SD-Eval

# SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words

[](https://arxiv.org/abs/2406.13340)

SD-Eval is a benchmark dataset aimed at multidimensional evaluation of spoken dialogue understanding and generation.
SD-Eval focuses on paralinguistic and environmental information and includes 7,303 utterances, amounting to 8.76 hours of speech data.
The data is aggregated from eight public datasets, representing four perspectives: emotion, accent, age, and background sound.

## 🛫️ Get Started

Please follow the instruction in [here](https://github.com/amphionspace/SD-Eval) to load the datasets.

## Citation
```
@article{ao2024sdeval,
title = {SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words},
author = {Junyi Ao and Yuancheng Wang and Xiaohai Tian and Dekun Chen and Jun Zhang and Lu Lu and Yuxuan Wang and Haizhou Li and Zhizheng Wu},
eprint={2406.13340},
archivePrefix={arXiv},
primaryClass={cs.CL},
year={2024}
}
```

## Disclaimer
Your access to and use of this dataset are at your own risk. We do not guarantee the accuracy of this dataset. The dataset is provided “as is” and we make no warranty or representation to you with respect to it and we expressly disclaim, and hereby expressly waive, all warranties, express, implied, statutory or otherwise. This includes, without limitation, warranties of quality, performance, merchantability or fitness for a particular purpose, non-infringement, absence of latent or other defects, accuracy, or the presence or absence of errors, whether or not known or discoverable. In no event will we be liable to you on any legal theory (including, without limitation, negligence) or otherwise for any direct, special, indirect, incidental, consequential, punitive, exemplary, or other losses, costs, expenses, or damages arising out of this public license or use of the licensed material. The disclaimer of warranties and limitation of liability provided above shall be interpreted in a manner that, to the extent possible, most closely approximates an absolute disclaimer and waiver of all liability.

# SD-Eval：超越文字的口语对话理解基准数据集

[](https://arxiv.org/abs/2406.13340)

SD-Eval是一款面向口语对话理解与生成的多维度评估基准数据集。

SD-Eval聚焦副语言与环境信息，共包含7303条话语，总语音时长达8.76小时。该数据集由8个公开数据集聚合而成，覆盖情感、口音、年龄与背景音四大评估维度。

## 🛫️ 快速上手

请遵循[此处](https://github.com/amphionspace/SD-Eval)的指引加载该数据集。

## 引用格式

@article{ao2024sdeval,
title = {SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words},
author = {Junyi Ao and Yuancheng Wang and Xiaohai Tian and Dekun Chen and Jun Zhang and Lu Lu and Yuxuan Wang and Haizhou Li and Zhizheng Wu},
eprint={2406.13340},
archivePrefix={arXiv},
primaryClass={cs.CL},
year={2024}
}

## 免责声明

您对本数据集的访问与使用风险自行承担。我方不保证本数据集的准确性。本数据集按"现状"提供，我方未就其作出任何明示或默示的担保、陈述或声明，并明确排除与放弃所有形式的担保，包括但不限于明示担保、默示担保、法定担保及其他形式的担保。前述担保范围包括但不限于质量、性能、适销性、特定用途适用性、不侵权、无潜在或其他缺陷、数据准确性，以及错误的存在与否，无论该错误是否已知或可被发现。在任何情况下，无论基于何种法律理论（包括但不限于过失），我方均不对因本公开许可协议或使用许可材料而产生的任何直接、特殊、间接、附带、继发性、惩罚性、惩戒性或其他损失、成本、费用或损害承担责任。上述免责声明与责任限制条款应在最大可能的范围内被解释为近乎绝对的免责与责任放弃。