img.shields.io/badge/License-Apache%202.0-green.svg" alt="Apache-2.0 许可证"></a>
</div>

## ✨ 概述
SoulX-Duplug是一款面向实时全双工语音对话的**即插即用流式语义语音活动检测（VAD）模型**。通过文本引导的流式状态预测，SoulX-Duplug可实现低延迟、语义感知的流式对话管理。除核心模型外，我们还开源了基于SoulX-Duplug构建的对话系统（https://github.com/Soul-AILab/SoulX-Duplug/tree/dialogue-system），展示了本模型在实际应用中的实用性。

为推动该领域的基准测试与研究，我们同时发布了**SoulX-Duplug-Eval评测数据集**（https://huggingface.co/datasets/Soul-AILab/SoulX-Duplug-Eval），这是一套用于全双工语音对话系统基准测试的配套评测集。

## 🧪 SoulX-Duplug-Eval
- 【Easy-Turn-Testset-en.zip】（https://huggingface.co/datasets/Soul-AILab/SoulX-Duplug-Eval/blob/main/Easy-Turn-Testset-en.zip）为原版[Easy Turn测试集](https://huggingface.co/datasets/ASLP-lab/Easy-Turn-Testset)的英文版本，聚焦双工状态预测任务，分为*完整*与*不完整*两个类别。其中*完整*类别包含318条语义完整的话语，*不完整*类别包含299条语义不完整的样本。
- 【Full-Duplex-Bench-zh.zip】（https://huggingface.co/datasets/Soul-AILab/SoulX-Duplug-Eval/blob/main/Full-Duplex-Bench-zh.zip）为[Full-Duplex-Bench](https://github.com/DanielLin94144/Full-Duplex-Bench)的中文版本。该数据集涵盖四类典型交互场景：*轮次切换*（155条样本）、*停顿处理*（239条样本）、*用户反馈语*（199条样本）以及*用户插话*（161条样本）。该测试集与Full-Duplex-Bench格式一致，可直接使用官方评测流程进行评估。

## 🔖 引用说明
若您的研究中用到本项目成果，请引用如下文献：
bibtex
@misc{yan2026soulxduplug,
title={SoulX-Duplug: Plug-and-Play Streaming State Prediction Module for Realtime Full-Duplex Speech Conversation},
author={Ruiqi Yan and Wenxi Chen and Zhanxun Liu and Ziyang Ma and Haopeng Lin and Hanlin Wen and Hanke Xie and Jun Wu and Yuzhe Liang and Yuxiang Zhao and Pengchao Feng and Jiale Qian and Hao Meng and Yuhang Dai and Shunshun Yin and Ming Tao and Lei Xie and Kai Yu and Xinsheng Wang and Xie Chen},
year={2026},
eprint={2603.14877},
archivePrefix={arXiv},
primaryClass={eess.AS},
url={https://arxiv.org/abs/2603.14877},
}

## 📜 许可证
本项目采用[Apache 2.0开源许可协议](https://github.com/Soul-AILab/SoulX-Duplug/blob/main/LICENSE)进行授权。

## 🙏 致谢
衷心感谢[Easy Turn](https://github.com/ASLP-lab/Easy-Turn)与[Full-Duplex-Bench](https://github.com/DanielLin94144/Full-Duplex-Bench)项目组的开源贡献。